Skip to content

Instantly share code, notes, and snippets.

@liuliu
Created May 24, 2023 16:08
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 1 You must be signed in to fork a gist
  • Save liuliu/f80ceaebe36b177c4d50598ad27c782b to your computer and use it in GitHub Desktop.
Save liuliu/f80ceaebe36b177c4d50598ad27c782b to your computer and use it in GitHub Desktop.
CCV_NNC_GEMM_FORWARD [1]: [3] -> [1] (0)
|-> 1. 0x1438bd420 (0x285d90fc0:0) [2x320] 0.517578 0.953613 -0.921875 ..
|-> 2. 0x1438bd570 (0x285d841c0:0) [1280x320] -0.001888 0.001598 0.001110 ..
|-> 3. 0x1438bd5e0 (0x285d84280:0) [1280] -0.019775 0.008278 0.010788 ..
|<- 1. 0x1438a0000 (0x285da5600:0) [2x1280] 0.044556 -0.020798 0.078064 ..
CCV_NNC_SWISH_FORWARD [2]: [1] -> [1] (0)
|-> 1. 0x1438a0000 (0x285da5600:0) [2x1280] 0.044556 -0.020798 0.078064 ..
|<- 1. 0x1438a0000 (0x285da5600:0) [2x1280] 0.022781 -0.010292 0.040558 ..
CCV_NNC_GEMM_FORWARD [3]: [3] -> [1] (0)
|-> 1. 0x1438a0000 (0x285da5600:0) [2x1280] 0.022781 -0.010292 0.040558 ..
|-> 2. 0x1438bd650 (0x285d84b80:0) [1280x1280] 0.002268 0.001678 -0.003374 ..
|-> 3. 0x1438bd6c0 (0x285d85300:0) [1280] 0.006294 0.001841 -0.010101 ..
|<- 1. 0x1438a0070 (0x285da5640:0) [2x1280] -0.068420 -0.037476 -0.015541 ..
CCV_NNC_CONVOLUTION_FORWARD [4]: [3] -> [1] (1)
Wait: (1, 0)
|-> 1. 0x1438bd3b0 (0x285d90d00:0) [2x64x64x4] 1.300781 0.501465 0.404785 ..
|-> 2. 0x1438bd730 (0x285d85340:0) [320x4x3x3] -0.030701 0.085693 0.096252 ..
|-> 3. 0x1438bd7a0 (0x285d84440:0) [320] -0.096619 -0.114014 0.106323 ..
|<- 1. 0x14390db70 (0x285f78ac0:0) [2x64x64x320] -0.319092 -0.406982 0.225342 ..
CCV_NNC_GEMM_FORWARD [5]: [2] -> [1] (2)
Wait: (2, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438be290 (0x285d842c0:0) [320x768] 0.050140 0.022263 -0.017365 ..
|<- 1. 0x1438a1500 (0x285da5b80:0) [2x133x320] -0.231689 -0.019897 8.742188 ..
CCV_NNC_TRANSPOSE_FORWARD [6]: [1] -> [1] (2)
|-> 1. 0x1438d4ba0 (0x285da5b80:0) [2x133x8x40] -0.231689 -0.019897 8.742188 ..
|<- 1. 0x1438a1570 (0x285da5bc0:0) [2x8x133x40] -0.231689 -0.019897 8.742188 ..
Emit: (2, 6)
CCV_NNC_GEMM_FORWARD [7]: [2] -> [1] (3)
Wait: (3, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438be300 (0x285d84380:0) [320x768] -0.017517 -0.007912 -0.000061 ..
|<- 1. 0x1438a16c0 (0x285da5c40:0) [2x133x320] 0.030670 -0.073059 -0.036987 ..
CCV_NNC_TRANSPOSE_FORWARD [8]: [1] -> [1] (3)
|-> 1. 0x1438d4cf0 (0x285da5c40:0) [2x133x8x40] 0.030670 -0.073059 -0.036987 ..
|<- 1. 0x1438a1730 (0x285da5c80:0) [2x8x133x40] 0.030670 -0.073059 -0.036987 ..
Emit: (3, 7)
CCV_NNC_GEMM_FORWARD [9]: [2] -> [1] (4)
Wait: (4, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438bf330 (0x285d85800:0) [320x768] 0.037933 -0.010902 -0.072021 ..
|<- 1. 0x1438a3020 (0x285da5f00:0) [2x133x320] -0.131592 -0.084351 1.820312 ..
CCV_NNC_TRANSPOSE_FORWARD [10]: [1] -> [1] (4)
|-> 1. 0x1438d8b30 (0x285da5f00:0) [2x133x8x40] -0.131592 -0.084351 1.820312 ..
|<- 1. 0x1438a3090 (0x285da5f40:0) [2x8x133x40] -0.131592 -0.084351 1.820312 ..
Emit: (4, 14)
CCV_NNC_GEMM_FORWARD [11]: [2] -> [1] (5)
Wait: (5, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438bf3a0 (0x285d85840:0) [320x768] 0.004913 -0.008904 -0.008820 ..
|<- 1. 0x1438a31e0 (0x285da5f80:0) [2x133x320] 0.014427 -0.034271 -0.016800 ..
CCV_NNC_TRANSPOSE_FORWARD [12]: [1] -> [1] (5)
|-> 1. 0x1438d8c80 (0x285da5f80:0) [2x133x8x40] 0.014427 -0.034271 -0.016800 ..
|<- 1. 0x1438a3250 (0x285da5fc0:0) [2x8x133x40] 0.014427 -0.034271 -0.016800 ..
Emit: (5, 15)
CCV_NNC_GEMM_FORWARD [13]: [2] -> [1] (6)
Wait: (6, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438c0590 (0x285d86280:0) [640x768] -0.077393 0.060516 -0.058655 ..
|<- 1. 0x1438a4b40 (0x285da6540:0) [2x133x640] 0.370605 -0.183228 -1.733398 ..
CCV_NNC_TRANSPOSE_FORWARD [14]: [1] -> [1] (6)
|-> 1. 0x1438dcac0 (0x285da6540:0) [2x133x8x80] 0.370605 -0.183228 -1.733398 ..
|<- 1. 0x1438a4bb0 (0x285da6580:0) [2x8x133x80] 0.370605 -0.183228 -1.733398 ..
Emit: (6, 24)
CCV_NNC_GEMM_FORWARD [15]: [2] -> [1] (7)
Wait: (7, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438c0600 (0x285d862c0:0) [640x768] -0.010658 -0.064941 -0.039856 ..
|<- 1. 0x1438a4d00 (0x285da6600:0) [2x133x640] 0.013397 0.017731 0.048828 ..
CCV_NNC_TRANSPOSE_FORWARD [16]: [1] -> [1] (7)
|-> 1. 0x1438dcc10 (0x285da6600:0) [2x133x8x80] 0.013397 0.017731 0.048828 ..
|<- 1. 0x1438a4d70 (0x285da6640:0) [2x8x133x80] 0.013397 0.017731 0.048828 ..
Emit: (7, 25)
CCV_NNC_GEMM_FORWARD [17]: [2] -> [1] (8)
Wait: (8, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438c1630 (0x285d86c00:0) [640x768] 0.046356 0.060303 0.039642 ..
|<- 1. 0x1438a6660 (0x285da6b40:0) [2x133x640] -0.381836 -0.479736 0.379883 ..
CCV_NNC_TRANSPOSE_FORWARD [18]: [1] -> [1] (8)
|-> 1. 0x1438e0a50 (0x285da6b40:0) [2x133x8x80] -0.381836 -0.479736 0.379883 ..
|<- 1. 0x1438a66d0 (0x285da6b80:0) [2x8x133x80] -0.381836 -0.479736 0.379883 ..
Emit: (8, 32)
CCV_NNC_GEMM_FORWARD [19]: [2] -> [1] (9)
Wait: (9, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438c16a0 (0x285d86c40:0) [640x768] -0.002068 0.001761 0.008499 ..
|<- 1. 0x1438a6820 (0x285da6c00:0) [2x133x640] 0.031586 0.014740 -0.047302 ..
CCV_NNC_TRANSPOSE_FORWARD [20]: [1] -> [1] (9)
|-> 1. 0x1438e0ba0 (0x285da6c00:0) [2x133x8x80] 0.031586 0.014740 -0.047302 ..
|<- 1. 0x1438a6890 (0x285da6c40:0) [2x8x133x80] 0.031586 0.014740 -0.047302 ..
Emit: (9, 33)
CCV_NNC_GEMM_FORWARD [21]: [2] -> [1] (10)
Wait: (10, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438c2890 (0x285d87680:0) [1280x768] 0.049530 -0.013351 0.006092 ..
|<- 1. 0x1438a8180 (0x285da7180:0) [2x133x1280] -0.213623 0.277832 -0.094299 ..
CCV_NNC_TRANSPOSE_FORWARD [22]: [1] -> [1] (10)
|-> 1. 0x1438e49e0 (0x285da7180:0) [2x133x8x160] -0.213623 0.277832 -0.094299 ..
|<- 1. 0x1438a81f0 (0x285da71c0:0) [2x8x133x160] -0.213623 0.277832 -0.094299 ..
Emit: (10, 42)
CCV_NNC_GEMM_FORWARD [23]: [2] -> [1] (11)
Wait: (11, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438c2900 (0x285d876c0:0) [1280x768] -0.006660 -0.087158 0.025131 ..
|<- 1. 0x1438a8340 (0x285da7240:0) [2x133x1280] -0.006889 -0.040039 0.008888 ..
CCV_NNC_TRANSPOSE_FORWARD [24]: [1] -> [1] (11)
|-> 1. 0x1438e4b30 (0x285da7240:0) [2x133x8x160] -0.006889 -0.040039 0.008888 ..
|<- 1. 0x1438a83b0 (0x285da7280:0) [2x8x133x160] -0.006889 -0.040039 0.008888 ..
Emit: (11, 43)
CCV_NNC_GEMM_FORWARD [25]: [2] -> [1] (12)
Wait: (12, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438c3930 (0x285d8ce00:0) [1280x768] 0.059662 0.042114 0.031982 ..
|<- 1. 0x1438a9ca0 (0x285da7640:0) [2x133x1280] 0.191650 0.108704 -0.219238 ..
CCV_NNC_TRANSPOSE_FORWARD [26]: [1] -> [1] (12)
|-> 1. 0x1438e8970 (0x285da7640:0) [2x133x8x160] 0.191650 0.108704 -0.219238 ..
|<- 1. 0x1438a9d10 (0x285da7680:0) [2x8x133x160] 0.191650 0.108704 -0.219238 ..
Emit: (12, 50)
CCV_NNC_GEMM_FORWARD [27]: [2] -> [1] (13)
Wait: (13, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438c39a0 (0x285d8f800:0) [1280x768] 0.045746 0.000335 -0.000800 ..
|<- 1. 0x1438a9e60 (0x285da7700:0) [2x133x1280] -0.091675 0.026260 0.035645 ..
CCV_NNC_TRANSPOSE_FORWARD [28]: [1] -> [1] (13)
|-> 1. 0x1438e8ac0 (0x285da7700:0) [2x133x8x160] -0.091675 0.026260 0.035645 ..
|<- 1. 0x1438a9ed0 (0x285da7740:0) [2x8x133x160] -0.091675 0.026260 0.035645 ..
Emit: (13, 51)
CCV_NNC_GEMM_FORWARD [29]: [2] -> [1] (14)
Wait: (14, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438c5370 (0x285e696c0:0) [1280x768] 0.050659 -0.016159 -0.011871 ..
|<- 1. 0x1438abfa0 (0x285da7f80:0) [2x133x1280] -0.178467 0.800293 -1.226562 ..
CCV_NNC_TRANSPOSE_FORWARD [30]: [1] -> [1] (14)
|-> 1. 0x1438ec9e0 (0x285da7f80:0) [2x133x8x160] -0.178467 0.800293 -1.226562 ..
|<- 1. 0x1438ac010 (0x285da7fc0:0) [2x8x133x160] -0.178467 0.800293 -1.226562 ..
Emit: (14, 60)
CCV_NNC_GEMM_FORWARD [31]: [2] -> [1] (15)
Wait: (15, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438c53e0 (0x285e6a280:0) [1280x768] 0.026581 -0.126099 0.020554 ..
|<- 1. 0x1438ac160 (0x285d850c0:0) [2x133x1280] -0.026199 -0.083679 -0.066772 ..
CCV_NNC_TRANSPOSE_FORWARD [32]: [1] -> [1] (15)
|-> 1. 0x1438ecb30 (0x285d850c0:0) [2x133x8x160] -0.026199 -0.083679 -0.066772 ..
|<- 1. 0x1438ac1d0 (0x285d84540:0) [2x8x133x160] -0.026199 -0.083679 -0.066772 ..
Emit: (15, 61)
CCV_NNC_GEMM_FORWARD [33]: [2] -> [1] (16)
Wait: (16, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438c79f0 (0x285d98e40:0) [1280x768] 0.005672 0.008583 -0.108887 ..
|<- 1. 0x1438aee00 (0x285d833c0:0) [2x133x1280] -0.494141 0.059296 0.135498 ..
CCV_NNC_TRANSPOSE_FORWARD [34]: [1] -> [1] (16)
|-> 1. 0x1438f10b0 (0x285d833c0:0) [2x133x8x160] -0.494141 0.059296 0.135498 ..
|<- 1. 0x1438aee70 (0x285d83e40:0) [2x8x133x160] -0.494141 0.059296 0.135498 ..
Emit: (16, 80)
CCV_NNC_GEMM_FORWARD [35]: [2] -> [1] (17)
Wait: (17, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438c7a60 (0x285d98e80:0) [1280x768] 0.018356 0.016327 -0.031113 ..
|<- 1. 0x1438aefc0 (0x285d83f80:0) [2x133x1280] 0.102844 -0.059814 -0.027191 ..
CCV_NNC_TRANSPOSE_FORWARD [36]: [1] -> [1] (17)
|-> 1. 0x1438f1200 (0x285d83f80:0) [2x133x8x160] 0.102844 -0.059814 -0.027191 ..
|<- 1. 0x1438af030 (0x285d83ec0:0) [2x8x133x160] 0.102844 -0.059814 -0.027191 ..
Emit: (17, 81)
CCV_NNC_GEMM_FORWARD [37]: [2] -> [1] (18)
Wait: (18, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438c8b70 (0x285d99840:0) [1280x768] -0.063782 -0.024292 0.022858 ..
|<- 1. 0x1438b0990 (0x285d83d40:0) [2x133x1280] 0.121155 0.245972 -0.240967 ..
CCV_NNC_TRANSPOSE_FORWARD [38]: [1] -> [1] (18)
|-> 1. 0x1438f51a0 (0x285d83d40:0) [2x133x8x160] 0.121155 0.245972 -0.240967 ..
|<- 1. 0x1438b0a00 (0x285d82b80:0) [2x8x133x160] 0.121155 0.245972 -0.240967 ..
Emit: (18, 90)
CCV_NNC_GEMM_FORWARD [39]: [2] -> [1] (19)
Wait: (19, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438c8be0 (0x285d99880:0) [1280x768] -0.043610 0.111389 -0.029739 ..
|<- 1. 0x1438b0b50 (0x285d80ec0:0) [2x133x1280] 0.004066 -0.018509 -0.005821 ..
CCV_NNC_TRANSPOSE_FORWARD [40]: [1] -> [1] (19)
|-> 1. 0x1438f52f0 (0x285d80ec0:0) [2x133x8x160] 0.004066 -0.018509 -0.005821 ..
|<- 1. 0x1438b0bc0 (0x285d8f740:0) [2x8x133x160] 0.004066 -0.018509 -0.005821 ..
Emit: (19, 91)
CCV_NNC_GEMM_FORWARD [41]: [2] -> [1] (20)
Wait: (20, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438c9cf0 (0x285d9a240:0) [1280x768] -0.001761 0.075928 0.115906 ..
|<- 1. 0x1438b2520 (0x285d89bc0:0) [2x133x1280] 0.334717 -0.014442 -0.148804 ..
CCV_NNC_TRANSPOSE_FORWARD [42]: [1] -> [1] (20)
|-> 1. 0x1438f9290 (0x285d89bc0:0) [2x133x8x160] 0.334717 -0.014442 -0.148804 ..
|<- 1. 0x1438b2590 (0x285d89340:0) [2x8x133x160] 0.334717 -0.014442 -0.148804 ..
Emit: (20, 100)
CCV_NNC_GEMM_FORWARD [43]: [2] -> [1] (21)
Wait: (21, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438c9d60 (0x285d9a280:0) [1280x768] -0.041809 -0.037811 0.074951 ..
|<- 1. 0x1438b26e0 (0x285d8ac40:0) [2x133x1280] 0.031281 0.007065 -0.043945 ..
CCV_NNC_TRANSPOSE_FORWARD [44]: [1] -> [1] (21)
|-> 1. 0x1438f93e0 (0x285d8ac40:0) [2x133x8x160] 0.031281 0.007065 -0.043945 ..
|<- 1. 0x1438b2750 (0x285d89c80:0) [2x8x133x160] 0.031281 0.007065 -0.043945 ..
Emit: (21, 101)
CCV_NNC_GEMM_FORWARD [45]: [2] -> [1] (22)
Wait: (22, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438caf50 (0x285d9acc0:0) [640x768] -0.113464 0.034241 -0.047577 ..
|<- 1. 0x1438b4120 (0x285df6b80:0) [2x133x640] -0.624512 0.743164 -0.471924 ..
CCV_NNC_TRANSPOSE_FORWARD [46]: [1] -> [1] (22)
|-> 1. 0x1438fd380 (0x285df6b80:0) [2x133x8x80] -0.624512 0.743164 -0.471924 ..
|<- 1. 0x1438b4190 (0x285df3a00:0) [2x8x133x80] -0.624512 0.743164 -0.471924 ..
Emit: (22, 110)
CCV_NNC_GEMM_FORWARD [47]: [2] -> [1] (23)
Wait: (23, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438cafc0 (0x285d9ad00:0) [640x768] -0.052460 -0.007027 -0.031403 ..
|<- 1. 0x1438b42e0 (0x285df3b40:0) [2x133x640] -0.003769 -0.020844 -0.024673 ..
CCV_NNC_TRANSPOSE_FORWARD [48]: [1] -> [1] (23)
|-> 1. 0x1438fd4d0 (0x285df3b40:0) [2x133x8x80] -0.003769 -0.020844 -0.024673 ..
|<- 1. 0x1438b4350 (0x285df34c0:0) [2x8x133x80] -0.003769 -0.020844 -0.024673 ..
Emit: (23, 111)
CCV_NNC_GEMM_FORWARD [49]: [2] -> [1] (24)
Wait: (24, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438cc0d0 (0x285d9b6c0:0) [640x768] -0.041046 -0.033722 -0.042297 ..
|<- 1. 0x1438b5cb0 (0x285df3480:0) [2x133x640] -0.090027 0.466309 0.978516 ..
CCV_NNC_TRANSPOSE_FORWARD [50]: [1] -> [1] (24)
|-> 1. 0x143901470 (0x285df3480:0) [2x133x8x80] -0.090027 0.466309 0.978516 ..
|<- 1. 0x1438b5d20 (0x285df3940:0) [2x8x133x80] -0.090027 0.466309 0.978516 ..
Emit: (24, 120)
CCV_NNC_GEMM_FORWARD [51]: [2] -> [1] (25)
Wait: (25, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438cc140 (0x285d9b700:0) [640x768] -0.016235 -0.003174 -0.023041 ..
|<- 1. 0x1438b5e70 (0x285df0a40:0) [2x133x640] -0.021072 0.016312 -0.006813 ..
CCV_NNC_TRANSPOSE_FORWARD [52]: [1] -> [1] (25)
|-> 1. 0x1439015c0 (0x285df0a40:0) [2x133x8x80] -0.021072 0.016312 -0.006813 ..
|<- 1. 0x1438b5ee0 (0x285df0740:0) [2x8x133x80] -0.021072 0.016312 -0.006813 ..
Emit: (25, 121)
CCV_NNC_GEMM_FORWARD [53]: [2] -> [1] (26)
Wait: (26, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438cd250 (0x285d9c0c0:0) [640x768] 0.073486 0.011406 -0.008133 ..
|<- 1. 0x1438b7840 (0x285de5780:0) [2x133x640] -0.396484 -0.269043 -0.424072 ..
CCV_NNC_TRANSPOSE_FORWARD [54]: [1] -> [1] (26)
|-> 1. 0x143905560 (0x285de5780:0) [2x133x8x80] -0.396484 -0.269043 -0.424072 ..
|<- 1. 0x1438b78b0 (0x285de7a00:0) [2x8x133x80] -0.396484 -0.269043 -0.424072 ..
Emit: (26, 130)
CCV_NNC_GEMM_FORWARD [55]: [2] -> [1] (27)
Wait: (27, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438cd2c0 (0x285d9c100:0) [640x768] 0.004990 0.025543 0.019318 ..
|<- 1. 0x1438b7a00 (0x285de0dc0:0) [2x133x640] 0.022568 -0.025116 -0.027023 ..
CCV_NNC_TRANSPOSE_FORWARD [56]: [1] -> [1] (27)
|-> 1. 0x1439056b0 (0x285de0dc0:0) [2x133x8x80] 0.022568 -0.025116 -0.027023 ..
|<- 1. 0x1438b7a70 (0x285de0e80:0) [2x8x133x80] 0.022568 -0.025116 -0.027023 ..
Emit: (27, 131)
CCV_NNC_GEMM_FORWARD [57]: [2] -> [1] (28)
Wait: (28, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438ce4b0 (0x285d9cb40:0) [320x768] -0.017227 0.046448 0.083008 ..
|<- 1. 0x1438b9440 (0x285e2f180:0) [2x133x320] 2.285156 0.156494 -1.203125 ..
CCV_NNC_TRANSPOSE_FORWARD [58]: [1] -> [1] (28)
|-> 1. 0x143909650 (0x285e2f180:0) [2x133x8x40] 2.285156 0.156494 -1.203125 ..
|<- 1. 0x1438b94b0 (0x285e2f300:0) [2x8x133x40] 2.285156 0.156494 -1.203125 ..
Emit: (28, 140)
CCV_NNC_GEMM_FORWARD [59]: [2] -> [1] (29)
Wait: (29, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438ce520 (0x285d9cb80:0) [320x768] 0.019409 0.018814 0.000233 ..
|<- 1. 0x1438b9600 (0x285e2fa40:0) [2x133x320] -0.004307 -0.029922 0.005905 ..
CCV_NNC_TRANSPOSE_FORWARD [60]: [1] -> [1] (29)
|-> 1. 0x1439097a0 (0x285e2fa40:0) [2x133x8x40] -0.004307 -0.029922 0.005905 ..
|<- 1. 0x1438b9670 (0x285e2ee80:0) [2x8x133x40] -0.004307 -0.029922 0.005905 ..
Emit: (29, 141)
CCV_NNC_GEMM_FORWARD [61]: [2] -> [1] (30)
Wait: (30, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438cf630 (0x285d9d540:0) [320x768] 0.016708 -0.056610 -0.050446 ..
|<- 1. 0x1438bafd0 (0x285ef5940:0) [2x133x320] -1.026367 0.949707 -6.625000 ..
CCV_NNC_TRANSPOSE_FORWARD [62]: [1] -> [1] (30)
|-> 1. 0x14390d740 (0x285ef5940:0) [2x133x8x40] -1.026367 0.949707 -6.625000 ..
|<- 1. 0x1438bb040 (0x285ef41c0:0) [2x8x133x40] -1.026367 0.949707 -6.625000 ..
Emit: (30, 150)
CCV_NNC_GEMM_FORWARD [63]: [2] -> [1] (31)
Wait: (31, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438cf6a0 (0x285d9d580:0) [320x768] 0.001955 -0.014694 -0.003132 ..
|<- 1. 0x1438bb190 (0x285ed4f80:0) [2x133x320] 0.047729 0.026077 0.020203 ..
CCV_NNC_TRANSPOSE_FORWARD [64]: [1] -> [1] (31)
|-> 1. 0x14390d890 (0x285ed4f80:0) [2x133x8x40] 0.047729 0.026077 0.020203 ..
|<- 1. 0x1438bb200 (0x285ed54c0:0) [2x8x133x40] 0.047729 0.026077 0.020203 ..
Emit: (31, 151)
CCV_NNC_GEMM_FORWARD [65]: [2] -> [1] (32)
Wait: (32, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438d07b0 (0x285d9df40:0) [320x768] 0.003315 0.021103 0.009254 ..
|<- 1. 0x1438bcb60 (0x285f6d480:0) [2x133x320] 0.226440 -0.880859 -0.376221 ..
CCV_NNC_TRANSPOSE_FORWARD [66]: [1] -> [1] (32)
|-> 1. 0x143911830 (0x285f6d480:0) [2x133x8x40] 0.226440 -0.880859 -0.376221 ..
|<- 1. 0x1438bcbd0 (0x285f6d400:0) [2x8x133x40] 0.226440 -0.880859 -0.376221 ..
Emit: (32, 160)
CCV_NNC_GEMM_FORWARD [67]: [2] -> [1] (33)
Wait: (33, 0)
|-> 1. 0x1438bd490 (0x285e6c2c0:0) [2x133x768] -0.387939 0.023743 -0.054749 ..
|-> 2. 0x1438d0820 (0x285d9df80:0) [320x768] 0.005962 -0.006207 -0.002657 ..
|<- 1. 0x1438bcd20 (0x285f6d200:0) [2x133x320] -0.004234 0.009697 0.024551 ..
CCV_NNC_TRANSPOSE_FORWARD [68]: [1] -> [1] (33)
|-> 1. 0x143911980 (0x285f6d200:0) [2x133x8x40] -0.004234 0.009697 0.024551 ..
|<- 1. 0x1438bcd90 (0x285da6ec0:0) [2x8x133x40] -0.004234 0.009697 0.024551 ..
Emit: (33, 161)
CCV_NNC_SWISH_FORWARD [69]: [1] -> [1] (0)
|-> 1. 0x1438a0070 (0x285da5640:0) [2x1280] -0.068420 -0.037476 -0.015541 ..
|<- 1. 0x1438a0070 (0x285da5640:0) [2x1280] -0.033051 -0.018387 -0.007710 ..
Emit: (0, 2)
CCV_NNC_GROUP_NORM_FORWARD [70]: [3] -> [3] (1)
|-> 1. 0x14390db70 (0x285f78ac0:0) [2x64x64x320] -0.319092 -0.406982 0.225342 ..
|-> 2. 0x1438bd810 (0x285d84100:0) [1x1x1x320] 0.484131 0.523926 0.366943 ..
|-> 3. 0x1438bd880 (0x285d84600:0) [1x1x1x320] -0.007233 -0.079224 -0.075317 ..
|<- 1. 0x1438a00e0 (0x285da5680:0) [2x64x64x320] -0.373535 -0.587402 0.132080 ..
|<- 2. 0x1438a0150 (0x285da5700:0) [2x1x1x32] -0.007511 -0.001691 0.001145 ..
|<- 3. 0x1438a01c0 (0x285da5740:0) [2x1x1x32] 2.427734 2.734375 3.083984 ..
CCV_NNC_SWISH_FORWARD [71]: [1] -> [1] (1)
|-> 1. 0x1438a00e0 (0x285da5680:0) [2x64x64x320] -0.373535 -0.587402 0.132080 ..
|<- 1. 0x1438a00e0 (0x285da5680:0) [2x64x64x320] -0.152344 -0.209839 0.070374 ..
CCV_NNC_CONVOLUTION_FORWARD [72]: [3] -> [1] (1)
|-> 1. 0x1438a00e0 (0x285da5680:0) [2x64x64x320] -0.152344 -0.209839 0.070374 ..
|-> 2. 0x1438bd9d0 (0x285d84500:0) [320x320x3x3] -0.018021 -0.052185 -0.052765 ..
|-> 3. 0x1438bda40 (0x285d84780:0) [320] 0.036621 -0.050140 0.015305 ..
|<- 1. 0x1438a02a0 (0x285da56c0:0) [2x64x64x320] 0.862793 0.136719 -1.131836 ..
Emit: (1, 1)
CCV_NNC_GEMM_FORWARD [73]: [3] -> [1] (0)
|-> 1. 0x1438a0070 (0x285da5640:0) [2x1280] -0.033051 -0.018387 -0.007710 ..
|-> 2. 0x1438bd8f0 (0x285d84400:0) [320x1280] -0.004944 -0.001311 -0.004967 ..
|-> 3. 0x1438bd960 (0x285d846c0:0) [320] 0.038757 -0.058807 0.015556 ..
|<- 1. 0x1438a0230 (0x285da5780:0) [2x320] 0.389648 0.819824 0.133667 ..
CCV_NNC_ADD_FORWARD [74]: [2] -> [1] (0)
Wait: (0, 1)
|-> 1. 0x1438a02a0 (0x285da56c0:0) [2x64x64x320] 0.862793 0.136719 -1.131836 ..
|-> 2. 0x1438d0f90 (0x285da5780:0) [2x1x1x320] 0.389648 0.819824 0.133667 ..
|<- 1. 0x1438a02a0 (0x285da56c0:0) [2x64x64x320] 1.251953 0.956543 -0.998047 ..
CCV_NNC_GROUP_NORM_FORWARD [75]: [3] -> [3] (0)
|-> 1. 0x1438a02a0 (0x285da56c0:0) [2x64x64x320] 1.251953 0.956543 -0.998047 ..
|-> 2. 0x1438bdab0 (0x285d84680:0) [1x1x1x320] 0.290283 0.676270 0.381104 ..
|-> 3. 0x1438bdb20 (0x285d84740:0) [1x1x1x320] -0.077087 -0.171631 -0.141968 ..
|<- 1. 0x1438a0310 (0x285da5680:0) [2x64x64x320] 0.135986 0.244141 -0.208862 ..
|<- 2. 0x1438a0380 (0x285da57c0:0) [2x1x1x32] -0.563965 -0.766113 -0.697754 ..
|<- 3. 0x1438a03f0 (0x285da5800:0) [2x1x1x32] 0.404297 0.273682 0.777832 ..
CCV_NNC_SWISH_FORWARD [76]: [1] -> [1] (0)
|-> 1. 0x1438a0310 (0x285da5680:0) [2x64x64x320] 0.135986 0.244141 -0.208862 ..
|<- 1. 0x1438a0310 (0x285da5680:0) [2x64x64x320] 0.072632 0.136841 -0.093567 ..
CCV_NNC_CONVOLUTION_FORWARD [77]: [3] -> [1] (0)
|-> 1. 0x1438a0310 (0x285da5680:0) [2x64x64x320] 0.072632 0.136841 -0.093567 ..
|-> 2. 0x1438bdb90 (0x285d84800:0) [320x320x3x3] 0.012184 0.018036 -0.006847 ..
|-> 3. 0x1438bdc00 (0x285d84700:0) [320] 0.001400 -0.109863 0.059784 ..
|<- 1. 0x1438a0460 (0x285da56c0:0) [2x64x64x320] 0.450928 -1.825195 0.461914 ..
CCV_NNC_ADD_FORWARD [78]: [2] -> [1] (0)
|-> 1. 0x14390db70 (0x285f78ac0:0) [2x64x64x320] -0.319092 -0.406982 0.225342 ..
|-> 2. 0x1438a0460 (0x285da56c0:0) [2x64x64x320] 0.450928 -1.825195 0.461914 ..
|<- 1. 0x1438a04d0 (0x285da5840:0) [2x64x64x320] 0.131836 -2.232422 0.687500 ..
CCV_NNC_GEMM_FORWARD [79]: [3] -> [1] (34)
Wait: (34, 2)
|-> 1. 0x1438a0070 (0x285da5640:0) [2x1280] -0.033051 -0.018387 -0.007710 ..
|-> 2. 0x1438be990 (0x285d84bc0:0) [320x1280] -0.004845 -0.001458 -0.003963 ..
|-> 3. 0x1438bea00 (0x285d85200:0) [320] 0.004868 -0.009079 -0.058716 ..
|<- 1. 0x1438a1d50 (0x285da5dc0:0) [2x320] 0.114136 0.382324 -0.697754 ..
Emit: (34, 10)
CCV_NNC_GEMM_FORWARD [80]: [3] -> [1] (35)
Wait: (35, 2)
|-> 1. 0x1438a0070 (0x285da5640:0) [2x1280] -0.033051 -0.018387 -0.007710 ..
|-> 2. 0x1438bfb10 (0x285d85c80:0) [640x1280] 0.006191 -0.002232 -0.009239 ..
|-> 3. 0x1438bfb80 (0x285d85cc0:0) [640] 0.027374 -0.004711 0.019440 ..
|<- 1. 0x1438a3870 (0x285da6180:0) [2x640] 0.351318 -0.119873 0.318848 ..
Emit: (35, 18)
CCV_NNC_GEMM_FORWARD [81]: [3] -> [1] (36)
Wait: (36, 2)
|-> 1. 0x1438a0070 (0x285da5640:0) [2x1280] -0.033051 -0.018387 -0.007710 ..
|-> 2. 0x1438c0c90 (0x285d86680:0) [640x1280] 0.004734 -0.008568 0.008568 ..
|-> 3. 0x1438c0d00 (0x285d866c0:0) [640] 0.026276 0.008690 -0.049683 ..
|<- 1. 0x1438a5390 (0x285da6840:0) [2x640] 0.087891 -3.085938 0.536621 ..
Emit: (36, 28)
CCV_NNC_GEMM_FORWARD [82]: [3] -> [1] (37)
Wait: (37, 2)
|-> 1. 0x1438a0070 (0x285da5640:0) [2x1280] -0.033051 -0.018387 -0.007710 ..
|-> 2. 0x1438c1e10 (0x285d87080:0) [1280x1280] -0.006657 0.006611 -0.002247 ..
|-> 3. 0x1438c1e80 (0x285d870c0:0) [1280] 0.013191 0.012268 0.008003 ..
|<- 1. 0x1438a6eb0 (0x285da6d80:0) [2x1280] 0.093994 0.277832 0.315918 ..
Emit: (37, 36)
CCV_NNC_GEMM_FORWARD [83]: [3] -> [1] (38)
Wait: (38, 2)
|-> 1. 0x1438a0070 (0x285da5640:0) [2x1280] -0.033051 -0.018387 -0.007710 ..
|-> 2. 0x1438c2f90 (0x285d87a80:0) [1280x1280] -0.005486 -0.005077 -0.003628 ..
|-> 3. 0x1438c3000 (0x285d87ac0:0) [1280] 0.044830 -0.016068 0.031052 ..
|<- 1. 0x1438a89d0 (0x285da7440:0) [2x1280] 0.601562 -0.082703 0.705078 ..
Emit: (38, 46)
CCV_NNC_GEMM_FORWARD [84]: [3] -> [1] (39)
Wait: (39, 2)
|-> 1. 0x1438a0070 (0x285da5640:0) [2x1280] -0.033051 -0.018387 -0.007710 ..
|-> 2. 0x1438c4110 (0x285d8a640:0) [1280x1280] -0.007282 -0.001312 0.003534 ..
|-> 3. 0x1438c4180 (0x285d8ac00:0) [1280] 0.077209 -0.040894 -0.032227 ..
|<- 1. 0x1438aa4f0 (0x285da7940:0) [2x1280] 0.770020 0.276611 0.438477 ..
Emit: (39, 54)
CCV_NNC_GEMM_FORWARD [85]: [3] -> [1] (40)
Wait: (40, 2)
|-> 1. 0x1438a0070 (0x285da5640:0) [2x1280] -0.033051 -0.018387 -0.007710 ..
|-> 2. 0x1438c4570 (0x285df7340:0) [1280x1280] 0.002802 -0.005547 0.010971 ..
|-> 3. 0x1438c45e0 (0x285df7280:0) [1280] -0.076843 0.028809 0.114197 ..
|<- 1. 0x1438aa8e0 (0x285da7a80:0) [2x1280] -0.554199 0.637207 0.615234 ..
Emit: (40, 55)
CCV_NNC_GEMM_FORWARD [86]: [3] -> [1] (41)
Wait: (41, 2)
|-> 1. 0x1438a0070 (0x285da5640:0) [2x1280] -0.033051 -0.018387 -0.007710 ..
|-> 2. 0x1438c49d0 (0x285dfd540:0) [1280x1280] 0.001873 -0.000576 -0.005287 ..
|-> 3. 0x1438c4a40 (0x285de0700:0) [1280] 0.076538 0.086609 0.002594 ..
|<- 1. 0x1438aacd0 (0x285da7bc0:0) [2x1280] 0.581543 1.150391 0.077393 ..
Emit: (41, 56)
CCV_NNC_GEMM_FORWARD [87]: [3] -> [1] (42)
Wait: (42, 2)
|-> 1. 0x1438a0070 (0x285da5640:0) [2x1280] -0.033051 -0.018387 -0.007710 ..
|-> 2. 0x1438c5a70 (0x285e6a040:0) [1280x1280] -0.000326 -0.004715 -0.008072 ..
|-> 3. 0x1438c5ae0 (0x285e69c00:0) [1280] 0.128540 -0.076782 0.120300 ..
|<- 1. 0x1438ac7f0 (0x285d84340:0) [2x1280] 0.444092 0.104248 0.304443 ..
Emit: (42, 64)
CCV_NNC_GEMM_FORWARD [88]: [3] -> [1] (43)
Wait: (43, 2)
|-> 1. 0x1438a0070 (0x285da5640:0) [2x1280] -0.033051 -0.018387 -0.007710 ..
|-> 2. 0x1438c5ed0 (0x285e69540:0) [1280x1280] -0.006855 -0.009766 -0.000924 ..
|-> 3. 0x1438c5f40 (0x285e69c80:0) [1280] 0.033813 0.077148 0.046234 ..
|<- 1. 0x1438acc50 (0x285d82bc0:0) [2x1280] 0.063354 0.040497 0.044067 ..
Emit: (43, 65)
CCV_NNC_GEMM_FORWARD [89]: [3] -> [1] (44)
Wait: (44, 2)
|-> 1. 0x1438a0070 (0x285da5640:0) [2x1280] -0.033051 -0.018387 -0.007710 ..
|-> 2. 0x1438c6410 (0x285d981c0:0) [1280x1280] 0.011826 -0.011513 -0.001285 ..
|-> 3. 0x1438c6480 (0x285d98200:0) [1280] 0.017502 -0.009285 -0.049225 ..
|<- 1. 0x1438ad120 (0x285d837c0:0) [2x1280] 0.086243 1.029297 0.114319 ..
Emit: (44, 68)
CCV_NNC_GEMM_FORWARD [90]: [3] -> [1] (45)
Wait: (45, 2)
|-> 1. 0x1438a0070 (0x285da5640:0) [2x1280] -0.033051 -0.018387 -0.007710 ..
|-> 2. 0x1438c6950 (0x285d984c0:0) [1280x1280] 0.004402 -0.006351 0.008255 ..
|-> 3. 0x1438c69c0 (0x285d98500:0) [1280] 0.031647 -0.037048 0.060364 ..
|<- 1. 0x1438ad5f0 (0x285d800c0:0) [2x1280] 0.105347 -0.784180 0.284912 ..
Emit: (45, 71)
CCV_NNC_GEMM_FORWARD [91]: [3] -> [1] (46)
Wait: (46, 2)
|-> 1. 0x1438a0070 (0x285da5640:0) [2x1280] -0.033051 -0.018387 -0.007710 ..
|-> 2. 0x1438c6f70 (0x285d98840:0) [1280x1280] -0.003630 0.008698 0.005058 ..
|-> 3. 0x1438c6fe0 (0x285d98880:0) [1280] 0.100220 0.082825 0.077271 ..
|<- 1. 0x1438adb30 (0x285d83980:0) [2x1280] -0.228027 0.609375 0.654297 ..
Emit: (46, 74)
CCV_NNC_GEMM_FORWARD [92]: [3] -> [1] (47)
Wait: (47, 2)
|-> 1. 0x1438a0070 (0x285da5640:0) [2x1280] -0.033051 -0.018387 -0.007710 ..
|-> 2. 0x1438c80f0 (0x285d99240:0) [1280x1280] 0.007771 -0.006096 0.009300 ..
|-> 3. 0x1438c8160 (0x285d99280:0) [1280] 0.065491 0.066833 -0.015106 ..
|<- 1. 0x1438af6c0 (0x285d83f40:0) [2x1280] -0.230713 0.213135 -0.136353 ..
Emit: (47, 84)
CCV_NNC_GEMM_FORWARD [93]: [3] -> [1] (48)
Wait: (48, 2)
|-> 1. 0x1438a0070 (0x285da5640:0) [2x1280] -0.033051 -0.018387 -0.007710 ..
|-> 2. 0x1438c9270 (0x285d99c40:0) [1280x1280] -0.000185 -0.003536 0.004467 ..
|-> 3. 0x1438c92e0 (0x285d99c80:0) [1280] 0.041534 0.008492 0.046967 ..
|<- 1. 0x1438b1250 (0x285d8c440:0) [2x1280] 1.041992 0.774902 1.260742 ..
Emit: (48, 94)
CCV_NNC_GEMM_FORWARD [94]: [3] -> [1] (49)
Wait: (49, 2)
|-> 1. 0x1438a0070 (0x285da5640:0) [2x1280] -0.033051 -0.018387 -0.007710 ..
|-> 2. 0x1438ca4d0 (0x285d9a6c0:0) [640x1280] -0.012924 -0.011131 0.001637 ..
|-> 3. 0x1438ca540 (0x285d9a700:0) [640] 0.100769 0.093994 0.061066 ..
|<- 1. 0x1438b2e50 (0x285df5b80:0) [2x640] 0.082214 1.164062 0.841797 ..
Emit: (49, 104)
CCV_NNC_GEMM_FORWARD [95]: [3] -> [1] (50)
Wait: (50, 2)
|-> 1. 0x1438a0070 (0x285da5640:0) [2x1280] -0.033051 -0.018387 -0.007710 ..
|-> 2. 0x1438cb650 (0x285d9b0c0:0) [640x1280] -0.000035 -0.001340 -0.006222 ..
|-> 3. 0x1438cb6c0 (0x285d9b100:0) [640] 0.053101 -0.055695 -0.059418 ..
|<- 1. 0x1438b49e0 (0x285df3880:0) [2x640] 0.327637 -0.112061 0.204590 ..
Emit: (50, 114)
CCV_NNC_GEMM_FORWARD [96]: [3] -> [1] (51)
Wait: (51, 2)
|-> 1. 0x1438a0070 (0x285da5640:0) [2x1280] -0.033051 -0.018387 -0.007710 ..
|-> 2. 0x1438cc7d0 (0x285d9bac0:0) [640x1280] 0.007111 -0.001447 0.010307 ..
|-> 3. 0x1438cc840 (0x285d9bb00:0) [640] 0.019012 0.010918 0.034790 ..
|<- 1. 0x1438b6570 (0x285dffc00:0) [2x640] -0.846680 0.141968 0.290283 ..
Emit: (51, 124)
CCV_NNC_GEMM_FORWARD [97]: [3] -> [1] (52)
Wait: (52, 2)
|-> 1. 0x1438a0070 (0x285da5640:0) [2x1280] -0.033051 -0.018387 -0.007710 ..
|-> 2. 0x1438cda30 (0x285d9c540:0) [320x1280] 0.001700 -0.003801 -0.004478 ..
|-> 3. 0x1438cdaa0 (0x285d9c580:0) [320] -0.004143 0.078064 0.069885 ..
|<- 1. 0x1438b8170 (0x285def880:0) [2x320] 0.466797 0.149780 1.849609 ..
Emit: (52, 134)
CCV_NNC_GEMM_FORWARD [98]: [3] -> [1] (53)
Wait: (53, 2)
|-> 1. 0x1438a0070 (0x285da5640:0) [2x1280] -0.033051 -0.018387 -0.007710 ..
|-> 2. 0x1438cebb0 (0x285d9cf40:0) [320x1280] 0.005024 -0.000107 0.000202 ..
|-> 3. 0x1438cec20 (0x285d9cf80:0) [320] 0.031738 -0.058533 0.119751 ..
|<- 1. 0x1438b9d00 (0x285e6b440:0) [2x320] 0.176636 -1.454102 0.976562 ..
Emit: (53, 144)
CCV_NNC_GEMM_FORWARD [99]: [3] -> [1] (54)
Wait: (54, 2)
|-> 1. 0x1438a0070 (0x285da5640:0) [2x1280] -0.033051 -0.018387 -0.007710 ..
|-> 2. 0x1438cfd30 (0x285d9d940:0) [320x1280] -0.006310 0.003212 0.005932 ..
|-> 3. 0x1438cfda0 (0x285d9d980:0) [320] -0.016846 -0.054718 0.046021 ..
|<- 1. 0x1438bb890 (0x285f65e80:0) [2x320] -0.972656 0.468994 0.141357 ..
Emit: (54, 154)
CCV_NNC_GROUP_NORM_FORWARD [100]: [3] -> [3] (0)
|-> 1. 0x1438a04d0 (0x285da5840:0) [2x64x64x320] 0.131836 -2.232422 0.687500 ..
|-> 2. 0x1438bdc70 (0x285d847c0:0) [1x1x1x320] 0.349365 0.203857 0.279053 ..
|-> 3. 0x1438bdce0 (0x285d84880:0) [1x1x1x320] -0.073303 0.182617 -0.251465 ..
|<- 1. 0x1438a0540 (0x285da5680:0) [2x64x64x320] -0.015656 -0.225952 -0.063171 ..
|<- 2. 0x1438a05b0 (0x285da5740:0) [2x1x1x32] -0.048035 -0.275879 0.005417 ..
|<- 3. 0x1438a0620 (0x285da5700:0) [2x1x1x32] 0.917480 1.359375 4.316406 ..
CCV_NNC_CONVOLUTION_FORWARD [101]: [3] -> [1] (0)
|-> 1. 0x1438a0540 (0x285da5680:0) [2x64x64x320] -0.015656 -0.225952 -0.063171 ..
|-> 2. 0x1438bdd50 (0x285d84840:0) [320x320x1x1] 0.018326 ..
|-> 3. 0x1438bddc0 (0x285d84c40:0) [320] 0.057037 0.063049 -0.028610 ..
|<- 1. 0x1438a0690 (0x285da56c0:0) [2x64x64x320] 0.347656 0.462646 -0.141479 ..
CCV_NNC_LAYER_NORM_FORWARD [102]: [3] -> [3] (0)
|-> 1. 0x1438d1000 (0x285da56c0:0) [2x4096x320] 0.347656 0.462646 -0.141479 ..
|-> 2. 0x1438bde30 (0x285d84d00:0) [1x1x320] 0.759766 0.622559 0.730469 ..
|-> 3. 0x1438bdea0 (0x285d84c80:0) [1x1x320] 0.039795 -0.103760 -0.001315 ..
|<- 1. 0x1438a0700 (0x285da5680:0) [2x4096x320] 1.031250 1.008789 -0.544434 ..
|<- 2. 0x1438a0770 (0x285da5880:0) [2x4096x1] 0.036041 ..
|<- 3. 0x1438a07e0 (0x285da58c0:0) [2x4096x1] 4.187500 ..
Emit: (0, 3)
CCV_NNC_GEMM_FORWARD [103]: [2] -> [1] (0)
|-> 1. 0x1438a0700 (0x285da5680:0) [2x4096x320] 1.031250 1.008789 -0.544434 ..
|-> 2. 0x1438bdf10 (0x285d84c00:0) [320x320] 0.071777 -0.076782 0.022446 ..
|<- 1. 0x1438a0850 (0x285da5900:0) [2x4096x320] 1.149414 -1.515625 -0.993164 ..
CCV_NNC_SCALAR_MUL_FORWARD [104]: [1] -> [1] (0)
|-> 1. 0x1438a0850 (0x285da5900:0) [2x4096x320] 1.149414 -1.515625 -0.993164 ..
|<- 1. 0x1438a0850 (0x285da5900:0) [2x4096x320] 0.181641 -0.239624 -0.156982 ..
CCV_NNC_TRANSPOSE_FORWARD [105]: [1] -> [1] (0)
|-> 1. 0x1438d10e0 (0x285da5900:0) [2x4096x8x40] 0.181641 -0.239624 -0.156982 ..
|<- 1. 0x1438a09a0 (0x285da59c0:0) [2x8x4096x40] 0.181641 -0.239624 -0.156982 ..
CCV_NNC_GEMM_FORWARD [106]: [2] -> [1] (1)
Wait: (1, 3)
|-> 1. 0x1438a0700 (0x285da5680:0) [2x4096x320] 1.031250 1.008789 -0.544434 ..
|-> 2. 0x1438bdf80 (0x285d84cc0:0) [320x320] -0.111938 -0.047272 -0.020325 ..
|<- 1. 0x1438a08c0 (0x285da5940:0) [2x4096x320] 0.471924 -0.942871 0.792969 ..
CCV_NNC_TRANSPOSE_FORWARD [107]: [1] -> [1] (1)
|-> 1. 0x1438d1070 (0x285da5940:0) [2x4096x8x40] 0.471924 -0.942871 0.792969 ..
|<- 1. 0x1438a0930 (0x285da5980:0) [2x8x4096x40] 0.471924 -0.942871 0.792969 ..
Emit: (1, 4)
CCV_NNC_GEMM_FORWARD [108]: [2] -> [1] (55)
Wait: (55, 3)
|-> 1. 0x1438a0700 (0x285da5680:0) [2x4096x320] 1.031250 1.008789 -0.544434 ..
|-> 2. 0x1438bdff0 (0x285d84d40:0) [320x320] -0.024887 0.011726 -0.073364 ..
|<- 1. 0x1438a0a10 (0x285da5a00:0) [2x4096x320] 0.333496 0.162231 0.011147 ..
CCV_NNC_TRANSPOSE_FORWARD [109]: [1] -> [1] (55)
|-> 1. 0x1438d1230 (0x285da5a00:0) [2x4096x8x40] 0.333496 0.162231 0.011147 ..
|<- 1. 0x1438a0af0 (0x285da5a80:0) [2x8x4096x40] 0.333496 0.162231 0.011147 ..
Emit: (55, 5)
CCV_NNC_GEMM_FORWARD [110]: [2] -> [1] (0)
Wait: (0, 4)
|-> 1. 0x1438d11c0 (0x285da59c0:0) [1x4096x40] 0.181641 -0.239624 -0.156982 ..
|-> 2. 0x1438d1150 (0x285da5980:0) [1x4096x40] 0.471924 -0.942871 0.792969 ..
|<- 1. 0x1438a0a80 (0x285da5a40:0) [1x4096x4096] 1.342773 1.739258 0.361328 ..
CCV_NNC_SOFTMAX_FORWARD [111]: [1] -> [1] (0)
|-> 1. 0x1438d12a0 (0x285da5a40:0) [4096x4096] 1.342773 1.739258 0.361328 ..
|<- 1. 0x1438d12a0 (0x285da5a40:0) [4096x4096] 0.000418 0.000622 0.000157 ..
CCV_NNC_GEMM_FORWARD [112]: [2] -> [1] (0)
Wait: (0, 5)
|-> 1. 0x1438d1380 (0x285da5a40:0) [1x4096x4096] 0.000418 0.000622 0.000157 ..
|-> 2. 0x1438d1310 (0x285da5a80:0) [1x4096x40] 0.333496 0.162231 0.011147 ..
|<- 1. 0x1438d4000 (0x285da5680:0) [1x4096x40] -0.164062 -0.099121 0.168091 ..
CCV_NNC_GEMM_FORWARD [113]: [2] -> [1] (0)
|-> 1. 0x1438d14a0 (0x285da59c0:0) [1x4096x40] 0.315186 0.172241 -0.090027 ..
|-> 2. 0x1438d13f0 (0x285da5980:0) [1x4096x40] 1.596680 -0.960449 0.928711 ..
|<- 1. 0x1438a0b60 (0x285da5a40:0) [1x4096x4096] 7.625000 3.019531 3.916016 ..
CCV_NNC_SOFTMAX_FORWARD [114]: [1] -> [1] (0)
|-> 1. 0x1438d1550 (0x285da5a40:0) [4096x4096] 7.625000 3.019531 3.916016 ..
|<- 1. 0x1438d1550 (0x285da5a40:0) [4096x4096] 0.034180 0.000342 0.000838 ..
CCV_NNC_GEMM_FORWARD [115]: [2] -> [1] (0)
|-> 1. 0x1438d1670 (0x285da5a40:0) [1x4096x4096] 0.034180 0.000342 0.000838 ..
|-> 2. 0x1438d15c0 (0x285da5a80:0) [1x4096x40] 0.084656 0.138184 0.002228 ..
|<- 1. 0x1438d4070 (0x285da5680:0) [1x4096x40] -0.028610 0.000618 0.013924 ..
CCV_NNC_GEMM_FORWARD [116]: [2] -> [1] (0)
|-> 1. 0x1438d1790 (0x285da59c0:0) [1x4096x40] -0.071655 -0.121826 -0.061707 ..
|-> 2. 0x1438d16e0 (0x285da5980:0) [1x4096x40] -0.478516 -1.603516 -0.821289 ..
|<- 1. 0x1438a0bd0 (0x285da5a40:0) [1x4096x4096] 4.460938 2.183594 2.863281 ..
CCV_NNC_SOFTMAX_FORWARD [117]: [1] -> [1] (0)
|-> 1. 0x1438d1840 (0x285da5a40:0) [4096x4096] 4.460938 2.183594 2.863281 ..
|<- 1. 0x1438d1840 (0x285da5a40:0) [4096x4096] 0.017975 0.001843 0.003637 ..
CCV_NNC_GEMM_FORWARD [118]: [2] -> [1] (0)
|-> 1. 0x1438d1960 (0x285da5a40:0) [1x4096x4096] 0.017975 0.001843 0.003637 ..
|-> 2. 0x1438d18b0 (0x285da5a80:0) [1x4096x40] 0.279053 -0.195801 0.358887 ..
|<- 1. 0x1438d4120 (0x285da5680:0) [1x4096x40] 0.075317 -0.022110 0.061371 ..
CCV_NNC_GEMM_FORWARD [119]: [2] -> [1] (0)
|-> 1. 0x1438d1a80 (0x285da59c0:0) [1x4096x40] -0.276611 -0.201660 -0.025070 ..
|-> 2. 0x1438d19d0 (0x285da5980:0) [1x4096x40] -0.522949 -0.113892 1.308594 ..
|<- 1. 0x1438a0c40 (0x285da5a40:0) [1x4096x4096] 0.968262 1.105469 0.160156 ..
CCV_NNC_SOFTMAX_FORWARD [120]: [1] -> [1] (0)
|-> 1. 0x1438d1b30 (0x285da5a40:0) [4096x4096] 0.968262 1.105469 0.160156 ..
|<- 1. 0x1438d1b30 (0x285da5a40:0) [4096x4096] 0.000864 0.000990 0.000385 ..
CCV_NNC_GEMM_FORWARD [121]: [2] -> [1] (0)
|-> 1. 0x1438d1c50 (0x285da5a40:0) [1x4096x4096] 0.000864 0.000990 0.000385 ..
|-> 2. 0x1438d1ba0 (0x285da5a80:0) [1x4096x40] 0.065002 -0.490479 -0.035065 ..
|<- 1. 0x1438d41d0 (0x285da5680:0) [1x4096x40] 0.084290 -0.009338 0.205078 ..
CCV_NNC_GEMM_FORWARD [122]: [2] -> [1] (0)
|-> 1. 0x1438d1d70 (0x285da59c0:0) [1x4096x40] 0.087524 -0.084839 0.022324 ..
|-> 2. 0x1438d1cc0 (0x285da5980:0) [1x4096x40] 1.386719 -0.196899 -1.851562 ..
|<- 1. 0x1438a0cb0 (0x285da5a40:0) [1x4096x4096] 4.031250 2.867188 2.191406 ..
CCV_NNC_SOFTMAX_FORWARD [123]: [1] -> [1] (0)
|-> 1. 0x1438d1e20 (0x285da5a40:0) [4096x4096] 4.031250 2.867188 2.191406 ..
|<- 1. 0x1438d1e20 (0x285da5a40:0) [4096x4096] 0.009003 0.002810 0.001430 ..
CCV_NNC_GEMM_FORWARD [124]: [2] -> [1] (0)
|-> 1. 0x1438d1f40 (0x285da5a40:0) [1x4096x4096] 0.009003 0.002810 0.001430 ..
|-> 2. 0x1438d1e90 (0x285da5a80:0) [1x4096x40] -0.168457 0.082825 -0.655273 ..
|<- 1. 0x1438d4280 (0x285da5680:0) [1x4096x40] 0.018707 -0.049713 -0.241455 ..
CCV_NNC_GEMM_FORWARD [125]: [2] -> [1] (0)
|-> 1. 0x1438d2060 (0x285da59c0:0) [1x4096x40] 0.116150 0.235718 0.070007 ..
|-> 2. 0x1438d1fb0 (0x285da5980:0) [1x4096x40] -0.277832 -1.186523 0.947266 ..
|<- 1. 0x1438a0d20 (0x285da5a40:0) [1x4096x4096] 1.523438 1.729492 1.864258 ..
CCV_NNC_SOFTMAX_FORWARD [126]: [1] -> [1] (0)
|-> 1. 0x1438d2110 (0x285da5a40:0) [4096x4096] 1.523438 1.729492 1.864258 ..
|<- 1. 0x1438d2110 (0x285da5a40:0) [4096x4096] 0.000710 0.000873 0.000998 ..
CCV_NNC_GEMM_FORWARD [127]: [2] -> [1] (0)
|-> 1. 0x1438d2230 (0x285da5a40:0) [1x4096x4096] 0.000710 0.000873 0.000998 ..
|-> 2. 0x1438d2180 (0x285da5a80:0) [1x4096x40] -0.005127 0.099792 0.155029 ..
|<- 1. 0x1438d4330 (0x285da5680:0) [1x4096x40] 0.072449 -0.060333 -0.011993 ..
CCV_NNC_GEMM_FORWARD [128]: [2] -> [1] (0)
|-> 1. 0x1438d2350 (0x285da59c0:0) [1x4096x40] 0.019272 -0.055237 -0.130005 ..
|-> 2. 0x1438d22a0 (0x285da5980:0) [1x4096x40] 0.814453 -0.346191 1.026367 ..
|<- 1. 0x1438a0d90 (0x285da5a40:0) [1x4096x4096] 8.171875 4.007812 5.050781 ..
CCV_NNC_SOFTMAX_FORWARD [129]: [1] -> [1] (0)
|-> 1. 0x1438d2400 (0x285da5a40:0) [4096x4096] 8.171875 4.007812 5.050781 ..
|<- 1. 0x1438d2400 (0x285da5a40:0) [4096x4096] 0.051697 0.000803 0.002281 ..
CCV_NNC_GEMM_FORWARD [130]: [2] -> [1] (0)
|-> 1. 0x1438d2520 (0x285da5a40:0) [1x4096x4096] 0.051697 0.000803 0.002281 ..
|-> 2. 0x1438d2470 (0x285da5a80:0) [1x4096x40] 0.229004 -0.007763 0.674316 ..
|<- 1. 0x1438d43e0 (0x285da5680:0) [1x4096x40] 0.202148 0.293457 0.154907 ..
CCV_NNC_GEMM_FORWARD [131]: [2] -> [1] (0)
|-> 1. 0x1438d2640 (0x285da59c0:0) [1x4096x40] -0.156494 -0.095947 0.025284 ..
|-> 2. 0x1438d2590 (0x285da5980:0) [1x4096x40] -0.095276 0.494385 0.494873 ..
|<- 1. 0x1438a0e00 (0x285da5a40:0) [1x4096x4096] -0.452148 -1.506836 -1.910156 ..
CCV_NNC_SOFTMAX_FORWARD [132]: [1] -> [1] (0)
|-> 1. 0x1438d26f0 (0x285da5a40:0) [4096x4096] -0.452148 -1.506836 -1.910156 ..
|<- 1. 0x1438d26f0 (0x285da5a40:0) [4096x4096] 0.000643 0.000224 0.000150 ..
CCV_NNC_GEMM_FORWARD [133]: [2] -> [1] (0)
|-> 1. 0x1438d2810 (0x285da5a40:0) [1x4096x4096] 0.000643 0.000224 0.000150 ..
|-> 2. 0x1438d2760 (0x285da5a80:0) [1x4096x40] 1.302734 -0.050659 -0.475342 ..
|<- 1. 0x1438d4490 (0x285da5680:0) [1x4096x40] -0.125122 0.123169 -0.030411 ..
CCV_NNC_GEMM_FORWARD [134]: [2] -> [1] (0)
|-> 1. 0x1438d2930 (0x285da59c0:0) [1x4096x40] 0.181641 -0.239624 -0.156982 ..
|-> 2. 0x1438d2880 (0x285da5980:0) [1x4096x40] 0.471924 -0.942871 0.792969 ..
|<- 1. 0x1438a0e70 (0x285da5a40:0) [1x4096x4096] 1.342773 1.739258 0.361328 ..
CCV_NNC_SOFTMAX_FORWARD [135]: [1] -> [1] (0)
|-> 1. 0x1438d29e0 (0x285da5a40:0) [4096x4096] 1.342773 1.739258 0.361328 ..
|<- 1. 0x1438d29e0 (0x285da5a40:0) [4096x4096] 0.000418 0.000622 0.000157 ..
CCV_NNC_GEMM_FORWARD [136]: [2] -> [1] (0)
|-> 1. 0x1438d2b00 (0x285da5a40:0) [1x4096x4096] 0.000418 0.000622 0.000157 ..
|-> 2. 0x1438d2a50 (0x285da5a80:0) [1x4096x40] 0.333496 0.162231 0.011147 ..
|<- 1. 0x1438d4540 (0x285da5680:0) [1x4096x40] -0.164062 -0.099121 0.168091 ..
CCV_NNC_GEMM_FORWARD [137]: [2] -> [1] (0)
|-> 1. 0x1438d2c20 (0x285da59c0:0) [1x4096x40] 0.315186 0.172241 -0.090027 ..
|-> 2. 0x1438d2b70 (0x285da5980:0) [1x4096x40] 1.596680 -0.960449 0.928711 ..
|<- 1. 0x1438a0ee0 (0x285da5a40:0) [1x4096x4096] 7.625000 3.019531 3.916016 ..
CCV_NNC_SOFTMAX_FORWARD [138]: [1] -> [1] (0)
|-> 1. 0x1438d2cd0 (0x285da5a40:0) [4096x4096] 7.625000 3.019531 3.916016 ..
|<- 1. 0x1438d2cd0 (0x285da5a40:0) [4096x4096] 0.034180 0.000342 0.000838 ..
CCV_NNC_GEMM_FORWARD [139]: [2] -> [1] (0)
|-> 1. 0x1438d2df0 (0x285da5a40:0) [1x4096x4096] 0.034180 0.000342 0.000838 ..
|-> 2. 0x1438d2d40 (0x285da5a80:0) [1x4096x40] 0.084656 0.138184 0.002228 ..
|<- 1. 0x1438d45f0 (0x285da5680:0) [1x4096x40] -0.028610 0.000618 0.013924 ..
CCV_NNC_GEMM_FORWARD [140]: [2] -> [1] (0)
|-> 1. 0x1438d2f10 (0x285da59c0:0) [1x4096x40] -0.071655 -0.121826 -0.061707 ..
|-> 2. 0x1438d2e60 (0x285da5980:0) [1x4096x40] -0.478516 -1.603516 -0.821289 ..
|<- 1. 0x1438a0f50 (0x285da5a40:0) [1x4096x4096] 4.460938 2.183594 2.863281 ..
CCV_NNC_SOFTMAX_FORWARD [141]: [1] -> [1] (0)
|-> 1. 0x1438d2fc0 (0x285da5a40:0) [4096x4096] 4.460938 2.183594 2.863281 ..
|<- 1. 0x1438d2fc0 (0x285da5a40:0) [4096x4096] 0.017975 0.001843 0.003637 ..
CCV_NNC_GEMM_FORWARD [142]: [2] -> [1] (0)
|-> 1. 0x1438d30e0 (0x285da5a40:0) [1x4096x4096] 0.017975 0.001843 0.003637 ..
|-> 2. 0x1438d3030 (0x285da5a80:0) [1x4096x40] 0.279053 -0.195801 0.358887 ..
|<- 1. 0x1438d46a0 (0x285da5680:0) [1x4096x40] 0.075317 -0.022110 0.061371 ..
CCV_NNC_GEMM_FORWARD [143]: [2] -> [1] (0)
|-> 1. 0x1438d3200 (0x285da59c0:0) [1x4096x40] -0.276611 -0.201660 -0.025070 ..
|-> 2. 0x1438d3150 (0x285da5980:0) [1x4096x40] -0.522949 -0.113892 1.308594 ..
|<- 1. 0x1438a0fc0 (0x285da5a40:0) [1x4096x4096] 0.968262 1.105469 0.160156 ..
CCV_NNC_SOFTMAX_FORWARD [144]: [1] -> [1] (0)
|-> 1. 0x1438d32b0 (0x285da5a40:0) [4096x4096] 0.968262 1.105469 0.160156 ..
|<- 1. 0x1438d32b0 (0x285da5a40:0) [4096x4096] 0.000864 0.000990 0.000385 ..
CCV_NNC_GEMM_FORWARD [145]: [2] -> [1] (0)
|-> 1. 0x1438d33d0 (0x285da5a40:0) [1x4096x4096] 0.000864 0.000990 0.000385 ..
|-> 2. 0x1438d3320 (0x285da5a80:0) [1x4096x40] 0.065002 -0.490479 -0.035065 ..
|<- 1. 0x1438d4750 (0x285da5680:0) [1x4096x40] 0.084290 -0.009338 0.205078 ..
CCV_NNC_GEMM_FORWARD [146]: [2] -> [1] (0)
|-> 1. 0x1438d34f0 (0x285da59c0:0) [1x4096x40] 0.087524 -0.084839 0.022324 ..
|-> 2. 0x1438d3440 (0x285da5980:0) [1x4096x40] 1.386719 -0.196899 -1.851562 ..
|<- 1. 0x1438a1030 (0x285da5a40:0) [1x4096x4096] 4.031250 2.867188 2.191406 ..
CCV_NNC_SOFTMAX_FORWARD [147]: [1] -> [1] (0)
|-> 1. 0x1438d35a0 (0x285da5a40:0) [4096x4096] 4.031250 2.867188 2.191406 ..
|<- 1. 0x1438d35a0 (0x285da5a40:0) [4096x4096] 0.009003 0.002810 0.001430 ..
CCV_NNC_GEMM_FORWARD [148]: [2] -> [1] (0)
|-> 1. 0x1438d36c0 (0x285da5a40:0) [1x4096x4096] 0.009003 0.002810 0.001430 ..
|-> 2. 0x1438d3610 (0x285da5a80:0) [1x4096x40] -0.168457 0.082825 -0.655273 ..
|<- 1. 0x1438d4800 (0x285da5680:0) [1x4096x40] 0.018707 -0.049713 -0.241455 ..
CCV_NNC_GEMM_FORWARD [149]: [2] -> [1] (0)
|-> 1. 0x1438d37e0 (0x285da59c0:0) [1x4096x40] 0.116150 0.235718 0.070007 ..
|-> 2. 0x1438d3730 (0x285da5980:0) [1x4096x40] -0.277832 -1.186523 0.947266 ..
|<- 1. 0x1438a10a0 (0x285da5a40:0) [1x4096x4096] 1.523438 1.729492 1.864258 ..
CCV_NNC_SOFTMAX_FORWARD [150]: [1] -> [1] (0)
|-> 1. 0x1438d3890 (0x285da5a40:0) [4096x4096] 1.523438 1.729492 1.864258 ..
|<- 1. 0x1438d3890 (0x285da5a40:0) [4096x4096] 0.000710 0.000873 0.000998 ..
CCV_NNC_GEMM_FORWARD [151]: [2] -> [1] (0)
|-> 1. 0x1438d39b0 (0x285da5a40:0) [1x4096x4096] 0.000710 0.000873 0.000998 ..
|-> 2. 0x1438d3900 (0x285da5a80:0) [1x4096x40] -0.005127 0.099792 0.155029 ..
|<- 1. 0x1438d48b0 (0x285da5680:0) [1x4096x40] 0.072449 -0.060333 -0.011993 ..
CCV_NNC_GEMM_FORWARD [152]: [2] -> [1] (0)
|-> 1. 0x1438d3ad0 (0x285da59c0:0) [1x4096x40] 0.019272 -0.055237 -0.130005 ..
|-> 2. 0x1438d3a20 (0x285da5980:0) [1x4096x40] 0.814453 -0.346191 1.026367 ..
|<- 1. 0x1438a1110 (0x285da5a40:0) [1x4096x4096] 8.171875 4.007812 5.050781 ..
CCV_NNC_SOFTMAX_FORWARD [153]: [1] -> [1] (0)
|-> 1. 0x1438d3b80 (0x285da5a40:0) [4096x4096] 8.171875 4.007812 5.050781 ..
|<- 1. 0x1438d3b80 (0x285da5a40:0) [4096x4096] 0.051697 0.000803 0.002281 ..
CCV_NNC_GEMM_FORWARD [154]: [2] -> [1] (0)
|-> 1. 0x1438d3ca0 (0x285da5a40:0) [1x4096x4096] 0.051697 0.000803 0.002281 ..
|-> 2. 0x1438d3bf0 (0x285da5a80:0) [1x4096x40] 0.229004 -0.007763 0.674316 ..
|<- 1. 0x1438d4960 (0x285da5680:0) [1x4096x40] 0.202148 0.293457 0.154907 ..
CCV_NNC_GEMM_FORWARD [155]: [2] -> [1] (0)
|-> 1. 0x1438d3dc0 (0x285da59c0:0) [1x4096x40] -0.156494 -0.095947 0.025284 ..
|-> 2. 0x1438d3d10 (0x285da5980:0) [1x4096x40] -0.095276 0.494385 0.494873 ..
|<- 1. 0x1438a1180 (0x285da5a40:0) [1x4096x4096] -0.452148 -1.506836 -1.910156 ..
CCV_NNC_SOFTMAX_FORWARD [156]: [1] -> [1] (0)
|-> 1. 0x1438d3e70 (0x285da5a40:0) [4096x4096] -0.452148 -1.506836 -1.910156 ..
|<- 1. 0x1438d3e70 (0x285da5a40:0) [4096x4096] 0.000643 0.000224 0.000150 ..
CCV_NNC_GEMM_FORWARD [157]: [2] -> [1] (0)
|-> 1. 0x1438d3f90 (0x285da5a40:0) [1x4096x4096] 0.000643 0.000224 0.000150 ..
|-> 2. 0x1438d3ee0 (0x285da5a80:0) [1x4096x40] 1.302734 -0.050659 -0.475342 ..
|<- 1. 0x1438d4a10 (0x285da5680:0) [1x4096x40] -0.125122 0.123169 -0.030411 ..
CCV_NNC_TRANSPOSE_FORWARD [158]: [1] -> [1] (0)
|-> 1. 0x1438d4ac0 (0x285da5680:0) [2x8x4096x40] -0.164062 -0.099121 0.168091 ..
|<- 1. 0x1438a1260 (0x285da5940:0) [2x4096x8x40] -0.164062 -0.099121 0.168091 ..
CCV_NNC_GEMM_FORWARD [159]: [3] -> [1] (0)
|-> 1. 0x1438d4b30 (0x285da5940:0) [2x4096x320] -0.164062 -0.099121 0.168091 ..
|-> 2. 0x1438be060 (0x285d84e40:0) [320x320] 0.020599 0.010056 -0.034363 ..
|-> 3. 0x1438be0d0 (0x285d84e00:0) [320] 0.058563 0.010330 0.046692 ..
|<- 1. 0x1438a12d0 (0x285da5ac0:0) [2x4096x320] 0.045868 -0.097534 0.009132 ..
CCV_NNC_ADD_FORWARD [160]: [2] -> [1] (0)
|-> 1. 0x1438a12d0 (0x285da5ac0:0) [2x4096x320] 0.045868 -0.097534 0.009132 ..
|-> 2. 0x1438d1000 (0x285da56c0:0) [2x4096x320] 0.347656 0.462646 -0.141479 ..
|<- 1. 0x1438a12d0 (0x285da5ac0:0) [2x4096x320] 0.393555 0.365234 -0.132324 ..
CCV_NNC_LAYER_NORM_FORWARD [161]: [3] -> [3] (0)
|-> 1. 0x1438a12d0 (0x285da5ac0:0) [2x4096x320] 0.393555 0.365234 -0.132324 ..
|-> 2. 0x1438be140 (0x285d84d80:0) [1x1x320] 0.379883 0.422607 0.413086 ..
|-> 3. 0x1438be1b0 (0x285d84dc0:0) [1x1x320] -0.121826 -0.066040 -0.111389 ..
|<- 1. 0x1438a1340 (0x285da5940:0) [2x4096x320] 0.410400 0.477295 -0.416016 ..
|<- 2. 0x1438a13b0 (0x285da5b00:0) [2x4096x1] 0.049011 ..
|<- 3. 0x1438a1420 (0x285da5b40:0) [2x4096x1] 4.066406 ..
CCV_NNC_GEMM_FORWARD [162]: [2] -> [1] (0)
|-> 1. 0x1438a1340 (0x285da5940:0) [2x4096x320] 0.410400 0.477295 -0.416016 ..
|-> 2. 0x1438be220 (0x285d84180:0) [320x320] -0.023132 -0.141235 -0.164551 ..
|<- 1. 0x1438a1490 (0x285da5900:0) [2x4096x320] -0.523926 -0.234985 1.871094 ..
CCV_NNC_SCALAR_MUL_FORWARD [163]: [1] -> [1] (0)
|-> 1. 0x1438a1490 (0x285da5900:0) [2x4096x320] -0.523926 -0.234985 1.871094 ..
|<- 1. 0x1438a1490 (0x285da5900:0) [2x4096x320] -0.082825 -0.037140 0.295898 ..
CCV_NNC_TRANSPOSE_FORWARD [164]: [1] -> [1] (0)
|-> 1. 0x1438d4c10 (0x285da5900:0) [2x4096x8x40] -0.082825 -0.037140 0.295898 ..
|<- 1. 0x1438a15e0 (0x285da56c0:0) [2x8x4096x40] -0.082825 -0.037140 0.295898 ..
CCV_NNC_GEMM_FORWARD [165]: [2] -> [1] (0)
Wait: (0, 6)
|-> 1. 0x1438a15e0 (0x285da56c0:0) [2x8x4096x40] -0.082825 -0.037140 0.295898 ..
|-> 2. 0x1438a1570 (0x285da5bc0:0) [2x8x133x40] -0.231689 -0.019897 8.742188 ..
|<- 1. 0x1438a1650 (0x285da5c00:0) [2x8x4096x133] 7.828125 1.667969 -1.150391 ..
CCV_NNC_SOFTMAX_FORWARD [166]: [1] -> [1] (0)
|-> 1. 0x1438d4c80 (0x285da5c00:0) [65536x133] 7.828125 1.667969 -1.150391 ..
|<- 1. 0x1438d4c80 (0x285da5c00:0) [65536x133] 0.928711 0.001961 0.000117 ..
CCV_NNC_GEMM_FORWARD [167]: [2] -> [1] (0)
Wait: (0, 7)
|-> 1. 0x1438d4d60 (0x285da5c00:0) [2x8x4096x133] 0.928711 0.001961 0.000117 ..
|-> 2. 0x1438a1730 (0x285da5c80:0) [2x8x133x40] 0.030670 -0.073059 -0.036987 ..
|<- 1. 0x1438a17a0 (0x285da56c0:0) [2x8x4096x40] 0.064331 -0.074341 -0.010612 ..
CCV_NNC_TRANSPOSE_FORWARD [168]: [1] -> [1] (0)
|-> 1. 0x1438d4dd0 (0x285da56c0:0) [2x8x4096x40] 0.064331 -0.074341 -0.010612 ..
|<- 1. 0x1438a1810 (0x285da5940:0) [2x4096x8x40] 0.064331 -0.074341 -0.010612 ..
CCV_NNC_GEMM_FORWARD [169]: [3] -> [1] (0)
|-> 1. 0x1438d4e40 (0x285da5940:0) [2x4096x320] 0.064331 -0.074341 -0.010612 ..
|-> 2. 0x1438be370 (0x285d85140:0) [320x320] 0.006714 -0.007145 0.013000 ..
|-> 3. 0x1438be3e0 (0x285d849c0:0) [320] 0.037170 -0.006664 0.000309 ..
|<- 1. 0x1438a1880 (0x285da5a80:0) [2x4096x320] 0.043182 0.030182 0.011131 ..
CCV_NNC_ADD_FORWARD [170]: [2] -> [1] (0)
|-> 1. 0x1438a1880 (0x285da5a80:0) [2x4096x320] 0.043182 0.030182 0.011131 ..
|-> 2. 0x1438a12d0 (0x285da5ac0:0) [2x4096x320] 0.393555 0.365234 -0.132324 ..
|<- 1. 0x1438a1880 (0x285da5a80:0) [2x4096x320] 0.436768 0.395508 -0.121216 ..
CCV_NNC_LAYER_NORM_FORWARD [171]: [3] -> [3] (0)
|-> 1. 0x1438a1880 (0x285da5a80:0) [2x4096x320] 0.436768 0.395508 -0.121216 ..
|-> 2. 0x1438be450 (0x285d84ac0:0) [1x1x320] 0.416260 0.481934 0.441650 ..
|-> 3. 0x1438be4c0 (0x285d84a00:0) [1x1x320] -0.141479 -0.019455 0.005322 ..
|<- 1. 0x1438a18f0 (0x285da5ac0:0) [2x4096x320] 0.462646 0.604492 -0.288818 ..
|<- 2. 0x1438a1960 (0x285da5cc0:0) [2x4096x1] 0.054352 ..
|<- 3. 0x1438a19d0 (0x285da5d00:0) [2x4096x1] 3.794922 ..
Emit: (0, 8)
CCV_NNC_GEMM_FORWARD [172]: [3] -> [1] (0)
|-> 1. 0x1438a18f0 (0x285da5ac0:0) [2x4096x320] 0.462646 0.604492 -0.288818 ..
|-> 2. 0x1438be530 (0x285d84900:0) [1280x320] 0.018341 -0.062164 0.038361 ..
|-> 3. 0x1438be5a0 (0x285d851c0:0) [1280] 0.033142 -0.048279 -0.067139 ..
|<- 1. 0x1438a1a40 (0x285da5d40:0) [2x4096x1280] 0.161499 -0.139038 -1.244141 ..
CCV_NNC_GELU_FORWARD [173]: [1] -> [1] (0)
|-> 1. 0x1438a1a40 (0x285da5d40:0) [2x4096x1280] 0.161499 -0.139038 -1.244141 ..
|<- 1. 0x1438a1a40 (0x285da5d40:0) [2x4096x1280] 0.091125 -0.061829 -0.132812 ..
CCV_NNC_GEMM_FORWARD [174]: [3] -> [1] (1)
Wait: (1, 8)
|-> 1. 0x1438a18f0 (0x285da5ac0:0) [2x4096x320] 0.462646 0.604492 -0.288818 ..
|-> 2. 0x1438be610 (0x285d84b00:0) [1280x320] -0.035797 0.002018 0.014442 ..
|-> 3. 0x1438be680 (0x285d84940:0) [1280] 0.006767 0.075500 0.015762 ..
|<- 1. 0x1438a1ab0 (0x285da5d80:0) [2x4096x1280] -0.197021 0.565430 0.207397 ..
Emit: (1, 9)
CCV_NNC_MUL_FORWARD [175]: [2] -> [1] (0)
Wait: (0, 9)
|-> 1. 0x1438a1ab0 (0x285da5d80:0) [2x4096x1280] -0.197021 0.565430 0.207397 ..
|-> 2. 0x1438a1a40 (0x285da5d40:0) [2x4096x1280] 0.091125 -0.061829 -0.132812 ..
|<- 1. 0x1438a1ab0 (0x285da5d80:0) [2x4096x1280] -0.017960 -0.034973 -0.027542 ..
CCV_NNC_GEMM_FORWARD [176]: [3] -> [1] (0)
|-> 1. 0x1438a1ab0 (0x285da5d80:0) [2x4096x1280] -0.017960 -0.034973 -0.027542 ..
|-> 2. 0x1438be6f0 (0x285d84a80:0) [320x1280] 0.078674 0.009918 -0.000766 ..
|-> 3. 0x1438be760 (0x285d848c0:0) [320] -0.005562 0.002239 -0.023773 ..
|<- 1. 0x1438a1b20 (0x285da56c0:0) [2x4096x320] 0.103027 -0.406494 0.565430 ..
CCV_NNC_ADD_FORWARD [177]: [2] -> [1] (0)
|-> 1. 0x1438a1b20 (0x285da56c0:0) [2x4096x320] 0.103027 -0.406494 0.565430 ..
|-> 2. 0x1438a1880 (0x285da5a80:0) [2x4096x320] 0.436768 0.395508 -0.121216 ..
|<- 1. 0x1438a1b20 (0x285da56c0:0) [2x4096x320] 0.540039 -0.010986 0.444336 ..
CCV_NNC_CONVOLUTION_FORWARD [178]: [3] -> [1] (0)
|-> 1. 0x1438d4eb0 (0x285da56c0:0) [2x64x64x320] 0.540039 -0.010986 0.444336 ..
|-> 2. 0x1438be7d0 (0x285d84b40:0) [320x320x1x1] -0.025055 ..
|-> 3. 0x1438be840 (0x285d84980:0) [320] -0.039307 -0.017242 -0.024658 ..
|<- 1. 0x1438a1b90 (0x285da5680:0) [2x64x64x320] -0.526367 -0.144165 0.465576 ..
CCV_NNC_ADD_FORWARD [179]: [2] -> [1] (0)
|-> 1. 0x1438a1b90 (0x285da5680:0) [2x64x64x320] -0.526367 -0.144165 0.465576 ..
|-> 2. 0x1438a04d0 (0x285da5840:0) [2x64x64x320] 0.131836 -2.232422 0.687500 ..
|<- 1. 0x143909a80 (0x285e6d340:0) [2x64x64x320] -0.394531 -2.376953 1.153320 ..
CCV_NNC_GROUP_NORM_FORWARD [180]: [3] -> [3] (0)
|-> 1. 0x143909a80 (0x285e6d340:0) [2x64x64x320] -0.394531 -2.376953 1.153320 ..
|-> 2. 0x1438be8b0 (0x285d84a40:0) [1x1x1x320] 0.416992 0.220825 0.264160 ..
|-> 3. 0x1438be920 (0x285d84200:0) [1x1x1x320] -0.109131 0.241455 -0.181763 ..
|<- 1. 0x1438a1c00 (0x285da5680:0) [2x64x64x320] -0.260498 -0.254639 0.110901 ..
|<- 2. 0x1438a1c70 (0x285da5740:0) [2x1x1x32] -0.012650 -0.262451 -0.010139 ..
|<- 3. 0x1438a1ce0 (0x285da5700:0) [2x1x1x32] 0.950195 1.647461 5.222656 ..
CCV_NNC_SWISH_FORWARD [181]: [1] -> [1] (0)
|-> 1. 0x1438a1c00 (0x285da5680:0) [2x64x64x320] -0.260498 -0.254639 0.110901 ..
|<- 1. 0x1438a1c00 (0x285da5680:0) [2x64x64x320] -0.113403 -0.111206 0.058533 ..
CCV_NNC_CONVOLUTION_FORWARD [182]: [3] -> [1] (0)
|-> 1. 0x1438a1c00 (0x285da5680:0) [2x64x64x320] -0.113403 -0.111206 0.058533 ..
|-> 2. 0x1438bea70 (0x285d85180:0) [320x320x3x3] 0.032501 0.068237 0.137939 ..
|-> 3. 0x1438beae0 (0x285d843c0:0) [320] 0.019516 0.005825 -0.055542 ..
|<- 1. 0x1438a1dc0 (0x285da56c0:0) [2x64x64x320] -0.125488 -0.400635 -0.284424 ..
CCV_NNC_ADD_FORWARD [183]: [2] -> [1] (0)
Wait: (0, 10)
|-> 1. 0x1438a1dc0 (0x285da56c0:0) [2x64x64x320] -0.125488 -0.400635 -0.284424 ..
|-> 2. 0x1438d4f20 (0x285da5dc0:0) [2x1x1x320] 0.114136 0.382324 -0.697754 ..
|<- 1. 0x1438a1dc0 (0x285da56c0:0) [2x64x64x320] -0.011353 -0.018311 -0.982422 ..
CCV_NNC_GROUP_NORM_FORWARD [184]: [3] -> [3] (0)
|-> 1. 0x1438a1dc0 (0x285da56c0:0) [2x64x64x320] -0.011353 -0.018311 -0.982422 ..
|-> 2. 0x1438beb50 (0x285d852c0:0) [1x1x1x320] 0.733398 0.608398 0.626465 ..
|-> 3. 0x1438bebc0 (0x285d853c0:0) [1x1x1x320] -0.231812 -0.169800 -0.094360 ..
|<- 1. 0x1438a1e30 (0x285da5680:0) [2x64x64x320] -0.522461 -0.417969 -1.359375 ..
|<- 2. 0x1438a1ea0 (0x285da5e00:0) [2x1x1x32] 0.225830 0.153564 0.310059 ..
|<- 3. 0x1438a1f10 (0x285da5800:0) [2x1x1x32] 1.670898 1.156250 0.658203 ..
CCV_NNC_SWISH_FORWARD [185]: [1] -> [1] (0)
|-> 1. 0x1438a1e30 (0x285da5680:0) [2x64x64x320] -0.522461 -0.417969 -1.359375 ..
|<- 1. 0x1438a1e30 (0x285da5680:0) [2x64x64x320] -0.194458 -0.165894 -0.277832 ..
CCV_NNC_CONVOLUTION_FORWARD [186]: [3] -> [1] (0)
|-> 1. 0x1438a1e30 (0x285da5680:0) [2x64x64x320] -0.194458 -0.165894 -0.277832 ..
|-> 2. 0x1438bec30 (0x285d85400:0) [320x320x3x3] -0.011002 -0.015823 -0.001194 ..
|-> 3. 0x1438beca0 (0x285d85440:0) [320] -0.017487 0.020096 -0.013153 ..
|<- 1. 0x1438a1f80 (0x285da56c0:0) [2x64x64x320] -0.270020 0.777832 -0.507324 ..
CCV_NNC_ADD_FORWARD [187]: [2] -> [1] (0)
|-> 1. 0x143909a80 (0x285e6d340:0) [2x64x64x320] -0.394531 -2.376953 1.153320 ..
|-> 2. 0x1438a1f80 (0x285da56c0:0) [2x64x64x320] -0.270020 0.777832 -0.507324 ..
|<- 1. 0x1438a1ff0 (0x285da5840:0) [2x64x64x320] -0.664551 -1.599609 0.645996 ..
CCV_NNC_GROUP_NORM_FORWARD [188]: [3] -> [3] (0)
|-> 1. 0x1438a1ff0 (0x285da5840:0) [2x64x64x320] -0.664551 -1.599609 0.645996 ..
|-> 2. 0x1438bed10 (0x285d85480:0) [1x1x1x320] 0.402344 0.316650 0.406982 ..
|-> 3. 0x1438bed80 (0x285d854c0:0) [1x1x1x320] -0.076233 0.042206 -0.025192 ..
|<- 1. 0x1438a2060 (0x285da5680:0) [2x64x64x320] -0.560059 -0.807617 0.330811 ..
|<- 2. 0x1438a20d0 (0x285da5740:0) [2x1x1x32] 0.093933 -0.135376 -0.198242 ..
|<- 3. 0x1438a2140 (0x285da5700:0) [2x1x1x32] 1.584961 2.177734 2.802734 ..
CCV_NNC_CONVOLUTION_FORWARD [189]: [3] -> [1] (0)
|-> 1. 0x1438a2060 (0x285da5680:0) [2x64x64x320] -0.560059 -0.807617 0.330811 ..
|-> 2. 0x1438bedf0 (0x285d85500:0) [320x320x1x1] 0.017532 ..
|-> 3. 0x1438bee60 (0x285d85540:0) [320] -0.068604 0.206543 -0.054993 ..
|<- 1. 0x1438a21b0 (0x285da56c0:0) [2x64x64x320] -0.506348 -0.774414 0.334961 ..
CCV_NNC_LAYER_NORM_FORWARD [190]: [3] -> [3] (0)
|-> 1. 0x1438d4f90 (0x285da56c0:0) [2x4096x320] -0.506348 -0.774414 0.334961 ..
|-> 2. 0x1438beed0 (0x285d85580:0) [1x1x320] 0.716309 0.794922 0.938965 ..
|-> 3. 0x1438bef40 (0x285d855c0:0) [1x1x320] 0.058411 -0.022797 -0.025116 ..
|<- 1. 0x1438a2220 (0x285da5680:0) [2x4096x320] -0.615234 -1.161133 0.540527 ..
|<- 2. 0x1438a2290 (0x285da5e40:0) [2x4096x1] 0.006432 ..
|<- 3. 0x1438a2300 (0x285da5880:0) [2x4096x1] 1.833984 ..
Emit: (0, 11)
CCV_NNC_GEMM_FORWARD [191]: [2] -> [1] (0)
|-> 1. 0x1438a2220 (0x285da5680:0) [2x4096x320] -0.615234 -1.161133 0.540527 ..
|-> 2. 0x1438befb0 (0x285d85600:0) [320x320] 0.098633 -0.015945 -0.021072 ..
|<- 1. 0x1438a2370 (0x285da5900:0) [2x4096x320] -0.845703 0.704590 -1.113281 ..
CCV_NNC_SCALAR_MUL_FORWARD [192]: [1] -> [1] (0)
|-> 1. 0x1438a2370 (0x285da5900:0) [2x4096x320] -0.845703 0.704590 -1.113281 ..
|<- 1. 0x1438a2370 (0x285da5900:0) [2x4096x320] -0.133667 0.111389 -0.176025 ..
CCV_NNC_TRANSPOSE_FORWARD [193]: [1] -> [1] (0)
|-> 1. 0x1438d5070 (0x285da5900:0) [2x4096x8x40] -0.133667 0.111389 -0.176025 ..
|<- 1. 0x1438a24c0 (0x285da5e80:0) [2x8x4096x40] -0.133667 0.111389 -0.176025 ..
CCV_NNC_GEMM_FORWARD [194]: [2] -> [1] (1)
Wait: (1, 11)
|-> 1. 0x1438a2220 (0x285da5680:0) [2x4096x320] -0.615234 -1.161133 0.540527 ..
|-> 2. 0x1438bf020 (0x285d85640:0) [320x320] 0.096313 0.077942 0.058289 ..
|<- 1. 0x1438a23e0 (0x285da5940:0) [2x4096x320] -1.801758 -0.114258 -0.691895 ..
CCV_NNC_TRANSPOSE_FORWARD [195]: [1] -> [1] (1)
|-> 1. 0x1438d5000 (0x285da5940:0) [2x4096x8x40] -1.801758 -0.114258 -0.691895 ..
|<- 1. 0x1438a2450 (0x285da59c0:0) [2x8x4096x40] -1.801758 -0.114258 -0.691895 ..
Emit: (1, 12)
CCV_NNC_GEMM_FORWARD [196]: [2] -> [1] (2)
Wait: (2, 11)
|-> 1. 0x1438a2220 (0x285da5680:0) [2x4096x320] -0.615234 -1.161133 0.540527 ..
|-> 2. 0x1438bf090 (0x285d85680:0) [320x320] 0.093872 0.079895 -0.008286 ..
|<- 1. 0x1438a2530 (0x285da5ec0:0) [2x4096x320] -1.234375 0.313965 -0.631348 ..
CCV_NNC_TRANSPOSE_FORWARD [197]: [1] -> [1] (2)
|-> 1. 0x1438d51c0 (0x285da5ec0:0) [2x4096x8x40] -1.234375 0.313965 -0.631348 ..
|<- 1. 0x1438a2610 (0x285da5980:0) [2x8x4096x40] -1.234375 0.313965 -0.631348 ..
Emit: (2, 13)
CCV_NNC_GEMM_FORWARD [198]: [2] -> [1] (0)
Wait: (0, 12)
|-> 1. 0x1438d5150 (0x285da5e80:0) [1x4096x40] -0.133667 0.111389 -0.176025 ..
|-> 2. 0x1438d50e0 (0x285da59c0:0) [1x4096x40] -1.801758 -0.114258 -0.691895 ..
|<- 1. 0x1438a25a0 (0x285da5a40:0) [1x4096x4096] 9.351562 8.132812 8.390625 ..
CCV_NNC_SOFTMAX_FORWARD [199]: [1] -> [1] (0)
|-> 1. 0x1438d5230 (0x285da5a40:0) [4096x4096] 9.351562 8.132812 8.390625 ..
|<- 1. 0x1438d5230 (0x285da5a40:0) [4096x4096] 0.011200 0.003311 0.004284 ..
CCV_NNC_GEMM_FORWARD [200]: [2] -> [1] (0)
Wait: (0, 13)
|-> 1. 0x1438d5310 (0x285da5a40:0) [1x4096x4096] 0.011200 0.003311 0.004284 ..
|-> 2. 0x1438d52a0 (0x285da5980:0) [1x4096x40] -1.234375 0.313965 -0.631348 ..
|<- 1. 0x1438d7f90 (0x285da5680:0) [1x4096x40] -0.480469 -0.030075 -0.577637 ..
CCV_NNC_GEMM_FORWARD [201]: [2] -> [1] (0)
|-> 1. 0x1438d5430 (0x285da5e80:0) [1x4096x40] 0.036346 -0.232666 -0.030319 ..
|-> 2. 0x1438d5380 (0x285da59c0:0) [1x4096x40] 0.977051 -1.407227 1.997070 ..
|<- 1. 0x1438a2680 (0x285da5a40:0) [1x4096x4096] 9.007812 7.761719 7.343750 ..
CCV_NNC_SOFTMAX_FORWARD [202]: [1] -> [1] (0)
|-> 1. 0x1438d54e0 (0x285da5a40:0) [4096x4096] 9.007812 7.761719 7.343750 ..
|<- 1. 0x1438d54e0 (0x285da5a40:0) [4096x4096] 0.020401 0.005867 0.003862 ..
CCV_NNC_GEMM_FORWARD [203]: [2] -> [1] (0)
|-> 1. 0x1438d5600 (0x285da5a40:0) [1x4096x4096] 0.020401 0.005867 0.003862 ..
|-> 2. 0x1438d5550 (0x285da5980:0) [1x4096x40] 0.047607 0.135132 0.761719 ..
|<- 1. 0x1438d8000 (0x285da5680:0) [1x4096x40] -0.014862 0.101135 0.027740 ..
CCV_NNC_GEMM_FORWARD [204]: [2] -> [1] (0)
|-> 1. 0x1438d5720 (0x285da5e80:0) [1x4096x40] 0.040222 0.023972 -0.001418 ..
|-> 2. 0x1438d5670 (0x285da59c0:0) [1x4096x40] 1.561523 -1.250000 -0.090881 ..
|<- 1. 0x1438a26f0 (0x285da5a40:0) [1x4096x4096] 4.054688 4.242188 3.722656 ..
CCV_NNC_SOFTMAX_FORWARD [205]: [1] -> [1] (0)
|-> 1. 0x1438d57d0 (0x285da5a40:0) [4096x4096] 4.054688 4.242188 3.722656 ..
|<- 1. 0x1438d57d0 (0x285da5a40:0) [4096x4096] 0.001454 0.001754 0.001043 ..
CCV_NNC_GEMM_FORWARD [206]: [2] -> [1] (0)
|-> 1. 0x1438d58f0 (0x285da5a40:0) [1x4096x4096] 0.001454 0.001754 0.001043 ..
|-> 2. 0x1438d5840 (0x285da5980:0) [1x4096x40] 0.251709 -0.178223 0.285889 ..
|<- 1. 0x1438d80b0 (0x285da5680:0) [1x4096x40] 0.086182 0.041504 0.114563 ..
CCV_NNC_GEMM_FORWARD [207]: [2] -> [1] (0)
|-> 1. 0x1438d5a10 (0x285da5e80:0) [1x4096x40] 0.019974 -0.073975 0.106140 ..
|-> 2. 0x1438d5960 (0x285da59c0:0) [1x4096x40] -0.028793 -1.217773 -0.375977 ..
|<- 1. 0x1438a2760 (0x285da5a40:0) [1x4096x4096] 4.730469 3.630859 3.685547 ..
CCV_NNC_SOFTMAX_FORWARD [208]: [1] -> [1] (0)
|-> 1. 0x1438d5ac0 (0x285da5a40:0) [4096x4096] 4.730469 3.630859 3.685547 ..
|<- 1. 0x1438d5ac0 (0x285da5a40:0) [4096x4096] 0.004051 0.001349 0.001425 ..
CCV_NNC_GEMM_FORWARD [209]: [2] -> [1] (0)
|-> 1. 0x1438d5be0 (0x285da5a40:0) [1x4096x4096] 0.004051 0.001349 0.001425 ..
|-> 2. 0x1438d5b30 (0x285da5980:0) [1x4096x40] 0.143555 -0.132324 1.009766 ..
|<- 1. 0x1438d8160 (0x285da5680:0) [1x4096x40] 0.039490 0.045532 0.094360 ..
CCV_NNC_GEMM_FORWARD [210]: [2] -> [1] (0)
|-> 1. 0x1438d5d00 (0x285da5e80:0) [1x4096x40] -0.148804 0.187744 -0.056671 ..
|-> 2. 0x1438d5c50 (0x285da59c0:0) [1x4096x40] -0.924316 1.144531 -1.469727 ..
|<- 1. 0x1438a27d0 (0x285da5a40:0) [1x4096x4096] 7.554688 5.988281 5.781250 ..
CCV_NNC_SOFTMAX_FORWARD [211]: [1] -> [1] (0)
|-> 1. 0x1438d5db0 (0x285da5a40:0) [4096x4096] 7.554688 5.988281 5.781250 ..
|<- 1. 0x1438d5db0 (0x285da5a40:0) [4096x4096] 0.014046 0.002932 0.002384 ..
CCV_NNC_GEMM_FORWARD [212]: [2] -> [1] (0)
|-> 1. 0x1438d5ed0 (0x285da5a40:0) [1x4096x4096] 0.014046 0.002932 0.002384 ..
|-> 2. 0x1438d5e20 (0x285da5980:0) [1x4096x40] -0.618652 0.281982 0.310791 ..
|<- 1. 0x1438d8210 (0x285da5680:0) [1x4096x40] 0.006836 -0.060699 0.176758 ..
CCV_NNC_GEMM_FORWARD [213]: [2] -> [1] (0)
|-> 1. 0x1438d5ff0 (0x285da5e80:0) [1x4096x40] 0.218262 -0.120422 0.347412 ..
|-> 2. 0x1438d5f40 (0x285da59c0:0) [1x4096x40] -0.532715 -0.188354 4.175781 ..
|<- 1. 0x1438a2840 (0x285da5a40:0) [1x4096x4096] 10.250000 7.101562 7.339844 ..
CCV_NNC_SOFTMAX_FORWARD [214]: [1] -> [1] (0)
|-> 1. 0x1438d60a0 (0x285da5a40:0) [4096x4096] 10.250000 7.101562 7.339844 ..
|<- 1. 0x1438d60a0 (0x285da5a40:0) [4096x4096] 0.023895 0.001026 0.001302 ..
CCV_NNC_GEMM_FORWARD [215]: [2] -> [1] (0)
|-> 1. 0x1438d61c0 (0x285da5a40:0) [1x4096x4096] 0.023895 0.001026 0.001302 ..
|-> 2. 0x1438d6110 (0x285da5980:0) [1x4096x40] -0.437500 0.525391 -0.966309 ..
|<- 1. 0x1438d82c0 (0x285da5680:0) [1x4096x40] -0.296143 0.230469 -0.135742 ..
CCV_NNC_GEMM_FORWARD [216]: [2] -> [1] (0)
|-> 1. 0x1438d62e0 (0x285da5e80:0) [1x4096x40] -0.085999 0.054932 -0.167969 ..
|-> 2. 0x1438d6230 (0x285da59c0:0) [1x4096x40] -0.529297 -0.944824 -0.623047 ..
|<- 1. 0x1438a28b0 (0x285da5a40:0) [1x4096x4096] 7.566406 6.777344 6.683594 ..
CCV_NNC_SOFTMAX_FORWARD [217]: [1] -> [1] (0)
|-> 1. 0x1438d6390 (0x285da5a40:0) [4096x4096] 7.566406 6.777344 6.683594 ..
|<- 1. 0x1438d6390 (0x285da5a40:0) [4096x4096] 0.010353 0.004704 0.004280 ..
CCV_NNC_GEMM_FORWARD [218]: [2] -> [1] (0)
|-> 1. 0x1438d64b0 (0x285da5a40:0) [1x4096x4096] 0.010353 0.004704 0.004280 ..
|-> 2. 0x1438d6400 (0x285da5980:0) [1x4096x40] -0.015900 1.032227 -0.623047 ..
|<- 1. 0x1438d8370 (0x285da5680:0) [1x4096x40] 0.037140 0.132935 -0.143066 ..
CCV_NNC_GEMM_FORWARD [219]: [2] -> [1] (0)
|-> 1. 0x1438d65d0 (0x285da5e80:0) [1x4096x40] 0.319580 0.124512 -0.062927 ..
|-> 2. 0x1438d6520 (0x285da59c0:0) [1x4096x40] 1.286133 0.171265 0.064270 ..
|<- 1. 0x1438a2920 (0x285da5a40:0) [1x4096x4096] 6.781250 6.187500 5.871094 ..
CCV_NNC_SOFTMAX_FORWARD [220]: [1] -> [1] (0)
|-> 1. 0x1438d6680 (0x285da5a40:0) [4096x4096] 6.781250 6.187500 5.871094 ..
|<- 1. 0x1438d6680 (0x285da5a40:0) [4096x4096] 0.008736 0.004826 0.003517 ..
CCV_NNC_GEMM_FORWARD [221]: [2] -> [1] (0)
|-> 1. 0x1438d67a0 (0x285da5a40:0) [1x4096x4096] 0.008736 0.004826 0.003517 ..
|-> 2. 0x1438d66f0 (0x285da5980:0) [1x4096x40] 0.427734 1.020508 -0.391602 ..
|<- 1. 0x1438d8420 (0x285da5680:0) [1x4096x40] 0.159302 0.101929 0.190674 ..
CCV_NNC_GEMM_FORWARD [222]: [2] -> [1] (0)
|-> 1. 0x1438d68c0 (0x285da5e80:0) [1x4096x40] -0.121582 0.141235 -0.150635 ..
|-> 2. 0x1438d6810 (0x285da59c0:0) [1x4096x40] -1.795898 0.127197 -0.631836 ..
|<- 1. 0x1438a2990 (0x285da5a40:0) [1x4096x4096] 9.343750 7.875000 8.054688 ..
CCV_NNC_SOFTMAX_FORWARD [223]: [1] -> [1] (0)
|-> 1. 0x1438d6970 (0x285da5a40:0) [4096x4096] 9.343750 7.875000 8.054688 ..
|<- 1. 0x1438d6970 (0x285da5a40:0) [4096x4096] 0.013000 0.002993 0.003582 ..
CCV_NNC_GEMM_FORWARD [224]: [2] -> [1] (0)
|-> 1. 0x1438d6a90 (0x285da5a40:0) [1x4096x4096] 0.013000 0.002993 0.003582 ..
|-> 2. 0x1438d69e0 (0x285da5980:0) [1x4096x40] -1.347656 0.064209 -0.540039 ..
|<- 1. 0x1438d84d0 (0x285da5680:0) [1x4096x40] -0.609375 -0.265625 -0.527832 ..
CCV_NNC_GEMM_FORWARD [225]: [2] -> [1] (0)
|-> 1. 0x1438d6bb0 (0x285da5e80:0) [1x4096x40] 0.030289 -0.225830 -0.026382 ..
|-> 2. 0x1438d6b00 (0x285da59c0:0) [1x4096x40] 1.179688 -1.460938 2.224609 ..
|<- 1. 0x1438a2a00 (0x285da5a40:0) [1x4096x4096] 8.429688 7.464844 6.949219 ..
CCV_NNC_SOFTMAX_FORWARD [226]: [1] -> [1] (0)
|-> 1. 0x1438d6c60 (0x285da5a40:0) [4096x4096] 8.429688 7.464844 6.949219 ..
|<- 1. 0x1438d6c60 (0x285da5a40:0) [4096x4096] 0.012314 0.004692 0.002802 ..
CCV_NNC_GEMM_FORWARD [227]: [2] -> [1] (0)
|-> 1. 0x1438d6d80 (0x285da5a40:0) [1x4096x4096] 0.012314 0.004692 0.002802 ..
|-> 2. 0x1438d6cd0 (0x285da5980:0) [1x4096x40] 0.073669 0.051788 0.720703 ..
|<- 1. 0x1438d8580 (0x285da5680:0) [1x4096x40] 0.076477 0.103088 -0.050232 ..
CCV_NNC_GEMM_FORWARD [228]: [2] -> [1] (0)
|-> 1. 0x1438d6ea0 (0x285da5e80:0) [1x4096x40] 0.018051 0.040741 0.011230 ..
|-> 2. 0x1438d6df0 (0x285da59c0:0) [1x4096x40] 1.687500 -1.275391 -0.047729 ..
|<- 1. 0x1438a2a70 (0x285da5a40:0) [1x4096x4096] 3.875000 3.882812 3.503906 ..
CCV_NNC_SOFTMAX_FORWARD [229]: [1] -> [1] (0)
|-> 1. 0x1438d6f50 (0x285da5a40:0) [4096x4096] 3.875000 3.882812 3.503906 ..
|<- 1. 0x1438d6f50 (0x285da5a40:0) [4096x4096] 0.001207 0.001217 0.000833 ..
CCV_NNC_GEMM_FORWARD [230]: [2] -> [1] (0)
|-> 1. 0x1438d7070 (0x285da5a40:0) [1x4096x4096] 0.001207 0.001217 0.000833 ..
|-> 2. 0x1438d6fc0 (0x285da5980:0) [1x4096x40] 0.242554 -0.054993 0.248047 ..
|<- 1. 0x1438d8630 (0x285da5680:0) [1x4096x40] -0.027039 0.208130 0.120972 ..
CCV_NNC_GEMM_FORWARD [231]: [2] -> [1] (0)
|-> 1. 0x1438d7190 (0x285da5e80:0) [1x4096x40] 0.043915 -0.065063 0.132202 ..
|-> 2. 0x1438d70e0 (0x285da59c0:0) [1x4096x40] 0.310303 -1.222656 -0.413330 ..
|<- 1. 0x1438a2ae0 (0x285da5a40:0) [1x4096x4096] 4.406250 3.453125 3.429688 ..
CCV_NNC_SOFTMAX_FORWARD [232]: [1] -> [1] (0)
|-> 1. 0x1438d7240 (0x285da5a40:0) [4096x4096] 4.406250 3.453125 3.429688 ..
|<- 1. 0x1438d7240 (0x285da5a40:0) [4096x4096] 0.003157 0.001217 0.001189 ..
CCV_NNC_GEMM_FORWARD [233]: [2] -> [1] (0)
|-> 1. 0x1438d7360 (0x285da5a40:0) [1x4096x4096] 0.003157 0.001217 0.001189 ..
|-> 2. 0x1438d72b0 (0x285da5980:0) [1x4096x40] 0.327148 -0.010162 0.989258 ..
|<- 1. 0x1438d86e0 (0x285da5680:0) [1x4096x40] 0.274902 0.059875 0.136841 ..
CCV_NNC_GEMM_FORWARD [234]: [2] -> [1] (0)
|-> 1. 0x1438d7480 (0x285da5e80:0) [1x4096x40] -0.153931 0.160278 -0.040253 ..
|-> 2. 0x1438d73d0 (0x285da59c0:0) [1x4096x40] -0.802246 1.071289 -1.416016 ..
|<- 1. 0x1438a2b50 (0x285da5a40:0) [1x4096x4096] 7.312500 5.859375 5.621094 ..
CCV_NNC_SOFTMAX_FORWARD [235]: [1] -> [1] (0)
|-> 1. 0x1438d7530 (0x285da5a40:0) [4096x4096] 7.312500 5.859375 5.621094 ..
|<- 1. 0x1438d7530 (0x285da5a40:0) [4096x4096] 0.010078 0.002357 0.001858 ..
CCV_NNC_GEMM_FORWARD [236]: [2] -> [1] (0)
|-> 1. 0x1438d7650 (0x285da5a40:0) [1x4096x4096] 0.010078 0.002357 0.001858 ..
|-> 2. 0x1438d75a0 (0x285da5980:0) [1x4096x40] -0.635742 0.504883 0.295898 ..
|<- 1. 0x1438d8790 (0x285da5680:0) [1x4096x40] -0.069641 0.125977 0.092590 ..
CCV_NNC_GEMM_FORWARD [237]: [2] -> [1] (0)
|-> 1. 0x1438d7770 (0x285da5e80:0) [1x4096x40] 0.232300 -0.134033 0.339844 ..
|-> 2. 0x1438d76c0 (0x285da59c0:0) [1x4096x40] -0.541992 -0.197754 4.132812 ..
|<- 1. 0x1438a2bc0 (0x285da5a40:0) [1x4096x4096] 9.828125 6.730469 6.972656 ..
CCV_NNC_SOFTMAX_FORWARD [238]: [1] -> [1] (0)
|-> 1. 0x1438d7820 (0x285da5a40:0) [4096x4096] 9.828125 6.730469 6.972656 ..
|<- 1. 0x1438d7820 (0x285da5a40:0) [4096x4096] 0.019714 0.000890 0.001135 ..
CCV_NNC_GEMM_FORWARD [239]: [2] -> [1] (0)
|-> 1. 0x1438d7940 (0x285da5a40:0) [1x4096x4096] 0.019714 0.000890 0.001135 ..
|-> 2. 0x1438d7890 (0x285da5980:0) [1x4096x40] -0.355225 0.519043 -0.960938 ..
|<- 1. 0x1438d8840 (0x285da5680:0) [1x4096x40] -0.189331 0.215210 -0.134521 ..
CCV_NNC_GEMM_FORWARD [240]: [2] -> [1] (0)
|-> 1. 0x1438d7a60 (0x285da5e80:0) [1x4096x40] -0.090820 0.027908 -0.152954 ..
|-> 2. 0x1438d79b0 (0x285da59c0:0) [1x4096x40] -0.628418 -1.050781 -0.554199 ..
|<- 1. 0x1438a2c30 (0x285da5a40:0) [1x4096x4096] 7.300781 6.683594 6.578125 ..
CCV_NNC_SOFTMAX_FORWARD [241]: [1] -> [1] (0)
|-> 1. 0x1438d7b10 (0x285da5a40:0) [4096x4096] 7.300781 6.683594 6.578125 ..
|<- 1. 0x1438d7b10 (0x285da5a40:0) [4096x4096] 0.007607 0.004105 0.003693 ..
CCV_NNC_GEMM_FORWARD [242]: [2] -> [1] (0)
|-> 1. 0x1438d7c30 (0x285da5a40:0) [1x4096x4096] 0.007607 0.004105 0.003693 ..
|-> 2. 0x1438d7b80 (0x285da5980:0) [1x4096x40] -0.047211 1.030273 -0.604980 ..
|<- 1. 0x1438d88f0 (0x285da5680:0) [1x4096x40] 0.035095 0.157349 -0.082520 ..
CCV_NNC_GEMM_FORWARD [243]: [2] -> [1] (0)
|-> 1. 0x1438d7d50 (0x285da5e80:0) [1x4096x40] 0.318115 0.130615 -0.016373 ..
|-> 2. 0x1438d7ca0 (0x285da59c0:0) [1x4096x40] 1.349609 0.178345 0.092834 ..
|<- 1. 0x1438a2ca0 (0x285da5a40:0) [1x4096x4096] 6.468750 5.933594 5.675781 ..
CCV_NNC_SOFTMAX_FORWARD [244]: [1] -> [1] (0)
|-> 1. 0x1438d7e00 (0x285da5a40:0) [4096x4096] 6.468750 5.933594 5.675781 ..
|<- 1. 0x1438d7e00 (0x285da5a40:0) [4096x4096] 0.006683 0.003914 0.003025 ..
CCV_NNC_GEMM_FORWARD [245]: [2] -> [1] (0)
|-> 1. 0x1438d7f20 (0x285da5a40:0) [1x4096x4096] 0.006683 0.003914 0.003025 ..
|-> 2. 0x1438d7e70 (0x285da5980:0) [1x4096x40] 0.369629 1.071289 -0.148315 ..
|<- 1. 0x1438d89a0 (0x285da5680:0) [1x4096x40] 0.111816 0.073914 0.389160 ..
CCV_NNC_TRANSPOSE_FORWARD [246]: [1] -> [1] (0)
|-> 1. 0x1438d8a50 (0x285da5680:0) [2x8x4096x40] -0.480469 -0.030075 -0.577637 ..
|<- 1. 0x1438a2d80 (0x285da5940:0) [2x4096x8x40] -0.480469 -0.030075 -0.577637 ..
CCV_NNC_GEMM_FORWARD [247]: [3] -> [1] (0)
|-> 1. 0x1438d8ac0 (0x285da5940:0) [2x4096x320] -0.480469 -0.030075 -0.577637 ..
|-> 2. 0x1438bf100 (0x285d856c0:0) [320x320] -0.011864 0.022491 0.002018 ..
|-> 3. 0x1438bf170 (0x285d85700:0) [320] -0.023834 0.402588 -0.052490 ..
|<- 1. 0x1438a2df0 (0x285da5680:0) [2x4096x320] -0.020523 0.836426 -0.084534 ..
CCV_NNC_ADD_FORWARD [248]: [2] -> [1] (0)
|-> 1. 0x1438a2df0 (0x285da5680:0) [2x4096x320] -0.020523 0.836426 -0.084534 ..
|-> 2. 0x1438d4f90 (0x285da56c0:0) [2x4096x320] -0.506348 -0.774414 0.334961 ..
|<- 1. 0x1438a2df0 (0x285da5680:0) [2x4096x320] -0.526855 0.062012 0.250488 ..
CCV_NNC_LAYER_NORM_FORWARD [249]: [3] -> [3] (0)
|-> 1. 0x1438a2df0 (0x285da5680:0) [2x4096x320] -0.526855 0.062012 0.250488 ..
|-> 2. 0x1438bf1e0 (0x285d85740:0) [1x1x320] 0.270508 0.379883 0.366699 ..
|-> 3. 0x1438bf250 (0x285d85780:0) [1x1x320] -0.055328 -0.174805 -0.028580 ..
|<- 1. 0x1438a2e60 (0x285da5940:0) [2x4096x320] -0.341553 -0.124695 0.159546 ..
|<- 2. 0x1438a2ed0 (0x285da5b40:0) [2x4096x1] -0.003223 ..
|<- 3. 0x1438a2f40 (0x285da5b00:0) [2x4096x1] 2.021484 ..
CCV_NNC_GEMM_FORWARD [250]: [2] -> [1] (0)
|-> 1. 0x1438a2e60 (0x285da5940:0) [2x4096x320] -0.341553 -0.124695 0.159546 ..
|-> 2. 0x1438bf2c0 (0x285d857c0:0) [320x320] 0.007980 0.001403 0.000995 ..
|<- 1. 0x1438a2fb0 (0x285da5900:0) [2x4096x320] -0.100891 -0.179932 -0.498535 ..
CCV_NNC_SCALAR_MUL_FORWARD [251]: [1] -> [1] (0)
|-> 1. 0x1438a2fb0 (0x285da5900:0) [2x4096x320] -0.100891 -0.179932 -0.498535 ..
|<- 1. 0x1438a2fb0 (0x285da5900:0) [2x4096x320] -0.015945 -0.028442 -0.078796 ..
CCV_NNC_TRANSPOSE_FORWARD [252]: [1] -> [1] (0)
|-> 1. 0x1438d8ba0 (0x285da5900:0) [2x4096x8x40] -0.015945 -0.028442 -0.078796 ..
|<- 1. 0x1438a3100 (0x285da56c0:0) [2x8x4096x40] -0.015945 -0.028442 -0.078796 ..
CCV_NNC_GEMM_FORWARD [253]: [2] -> [1] (0)
Wait: (0, 14)
|-> 1. 0x1438a3100 (0x285da56c0:0) [2x8x4096x40] -0.015945 -0.028442 -0.078796 ..
|-> 2. 0x1438a3090 (0x285da5f40:0) [2x8x133x40] -0.131592 -0.084351 1.820312 ..
|<- 1. 0x1438a3170 (0x285da5c00:0) [2x8x4096x133] 4.199219 2.185547 1.363281 ..
CCV_NNC_SOFTMAX_FORWARD [254]: [1] -> [1] (0)
|-> 1. 0x1438d8c10 (0x285da5c00:0) [65536x133] 4.199219 2.185547 1.363281 ..
|<- 1. 0x1438d8c10 (0x285da5c00:0) [65536x133] 0.349121 0.046631 0.020493 ..
CCV_NNC_GEMM_FORWARD [255]: [2] -> [1] (0)
Wait: (0, 15)
|-> 1. 0x1438d8cf0 (0x285da5c00:0) [2x8x4096x133] 0.349121 0.046631 0.020493 ..
|-> 2. 0x1438a3250 (0x285da5fc0:0) [2x8x133x40] 0.014427 -0.034271 -0.016800 ..
|<- 1. 0x1438a32c0 (0x285da56c0:0) [2x8x4096x40] -0.003622 -0.073608 -0.039703 ..
CCV_NNC_TRANSPOSE_FORWARD [256]: [1] -> [1] (0)
|-> 1. 0x1438d8d60 (0x285da56c0:0) [2x8x4096x40] -0.003622 -0.073608 -0.039703 ..
|<- 1. 0x1438a3330 (0x285da5940:0) [2x4096x8x40] -0.003622 -0.073608 -0.039703 ..
CCV_NNC_GEMM_FORWARD [257]: [3] -> [1] (0)
|-> 1. 0x1438d8dd0 (0x285da5940:0) [2x4096x320] -0.003622 -0.073608 -0.039703 ..
|-> 2. 0x1438bf410 (0x285d85880:0) [320x320] -0.001719 0.002342 0.004265 ..
|-> 3. 0x1438bf480 (0x285d858c0:0) [320] 0.001342 0.312988 0.043030 ..
|<- 1. 0x1438a33a0 (0x285da5ac0:0) [2x4096x320] 0.007706 0.598145 0.029892 ..
CCV_NNC_ADD_FORWARD [258]: [2] -> [1] (0)
|-> 1. 0x1438a33a0 (0x285da5ac0:0) [2x4096x320] 0.007706 0.598145 0.029892 ..
|-> 2. 0x1438a2df0 (0x285da5680:0) [2x4096x320] -0.526855 0.062012 0.250488 ..
|<- 1. 0x1438a33a0 (0x285da5ac0:0) [2x4096x320] -0.519043 0.660156 0.280273 ..
CCV_NNC_LAYER_NORM_FORWARD [259]: [3] -> [3] (0)
|-> 1. 0x1438a33a0 (0x285da5ac0:0) [2x4096x320] -0.519043 0.660156 0.280273 ..
|-> 2. 0x1438bf4f0 (0x285d85900:0) [1x1x320] 0.512207 0.289551 0.570312 ..
|-> 3. 0x1438bf560 (0x285d85940:0) [1x1x320] 0.000493 -0.209961 -0.087341 ..
|<- 1. 0x1438a3410 (0x285da6000:0) [2x4096x320] -0.515137 0.178833 0.246826 ..
|<- 2. 0x1438a3480 (0x285da6040:0) [2x4096x1] -0.013893 ..
|<- 3. 0x1438a34f0 (0x285da6080:0) [2x4096x1] 1.992188 ..
Emit: (0, 16)
CCV_NNC_GEMM_FORWARD [260]: [3] -> [1] (0)
|-> 1. 0x1438a3410 (0x285da6000:0) [2x4096x320] -0.515137 0.178833 0.246826 ..
|-> 2. 0x1438bf5d0 (0x285d85980:0) [1280x320] -0.038788 0.038239 0.032745 ..
|-> 3. 0x1438bf640 (0x285d859c0:0) [1280] 0.097046 0.036072 0.077148 ..
|<- 1. 0x1438a3560 (0x285da5d40:0) [2x4096x1280] 0.205566 0.226318 0.549316 ..
CCV_NNC_GELU_FORWARD [261]: [1] -> [1] (0)
|-> 1. 0x1438a3560 (0x285da5d40:0) [2x4096x1280] 0.205566 0.226318 0.549316 ..
|<- 1. 0x1438a3560 (0x285da5d40:0) [2x4096x1280] 0.119507 0.133423 0.389160 ..
CCV_NNC_GEMM_FORWARD [262]: [3] -> [1] (1)
Wait: (1, 16)
|-> 1. 0x1438a3410 (0x285da6000:0) [2x4096x320] -0.515137 0.178833 0.246826 ..
|-> 2. 0x1438bf6b0 (0x285d85a00:0) [1280x320] -0.009453 -0.016190 0.016663 ..
|-> 3. 0x1438bf720 (0x285d85a40:0) [1280] -0.011093 -0.059692 -0.029694 ..
|<- 1. 0x1438a35d0 (0x285da5d80:0) [2x4096x1280] -0.123535 0.455322 -0.136108 ..
Emit: (1, 17)
CCV_NNC_MUL_FORWARD [263]: [2] -> [1] (0)
Wait: (0, 17)
|-> 1. 0x1438a35d0 (0x285da5d80:0) [2x4096x1280] -0.123535 0.455322 -0.136108 ..
|-> 2. 0x1438a3560 (0x285da5d40:0) [2x4096x1280] 0.119507 0.133423 0.389160 ..
|<- 1. 0x1438a35d0 (0x285da5d80:0) [2x4096x1280] -0.014763 0.060760 -0.052979 ..
CCV_NNC_GEMM_FORWARD [264]: [3] -> [1] (0)
|-> 1. 0x1438a35d0 (0x285da5d80:0) [2x4096x1280] -0.014763 0.060760 -0.052979 ..
|-> 2. 0x1438bf790 (0x285d85a80:0) [320x1280] 0.064453 0.011925 -0.068970 ..
|-> 3. 0x1438bf800 (0x285d85ac0:0) [320] -0.027100 -0.310547 -0.016296 ..
|<- 1. 0x1438a3640 (0x285da56c0:0) [2x4096x320] -0.001959 -0.343994 -0.374268 ..
CCV_NNC_ADD_FORWARD [265]: [2] -> [1] (0)
|-> 1. 0x1438a3640 (0x285da56c0:0) [2x4096x320] -0.001959 -0.343994 -0.374268 ..
|-> 2. 0x1438a33a0 (0x285da5ac0:0) [2x4096x320] -0.519043 0.660156 0.280273 ..
|<- 1. 0x1438a3640 (0x285da56c0:0) [2x4096x320] -0.520996 0.316162 -0.093994 ..
CCV_NNC_CONVOLUTION_FORWARD [266]: [3] -> [1] (0)
|-> 1. 0x1438d8e40 (0x285da56c0:0) [2x64x64x320] -0.520996 0.316162 -0.093994 ..
|-> 2. 0x1438bf870 (0x285d85b00:0) [320x320x1x1] -0.055328 ..
|-> 3. 0x1438bf8e0 (0x285d85b40:0) [320] 0.022568 0.040405 -0.043579 ..
|<- 1. 0x1438a36b0 (0x285da5ac0:0) [2x64x64x320] 0.085571 0.700684 0.460449 ..
CCV_NNC_ADD_FORWARD [267]: [2] -> [1] (0)
|-> 1. 0x1438a36b0 (0x285da5ac0:0) [2x64x64x320] 0.085571 0.700684 0.460449 ..
|-> 2. 0x1438a1ff0 (0x285da5840:0) [2x64x64x320] -0.664551 -1.599609 0.645996 ..
|<- 1. 0x143905990 (0x285de0a40:0) [2x64x64x320] -0.579102 -0.898926 1.106445 ..
CCV_NNC_CONVOLUTION_FORWARD [268]: [3] -> [1] (0)
|-> 1. 0x143905990 (0x285de0a40:0) [2x64x64x320] -0.579102 -0.898926 1.106445 ..
|-> 2. 0x1438bf950 (0x285d85b80:0) [320x320x3x3] 0.000292 -0.000571 -0.037109 ..
|-> 3. 0x1438bf9c0 (0x285d85bc0:0) [320] 0.000891 -0.006954 -0.006714 ..
|<- 1. 0x1439018a0 (0x285df0000:0) [2x32x32x320] 0.989258 0.309814 0.657715 ..
Emit: (0, 19)
CCV_NNC_GROUP_NORM_FORWARD [269]: [3] -> [3] (0)
|-> 1. 0x1439018a0 (0x285df0000:0) [2x32x32x320] 0.989258 0.309814 0.657715 ..
|-> 2. 0x1438bfa30 (0x285d85c00:0) [1x1x1x320] 0.254639 0.270996 0.242065 ..
|-> 3. 0x1438bfaa0 (0x285d85c40:0) [1x1x1x320] 0.009743 0.018799 0.027435 ..
|<- 1. 0x1438a3720 (0x285da60c0:0) [2x32x32x320] 0.219238 0.100952 0.165161 ..
|<- 2. 0x1438a3790 (0x285da6100:0) [2x1x1x32] -0.086548 0.030014 0.079834 ..
|<- 3. 0x1438a3800 (0x285da6140:0) [2x1x1x32] 0.764648 1.391602 1.579102 ..
CCV_NNC_SWISH_FORWARD [270]: [1] -> [1] (0)
|-> 1. 0x1438a3720 (0x285da60c0:0) [2x32x32x320] 0.219238 0.100952 0.165161 ..
|<- 1. 0x1438a3720 (0x285da60c0:0) [2x32x32x320] 0.121582 0.053009 0.089355 ..
CCV_NNC_CONVOLUTION_FORWARD [271]: [3] -> [1] (0)
|-> 1. 0x1438a3720 (0x285da60c0:0) [2x32x32x320] 0.121582 0.053009 0.089355 ..
|-> 2. 0x1438bfbf0 (0x285d85d00:0) [640x320x3x3] -0.003166 -0.036407 -0.039703 ..
|-> 3. 0x1438bfc60 (0x285d85d40:0) [640] 0.025604 0.001693 0.020493 ..
|<- 1. 0x1438a38e0 (0x285da61c0:0) [2x32x32x640] -0.563965 -0.265381 0.013863 ..
CCV_NNC_ADD_FORWARD [272]: [2] -> [1] (0)
Wait: (0, 18)
|-> 1. 0x1438a38e0 (0x285da61c0:0) [2x32x32x640] -0.563965 -0.265381 0.013863 ..
|-> 2. 0x1438d8eb0 (0x285da6180:0) [2x1x1x640] 0.351318 -0.119873 0.318848 ..
|<- 1. 0x1438a38e0 (0x285da61c0:0) [2x32x32x640] -0.212646 -0.385254 0.332764 ..
CCV_NNC_GROUP_NORM_FORWARD [273]: [3] -> [3] (0)
|-> 1. 0x1438a38e0 (0x285da61c0:0) [2x32x32x640] -0.212646 -0.385254 0.332764 ..
|-> 2. 0x1438bfcd0 (0x285d85d80:0) [1x1x1x640] 0.268799 0.246338 0.254639 ..
|-> 3. 0x1438bfd40 (0x285d85dc0:0) [1x1x1x640] -0.096436 -0.092163 -0.112000 ..
|<- 1. 0x1438a3950 (0x285da6200:0) [2x32x32x640] -0.117004 -0.155640 0.014198 ..
|<- 2. 0x1438a39c0 (0x285da6240:0) [2x1x1x32] -0.139771 0.230103 0.045135 ..
|<- 3. 0x1438a3a30 (0x285da6280:0) [2x1x1x32] 1.048828 2.091797 1.273438 ..
CCV_NNC_SWISH_FORWARD [274]: [1] -> [1] (0)
|-> 1. 0x1438a3950 (0x285da6200:0) [2x32x32x640] -0.117004 -0.155640 0.014198 ..
|<- 1. 0x1438a3950 (0x285da6200:0) [2x32x32x640] -0.055084 -0.071777 0.007149 ..
CCV_NNC_CONVOLUTION_FORWARD [275]: [3] -> [1] (0)
|-> 1. 0x1438a3950 (0x285da6200:0) [2x32x32x640] -0.055084 -0.071777 0.007149 ..
|-> 2. 0x1438bfdb0 (0x285d85e00:0) [640x640x3x3] -0.040833 -0.005260 0.009308 ..
|-> 3. 0x1438bfe20 (0x285d85e40:0) [640] 0.005589 0.024704 0.081360 ..
|<- 1. 0x1438a3aa0 (0x285da61c0:0) [2x32x32x640] -0.117065 0.945312 0.622070 ..
CCV_NNC_CONVOLUTION_FORWARD [276]: [3] -> [1] (1)
Wait: (1, 19)
|-> 1. 0x1439018a0 (0x285df0000:0) [2x32x32x320] 0.989258 0.309814 0.657715 ..
|-> 2. 0x1438bfe90 (0x285d85e80:0) [640x320x1x1] 0.000690 ..
|-> 3. 0x1438bff00 (0x285d85ec0:0) [640] 0.021500 0.020828 0.086731 ..
|<- 1. 0x1438a3b10 (0x285da62c0:0) [2x32x32x640] -1.510742 -0.214111 -0.177734 ..
Emit: (1, 20)
CCV_NNC_ADD_FORWARD [277]: [2] -> [1] (0)
Wait: (0, 20)
|-> 1. 0x1438a3b10 (0x285da62c0:0) [2x32x32x640] -1.510742 -0.214111 -0.177734 ..
|-> 2. 0x1438a3aa0 (0x285da61c0:0) [2x32x32x640] -0.117065 0.945312 0.622070 ..
|<- 1. 0x1438a3b10 (0x285da62c0:0) [2x32x32x640] -1.627930 0.731445 0.444336 ..
CCV_NNC_GROUP_NORM_FORWARD [278]: [3] -> [3] (0)
|-> 1. 0x1438a3b10 (0x285da62c0:0) [2x32x32x640] -1.627930 0.731445 0.444336 ..
|-> 2. 0x1438bff70 (0x285d85f00:0) [1x1x1x640] 0.250977 0.392822 0.360107 ..
|-> 3. 0x1438bffe0 (0x285d85f40:0) [1x1x1x640] -0.014748 -0.003046 0.059326 ..
|<- 1. 0x1438a3b80 (0x285da6200:0) [2x32x32x640] -0.317383 0.351807 0.292236 ..
|<- 2. 0x1438a3bf0 (0x285da6100:0) [2x1x1x32] -0.279297 0.080261 -0.018372 ..
|<- 3. 0x1438a3c60 (0x285da6140:0) [2x1x1x32] 0.894043 1.658203 1.358398 ..
CCV_NNC_CONVOLUTION_FORWARD [279]: [3] -> [1] (0)
|-> 1. 0x1438a3b80 (0x285da6200:0) [2x32x32x640] -0.317383 0.351807 0.292236 ..
|-> 2. 0x1438c0050 (0x285d85f80:0) [640x640x1x1] 0.002949 ..
|-> 3. 0x1438c00c0 (0x285d85fc0:0) [640] 0.040070 -0.046509 -0.025711 ..
|<- 1. 0x1438a3cd0 (0x285da61c0:0) [2x32x32x640] 0.011711 0.003101 0.220581 ..
CCV_NNC_LAYER_NORM_FORWARD [280]: [3] -> [3] (0)
|-> 1. 0x1438d8f20 (0x285da61c0:0) [2x1024x640] 0.011711 0.003101 0.220581 ..
|-> 2. 0x1438c0130 (0x285d86000:0) [1x1x640] 0.505859 0.574707 0.518555 ..
|-> 3. 0x1438c01a0 (0x285d86040:0) [1x1x640] -0.050354 0.034210 -0.035522 ..
|<- 1. 0x1438a3d40 (0x285da6300:0) [2x1024x640] -0.038330 0.039764 0.153809 ..
|<- 2. 0x1438a3db0 (0x285da6340:0) [2x1024x1] -0.002829 ..
|<- 3. 0x1438a3e20 (0x285da6380:0) [2x1024x1] 1.633789 ..
Emit: (0, 21)
CCV_NNC_GEMM_FORWARD [281]: [2] -> [1] (0)
|-> 1. 0x1438a3d40 (0x285da6300:0) [2x1024x640] -0.038330 0.039764 0.153809 ..
|-> 2. 0x1438c0210 (0x285d86080:0) [640x640] 0.021545 0.046692 -0.021286 ..
|<- 1. 0x1438a3e90 (0x285da63c0:0) [2x1024x640] -0.520996 -1.092773 -0.407471 ..
CCV_NNC_SCALAR_MUL_FORWARD [282]: [1] -> [1] (0)
|-> 1. 0x1438a3e90 (0x285da63c0:0) [2x1024x640] -0.520996 -1.092773 -0.407471 ..
|<- 1. 0x1438a3e90 (0x285da63c0:0) [2x1024x640] -0.058258 -0.122192 -0.045563 ..
CCV_NNC_TRANSPOSE_FORWARD [283]: [1] -> [1] (0)
|-> 1. 0x1438d9000 (0x285da63c0:0) [2x1024x8x80] -0.058258 -0.122192 -0.045563 ..
|<- 1. 0x1438a3fe0 (0x285da6480:0) [2x8x1024x80] -0.058258 -0.122192 -0.045563 ..
CCV_NNC_GEMM_FORWARD [284]: [2] -> [1] (1)
Wait: (1, 21)
|-> 1. 0x1438a3d40 (0x285da6300:0) [2x1024x640] -0.038330 0.039764 0.153809 ..
|-> 2. 0x1438c0280 (0x285d860c0:0) [640x640] 0.084473 -0.108582 0.039673 ..
|<- 1. 0x1438a3f00 (0x285da6400:0) [2x1024x640] -0.410889 -0.769531 -0.632812 ..
CCV_NNC_TRANSPOSE_FORWARD [285]: [1] -> [1] (1)
|-> 1. 0x1438d8f90 (0x285da6400:0) [2x1024x8x80] -0.410889 -0.769531 -0.632812 ..
|<- 1. 0x1438a3f70 (0x285da6440:0) [2x8x1024x80] -0.410889 -0.769531 -0.632812 ..
Emit: (1, 22)
CCV_NNC_GEMM_FORWARD [286]: [2] -> [1] (2)
Wait: (2, 21)
|-> 1. 0x1438a3d40 (0x285da6300:0) [2x1024x640] -0.038330 0.039764 0.153809 ..
|-> 2. 0x1438c02f0 (0x285d86100:0) [640x640] -0.016006 0.012390 -0.068909 ..
|<- 1. 0x1438a4050 (0x285da64c0:0) [2x1024x640] -0.335938 0.587891 0.184082 ..
CCV_NNC_TRANSPOSE_FORWARD [287]: [1] -> [1] (2)
|-> 1. 0x1438d9150 (0x285da64c0:0) [2x1024x8x80] -0.335938 0.587891 0.184082 ..
|<- 1. 0x1438a4130 (0x285da6200:0) [2x8x1024x80] -0.335938 0.587891 0.184082 ..
Emit: (2, 23)
CCV_NNC_GEMM_FORWARD [288]: [2] -> [1] (0)
Wait: (0, 22)
|-> 1. 0x1438d90e0 (0x285da6480:0) [1x1024x80] -0.058258 -0.122192 -0.045563 ..
|-> 2. 0x1438d9070 (0x285da6440:0) [1x1024x80] -0.410889 -0.769531 -0.632812 ..
|<- 1. 0x1438a40c0 (0x285da6500:0) [1x1024x1024] 5.570312 5.574219 5.335938 ..
CCV_NNC_SOFTMAX_FORWARD [289]: [1] -> [1] (0)
|-> 1. 0x1438d91c0 (0x285da6500:0) [1024x1024] 5.570312 5.574219 5.335938 ..
|<- 1. 0x1438d91c0 (0x285da6500:0) [1024x1024] 0.017990 0.018066 0.014236 ..
CCV_NNC_GEMM_FORWARD [290]: [2] -> [1] (0)
Wait: (0, 23)
|-> 1. 0x1438d92a0 (0x285da6500:0) [1x1024x1024] 0.017990 0.018066 0.014236 ..
|-> 2. 0x1438d9230 (0x285da6200:0) [1x1024x80] -0.335938 0.587891 0.184082 ..
|<- 1. 0x1438dbf20 (0x285da6300:0) [1x1024x80] -0.361084 0.128540 -0.017471 ..
CCV_NNC_GEMM_FORWARD [291]: [2] -> [1] (0)
|-> 1. 0x1438d93c0 (0x285da6480:0) [1x1024x80] 0.183472 -0.044678 -0.124023 ..
|-> 2. 0x1438d9310 (0x285da6440:0) [1x1024x80] 1.311523 -1.477539 -0.934082 ..
|<- 1. 0x1438a41a0 (0x285da6500:0) [1x1024x1024] 8.023438 2.181641 4.316406 ..
CCV_NNC_SOFTMAX_FORWARD [292]: [1] -> [1] (0)
|-> 1. 0x1438d9470 (0x285da6500:0) [1024x1024] 8.023438 2.181641 4.316406 ..
|<- 1. 0x1438d9470 (0x285da6500:0) [1024x1024] 0.016083 0.000047 0.000395 ..
CCV_NNC_GEMM_FORWARD [293]: [2] -> [1] (0)
|-> 1. 0x1438d9590 (0x285da6500:0) [1x1024x1024] 0.016083 0.000047 0.000395 ..
|-> 2. 0x1438d94e0 (0x285da6200:0) [1x1024x80] -0.179077 0.330566 -0.060211 ..
|<- 1. 0x1438dbf90 (0x285da6300:0) [1x1024x80] 0.000919 0.247803 -0.168701 ..
CCV_NNC_GEMM_FORWARD [294]: [2] -> [1] (0)
|-> 1. 0x1438d96b0 (0x285da6480:0) [1x1024x80] -0.057922 -0.082520 -0.039917 ..
|-> 2. 0x1438d9600 (0x285da6440:0) [1x1024x80] -1.572266 -1.166992 0.088196 ..
|<- 1. 0x1438a4210 (0x285da6500:0) [1x1024x1024] 5.429688 3.023438 3.111328 ..
CCV_NNC_SOFTMAX_FORWARD [295]: [1] -> [1] (0)
|-> 1. 0x1438d9760 (0x285da6500:0) [1024x1024] 5.429688 3.023438 3.111328 ..
|<- 1. 0x1438d9760 (0x285da6500:0) [1024x1024] 0.052948 0.004772 0.005211 ..
CCV_NNC_GEMM_FORWARD [296]: [2] -> [1] (0)
|-> 1. 0x1438d9880 (0x285da6500:0) [1x1024x1024] 0.052948 0.004772 0.005211 ..
|-> 2. 0x1438d97d0 (0x285da6200:0) [1x1024x80] -0.742676 -0.222290 -0.208740 ..
|<- 1. 0x1438dc040 (0x285da6300:0) [1x1024x80] -0.292725 -0.001611 0.300781 ..
CCV_NNC_GEMM_FORWARD [297]: [2] -> [1] (0)
|-> 1. 0x1438d99a0 (0x285da6480:0) [1x1024x80] 0.012566 -0.013527 -0.073425 ..
|-> 2. 0x1438d98f0 (0x285da6440:0) [1x1024x80] -2.072266 -0.619141 -1.301758 ..
|<- 1. 0x1438a4280 (0x285da6500:0) [1x1024x1024] 8.476562 8.156250 9.359375 ..
CCV_NNC_SOFTMAX_FORWARD [298]: [1] -> [1] (0)
|-> 1. 0x1438d9a50 (0x285da6500:0) [1024x1024] 8.476562 8.156250 9.359375 ..
|<- 1. 0x1438d9a50 (0x285da6500:0) [1024x1024] 0.003235 0.002348 0.007820 ..
CCV_NNC_GEMM_FORWARD [299]: [2] -> [1] (0)
|-> 1. 0x1438d9b70 (0x285da6500:0) [1x1024x1024] 0.003235 0.002348 0.007820 ..
|-> 2. 0x1438d9ac0 (0x285da6200:0) [1x1024x80] 0.027679 0.418701 -0.992676 ..
|<- 1. 0x1438dc0f0 (0x285da6300:0) [1x1024x80] -0.282227 0.398438 -0.941895 ..
CCV_NNC_GEMM_FORWARD [300]: [2] -> [1] (0)
|-> 1. 0x1438d9c90 (0x285da6480:0) [1x1024x80] -0.044586 -0.031982 -0.024704 ..
|-> 2. 0x1438d9be0 (0x285da6440:0) [1x1024x80] 1.074219 0.126831 1.488281 ..
|<- 1. 0x1438a42f0 (0x285da6500:0) [1x1024x1024] 0.976562 1.429688 1.472656 ..
CCV_NNC_SOFTMAX_FORWARD [301]: [1] -> [1] (0)
|-> 1. 0x1438d9d40 (0x285da6500:0) [1024x1024] 0.976562 1.429688 1.472656 ..
|<- 1. 0x1438d9d40 (0x285da6500:0) [1024x1024] 0.001372 0.002159 0.002253 ..
CCV_NNC_GEMM_FORWARD [302]: [2] -> [1] (0)
|-> 1. 0x1438d9e60 (0x285da6500:0) [1x1024x1024] 0.001372 0.002159 0.002253 ..
|-> 2. 0x1438d9db0 (0x285da6200:0) [1x1024x80] 0.544922 0.029510 0.598633 ..
|<- 1. 0x1438dc1a0 (0x285da6300:0) [1x1024x80] 0.154419 0.206909 0.036774 ..
CCV_NNC_GEMM_FORWARD [303]: [2] -> [1] (0)
|-> 1. 0x1438d9f80 (0x285da6480:0) [1x1024x80] 0.044128 0.020248 0.016449 ..
|-> 2. 0x1438d9ed0 (0x285da6440:0) [1x1024x80] -0.579102 -0.297852 -0.833984 ..
|<- 1. 0x1438a4360 (0x285da6500:0) [1x1024x1024] 0.775391 -0.621094 -0.245117 ..
CCV_NNC_SOFTMAX_FORWARD [304]: [1] -> [1] (0)
|-> 1. 0x1438da030 (0x285da6500:0) [1024x1024] 0.775391 -0.621094 -0.245117 ..
|<- 1. 0x1438da030 (0x285da6500:0) [1024x1024] 0.003210 0.000794 0.001157 ..
CCV_NNC_GEMM_FORWARD [305]: [2] -> [1] (0)
|-> 1. 0x1438da150 (0x285da6500:0) [1x1024x1024] 0.003210 0.000794 0.001157 ..
|-> 2. 0x1438da0a0 (0x285da6200:0) [1x1024x80] -0.126099 0.404541 -0.460449 ..
|<- 1. 0x1438dc250 (0x285da6300:0) [1x1024x80] -0.294922 0.374512 0.024796 ..
CCV_NNC_GEMM_FORWARD [306]: [2] -> [1] (0)
|-> 1. 0x1438da270 (0x285da6480:0) [1x1024x80] 0.011032 -0.000726 -0.145264 ..
|-> 2. 0x1438da1c0 (0x285da6440:0) [1x1024x80] -1.261719 1.200195 -1.605469 ..
|<- 1. 0x1438a43d0 (0x285da6500:0) [1x1024x1024] 5.765625 3.843750 3.955078 ..
CCV_NNC_SOFTMAX_FORWARD [307]: [1] -> [1] (0)
|-> 1. 0x1438da320 (0x285da6500:0) [1024x1024] 5.765625 3.843750 3.955078 ..
|<- 1. 0x1438da320 (0x285da6500:0) [1024x1024] 0.034363 0.005028 0.005619 ..
CCV_NNC_GEMM_FORWARD [308]: [2] -> [1] (0)
|-> 1. 0x1438da440 (0x285da6500:0) [1x1024x1024] 0.034363 0.005028 0.005619 ..
|-> 2. 0x1438da390 (0x285da6200:0) [1x1024x80] -0.669922 -0.351074 -0.237671 ..
|<- 1. 0x1438dc300 (0x285da6300:0) [1x1024x80] -0.017807 -0.226807 -0.214600 ..
CCV_NNC_GEMM_FORWARD [309]: [2] -> [1] (0)
|-> 1. 0x1438da560 (0x285da6480:0) [1x1024x80] 0.061798 -0.091064 0.092712 ..
|-> 2. 0x1438da4b0 (0x285da6440:0) [1x1024x80] -1.122070 0.973633 2.224609 ..
|<- 1. 0x1438a4440 (0x285da6500:0) [1x1024x1024] 6.023438 4.640625 4.320312 ..
CCV_NNC_SOFTMAX_FORWARD [310]: [1] -> [1] (0)
|-> 1. 0x1438da610 (0x285da6500:0) [1024x1024] 6.023438 4.640625 4.320312 ..
|<- 1. 0x1438da610 (0x285da6500:0) [1024x1024] 0.064880 0.016281 0.011818 ..
CCV_NNC_GEMM_FORWARD [311]: [2] -> [1] (0)
|-> 1. 0x1438da730 (0x285da6500:0) [1x1024x1024] 0.064880 0.016281 0.011818 ..
|-> 2. 0x1438da680 (0x285da6200:0) [1x1024x80] -0.178711 1.040039 -0.553711 ..
|<- 1. 0x1438dc3b0 (0x285da6300:0) [1x1024x80] -0.082153 0.366699 -0.263428 ..
CCV_NNC_GEMM_FORWARD [312]: [2] -> [1] (0)
|-> 1. 0x1438da850 (0x285da6480:0) [1x1024x80] -0.038757 -0.099304 -0.036530 ..
|-> 2. 0x1438da7a0 (0x285da6440:0) [1x1024x80] -0.388428 -1.009766 -0.566895 ..
|<- 1. 0x1438a44b0 (0x285da6500:0) [1x1024x1024] 5.679688 5.593750 5.460938 ..
CCV_NNC_SOFTMAX_FORWARD [313]: [1] -> [1] (0)
|-> 1. 0x1438da900 (0x285da6500:0) [1024x1024] 5.679688 5.593750 5.460938 ..
|<- 1. 0x1438da900 (0x285da6500:0) [1024x1024] 0.021042 0.019318 0.016907 ..
CCV_NNC_GEMM_FORWARD [314]: [2] -> [1] (0)
|-> 1. 0x1438daa20 (0x285da6500:0) [1x1024x1024] 0.021042 0.019318 0.016907 ..
|-> 2. 0x1438da970 (0x285da6200:0) [1x1024x80] -0.329834 0.572266 0.132324 ..
|<- 1. 0x1438dc460 (0x285da6300:0) [1x1024x80] -0.384521 0.130493 -0.053589 ..
CCV_NNC_GEMM_FORWARD [315]: [2] -> [1] (0)
|-> 1. 0x1438dab40 (0x285da6480:0) [1x1024x80] 0.178711 -0.053009 -0.130005 ..
|-> 2. 0x1438daa90 (0x285da6440:0) [1x1024x80] 1.332031 -1.637695 -0.878906 ..
|<- 1. 0x1438a4520 (0x285da6500:0) [1x1024x1024] 7.808594 2.779297 4.605469 ..
CCV_NNC_SOFTMAX_FORWARD [316]: [1] -> [1] (0)
|-> 1. 0x1438dabf0 (0x285da6500:0) [1024x1024] 7.808594 2.779297 4.605469 ..
|<- 1. 0x1438dabf0 (0x285da6500:0) [1024x1024] 0.013405 0.000088 0.000545 ..
CCV_NNC_GEMM_FORWARD [317]: [2] -> [1] (0)
|-> 1. 0x1438dad10 (0x285da6500:0) [1x1024x1024] 0.013405 0.000088 0.000545 ..
|-> 2. 0x1438dac60 (0x285da6200:0) [1x1024x80] -0.192017 0.287109 -0.053925 ..
|<- 1. 0x1438dc510 (0x285da6300:0) [1x1024x80] 0.139404 0.192505 -0.123840 ..
CCV_NNC_GEMM_FORWARD [318]: [2] -> [1] (0)
|-> 1. 0x1438dae30 (0x285da6480:0) [1x1024x80] -0.055725 -0.087036 -0.044281 ..
|-> 2. 0x1438dad80 (0x285da6440:0) [1x1024x80] -1.325195 -1.289062 0.051819 ..
|<- 1. 0x1438a4590 (0x285da6500:0) [1x1024x1024] 5.421875 3.320312 3.195312 ..
CCV_NNC_SOFTMAX_FORWARD [319]: [1] -> [1] (0)
|-> 1. 0x1438daee0 (0x285da6500:0) [1024x1024] 5.421875 3.320312 3.195312 ..
|<- 1. 0x1438daee0 (0x285da6500:0) [1024x1024] 0.057922 0.007080 0.006248 ..
CCV_NNC_GEMM_FORWARD [320]: [2] -> [1] (0)
|-> 1. 0x1438db000 (0x285da6500:0) [1x1024x1024] 0.057922 0.007080 0.006248 ..
|-> 2. 0x1438daf50 (0x285da6200:0) [1x1024x80] -0.742188 -0.330811 -0.071472 ..
|<- 1. 0x1438dc5c0 (0x285da6300:0) [1x1024x80] -0.361084 -0.045593 0.334473 ..
CCV_NNC_GEMM_FORWARD [321]: [2] -> [1] (0)
|-> 1. 0x1438db120 (0x285da6480:0) [1x1024x80] 0.014198 0.003281 -0.079468 ..
|-> 2. 0x1438db070 (0x285da6440:0) [1x1024x80] -2.187500 -0.302734 -1.355469 ..
|<- 1. 0x1438a4600 (0x285da6500:0) [1x1024x1024] 8.507812 8.203125 9.304688 ..
CCV_NNC_SOFTMAX_FORWARD [322]: [1] -> [1] (0)
|-> 1. 0x1438db1d0 (0x285da6500:0) [1024x1024] 8.507812 8.203125 9.304688 ..
|<- 1. 0x1438db1d0 (0x285da6500:0) [1024x1024] 0.003477 0.002563 0.007713 ..
CCV_NNC_GEMM_FORWARD [323]: [2] -> [1] (0)
|-> 1. 0x1438db2f0 (0x285da6500:0) [1x1024x1024] 0.003477 0.002563 0.007713 ..
|-> 2. 0x1438db240 (0x285da6200:0) [1x1024x80] 0.006760 0.414062 -0.980957 ..
|<- 1. 0x1438dc670 (0x285da6300:0) [1x1024x80] -0.318848 0.344482 -0.938965 ..
CCV_NNC_GEMM_FORWARD [324]: [2] -> [1] (0)
|-> 1. 0x1438db410 (0x285da6480:0) [1x1024x80] -0.034363 -0.038727 -0.018570 ..
|-> 2. 0x1438db360 (0x285da6440:0) [1x1024x80] 0.910156 0.247681 1.322266 ..
|<- 1. 0x1438a4670 (0x285da6500:0) [1x1024x1024] 1.238281 1.551758 1.779297 ..
CCV_NNC_SOFTMAX_FORWARD [325]: [1] -> [1] (0)
|-> 1. 0x1438db4c0 (0x285da6500:0) [1024x1024] 1.238281 1.551758 1.779297 ..
|<- 1. 0x1438db4c0 (0x285da6500:0) [1024x1024] 0.001794 0.002455 0.003080 ..
CCV_NNC_GEMM_FORWARD [326]: [2] -> [1] (0)
|-> 1. 0x1438db5e0 (0x285da6500:0) [1x1024x1024] 0.001794 0.002455 0.003080 ..
|-> 2. 0x1438db530 (0x285da6200:0) [1x1024x80] 0.464355 0.148926 0.725098 ..
|<- 1. 0x1438dc720 (0x285da6300:0) [1x1024x80] 0.254883 0.322021 0.157227 ..
CCV_NNC_GEMM_FORWARD [327]: [2] -> [1] (0)
|-> 1. 0x1438db700 (0x285da6480:0) [1x1024x80] 0.039307 0.029373 -0.006130 ..
|-> 2. 0x1438db650 (0x285da6440:0) [1x1024x80] -0.614258 -0.156738 -0.780273 ..
|<- 1. 0x1438a46e0 (0x285da6500:0) [1x1024x1024] 0.920410 -0.377930 -0.031647 ..
CCV_NNC_SOFTMAX_FORWARD [328]: [1] -> [1] (0)
|-> 1. 0x1438db7b0 (0x285da6500:0) [1024x1024] 0.920410 -0.377930 -0.031647 ..
|<- 1. 0x1438db7b0 (0x285da6500:0) [1024x1024] 0.002964 0.000809 0.001144 ..
CCV_NNC_GEMM_FORWARD [329]: [2] -> [1] (0)
|-> 1. 0x1438db8d0 (0x285da6500:0) [1x1024x1024] 0.002964 0.000809 0.001144 ..
|-> 2. 0x1438db820 (0x285da6200:0) [1x1024x80] -0.185791 0.209961 -0.484375 ..
|<- 1. 0x1438dc7d0 (0x285da6300:0) [1x1024x80] -0.371338 0.261719 0.041748 ..
CCV_NNC_GEMM_FORWARD [330]: [2] -> [1] (0)
|-> 1. 0x1438db9f0 (0x285da6480:0) [1x1024x80] 0.001505 -0.010872 -0.146973 ..
|-> 2. 0x1438db940 (0x285da6440:0) [1x1024x80] -1.353516 1.194336 -1.552734 ..
|<- 1. 0x1438a4750 (0x285da6500:0) [1x1024x1024] 5.667969 3.976562 4.187500 ..
CCV_NNC_SOFTMAX_FORWARD [331]: [1] -> [1] (0)
|-> 1. 0x1438dbaa0 (0x285da6500:0) [1024x1024] 5.667969 3.976562 4.187500 ..
|<- 1. 0x1438dbaa0 (0x285da6500:0) [1024x1024] 0.036499 0.006725 0.008308 ..
CCV_NNC_GEMM_FORWARD [332]: [2] -> [1] (0)
|-> 1. 0x1438dbbc0 (0x285da6500:0) [1x1024x1024] 0.036499 0.006725 0.008308 ..
|-> 2. 0x1438dbb10 (0x285da6200:0) [1x1024x80] -0.753906 -0.347900 -0.301025 ..
|<- 1. 0x1438dc880 (0x285da6300:0) [1x1024x80] -0.161499 -0.282471 -0.173218 ..
CCV_NNC_GEMM_FORWARD [333]: [2] -> [1] (0)
|-> 1. 0x1438dbce0 (0x285da6480:0) [1x1024x80] 0.087769 -0.096741 0.088684 ..
|-> 2. 0x1438dbc30 (0x285da6440:0) [1x1024x80] -1.050781 1.060547 2.183594 ..
|<- 1. 0x1438a47c0 (0x285da6500:0) [1x1024x1024] 6.304688 5.085938 4.675781 ..
CCV_NNC_SOFTMAX_FORWARD [334]: [1] -> [1] (0)
|-> 1. 0x1438dbd90 (0x285da6500:0) [1024x1024] 6.304688 5.085938 4.675781 ..
|<- 1. 0x1438dbd90 (0x285da6500:0) [1024x1024] 0.075073 0.022186 0.014725 ..
CCV_NNC_GEMM_FORWARD [335]: [2] -> [1] (0)
|-> 1. 0x1438dbeb0 (0x285da6500:0) [1x1024x1024] 0.075073 0.022186 0.014725 ..
|-> 2. 0x1438dbe00 (0x285da6200:0) [1x1024x80] -0.238281 1.119141 -0.505859 ..
|<- 1. 0x1438dc930 (0x285da6300:0) [1x1024x80] -0.135010 0.397217 -0.234375 ..
CCV_NNC_TRANSPOSE_FORWARD [336]: [1] -> [1] (0)
|-> 1. 0x1438dc9e0 (0x285da6300:0) [2x8x1024x80] -0.361084 0.128540 -0.017471 ..
|<- 1. 0x1438a48a0 (0x285da6200:0) [2x1024x8x80] -0.361084 0.128540 -0.017471 ..
CCV_NNC_GEMM_FORWARD [337]: [3] -> [1] (0)
|-> 1. 0x1438dca50 (0x285da6200:0) [2x1024x640] -0.361084 0.128540 -0.017471 ..
|-> 2. 0x1438c0360 (0x285d86140:0) [640x640] -0.028152 -0.005211 0.069153 ..
|-> 3. 0x1438c03d0 (0x285d86180:0) [640] 0.000637 0.002556 -0.041992 ..
|<- 1. 0x1438a4910 (0x285da6300:0) [2x1024x640] 0.014832 -0.139160 -0.882812 ..
CCV_NNC_ADD_FORWARD [338]: [2] -> [1] (0)
|-> 1. 0x1438a4910 (0x285da6300:0) [2x1024x640] 0.014832 -0.139160 -0.882812 ..
|-> 2. 0x1438d8f20 (0x285da61c0:0) [2x1024x640] 0.011711 0.003101 0.220581 ..
|<- 1. 0x1438a4910 (0x285da6300:0) [2x1024x640] 0.026550 -0.136108 -0.662109 ..
CCV_NNC_LAYER_NORM_FORWARD [339]: [3] -> [3] (0)
|-> 1. 0x1438a4910 (0x285da6300:0) [2x1024x640] 0.026550 -0.136108 -0.662109 ..
|-> 2. 0x1438c0440 (0x285d861c0:0) [1x1x640] 0.403564 0.457031 0.463867 ..
|-> 3. 0x1438c04b0 (0x285d86200:0) [1x1x640] 0.034668 -0.095215 -0.043091 ..
|<- 1. 0x1438a4980 (0x285da61c0:0) [2x1024x640] 0.045197 -0.222778 -0.630371 ..
|<- 2. 0x1438a49f0 (0x285da6380:0) [2x1024x1] 0.012642 ..
|<- 3. 0x1438a4a60 (0x285da6340:0) [2x1024x1] 1.876953 ..
CCV_NNC_GEMM_FORWARD [340]: [2] -> [1] (0)
|-> 1. 0x1438a4980 (0x285da61c0:0) [2x1024x640] 0.045197 -0.222778 -0.630371 ..
|-> 2. 0x1438c0520 (0x285d86240:0) [640x640] -0.068909 -0.063782 0.046234 ..
|<- 1. 0x1438a4ad0 (0x285da6200:0) [2x1024x640] -0.490234 -1.106445 -0.379150 ..
CCV_NNC_SCALAR_MUL_FORWARD [341]: [1] -> [1] (0)
|-> 1. 0x1438a4ad0 (0x285da6200:0) [2x1024x640] -0.490234 -1.106445 -0.379150 ..
|<- 1. 0x1438a4ad0 (0x285da6200:0) [2x1024x640] -0.054810 -0.123718 -0.042389 ..
CCV_NNC_TRANSPOSE_FORWARD [342]: [1] -> [1] (0)
|-> 1. 0x1438dcb30 (0x285da6200:0) [2x1024x8x80] -0.054810 -0.123718 -0.042389 ..
|<- 1. 0x1438a4c20 (0x285da6440:0) [2x8x1024x80] -0.054810 -0.123718 -0.042389 ..
CCV_NNC_GEMM_FORWARD [343]: [2] -> [1] (0)
Wait: (0, 24)
|-> 1. 0x1438a4c20 (0x285da6440:0) [2x8x1024x80] -0.054810 -0.123718 -0.042389 ..
|-> 2. 0x1438a4bb0 (0x285da6580:0) [2x8x133x80] 0.370605 -0.183228 -1.733398 ..
|<- 1. 0x1438a4c90 (0x285da65c0:0) [2x8x1024x133] 6.578125 -0.109436 -0.457764 ..
CCV_NNC_SOFTMAX_FORWARD [344]: [1] -> [1] (0)
|-> 1. 0x1438dcba0 (0x285da65c0:0) [16384x133] 6.578125 -0.109436 -0.457764 ..
|<- 1. 0x1438dcba0 (0x285da65c0:0) [16384x133] 0.646973 0.000806 0.000569 ..
CCV_NNC_GEMM_FORWARD [345]: [2] -> [1] (0)
Wait: (0, 25)
|-> 1. 0x1438dcc80 (0x285da65c0:0) [2x8x1024x133] 0.646973 0.000806 0.000569 ..
|-> 2. 0x1438a4d70 (0x285da6640:0) [2x8x133x80] 0.013397 0.017731 0.048828 ..
|<- 1. 0x1438a4de0 (0x285da6440:0) [2x8x1024x80] 0.079773 0.100769 -0.193115 ..
CCV_NNC_TRANSPOSE_FORWARD [346]: [1] -> [1] (0)
|-> 1. 0x1438dccf0 (0x285da6440:0) [2x8x1024x80] 0.079773 0.100769 -0.193115 ..
|<- 1. 0x1438a4e50 (0x285da61c0:0) [2x1024x8x80] 0.079773 0.100769 -0.193115 ..
CCV_NNC_GEMM_FORWARD [347]: [3] -> [1] (0)
|-> 1. 0x1438dcd60 (0x285da61c0:0) [2x1024x640] 0.079773 0.100769 -0.193115 ..
|-> 2. 0x1438c0670 (0x285d86300:0) [640x640] -0.001424 0.000917 -0.006500 ..
|-> 3. 0x1438c06e0 (0x285d86340:0) [640] -0.015472 0.013123 -0.070862 ..
|<- 1. 0x1438a4ec0 (0x285da6400:0) [2x1024x640] 0.012054 0.027100 -0.074219 ..
CCV_NNC_ADD_FORWARD [348]: [2] -> [1] (0)
|-> 1. 0x1438a4ec0 (0x285da6400:0) [2x1024x640] 0.012054 0.027100 -0.074219 ..
|-> 2. 0x1438a4910 (0x285da6300:0) [2x1024x640] 0.026550 -0.136108 -0.662109 ..
|<- 1. 0x1438a4ec0 (0x285da6400:0) [2x1024x640] 0.038605 -0.109009 -0.736328 ..
CCV_NNC_LAYER_NORM_FORWARD [349]: [3] -> [3] (0)
|-> 1. 0x1438a4ec0 (0x285da6400:0) [2x1024x640] 0.038605 -0.109009 -0.736328 ..
|-> 2. 0x1438c0750 (0x285d86380:0) [1x1x640] 0.307373 0.304199 0.304932 ..
|-> 3. 0x1438c07c0 (0x285d863c0:0) [1x1x640] 0.016418 -0.054840 0.052734 ..
|<- 1. 0x1438a4f30 (0x285da6680:0) [2x1024x640] 0.031403 -0.121338 -0.360352 ..
|<- 2. 0x1438a4fa0 (0x285da66c0:0) [2x1024x1] 0.011696 ..
|<- 3. 0x1438a5010 (0x285da6700:0) [2x1024x1] 1.811523 ..
Emit: (0, 26)
CCV_NNC_GEMM_FORWARD [350]: [3] -> [1] (0)
|-> 1. 0x1438a4f30 (0x285da6680:0) [2x1024x640] 0.031403 -0.121338 -0.360352 ..
|-> 2. 0x1438c0830 (0x285d86400:0) [2560x640] -0.052673 -0.019516 -0.017975 ..
|-> 3. 0x1438c08a0 (0x285d86440:0) [2560] -0.304199 0.028854 0.045166 ..
|<- 1. 0x1438a5080 (0x285da6740:0) [2x1024x2560] -0.736328 0.725098 -0.290527 ..
CCV_NNC_GELU_FORWARD [351]: [1] -> [1] (0)
|-> 1. 0x1438a5080 (0x285da6740:0) [2x1024x2560] -0.736328 0.725098 -0.290527 ..
|<- 1. 0x1438a5080 (0x285da6740:0) [2x1024x2560] -0.169922 0.555176 -0.112061 ..
CCV_NNC_GEMM_FORWARD [352]: [3] -> [1] (1)
Wait: (1, 26)
|-> 1. 0x1438a4f30 (0x285da6680:0) [2x1024x640] 0.031403 -0.121338 -0.360352 ..
|-> 2. 0x1438c0910 (0x285d86480:0) [2560x640] 0.075134 0.030365 0.000856 ..
|-> 3. 0x1438c0980 (0x285d864c0:0) [2560] -0.089661 0.030685 -0.067871 ..
|<- 1. 0x1438a50f0 (0x285da6780:0) [2x1024x2560] -0.932617 0.306396 -1.067383 ..
Emit: (1, 27)
CCV_NNC_MUL_FORWARD [353]: [2] -> [1] (0)
Wait: (0, 27)
|-> 1. 0x1438a50f0 (0x285da6780:0) [2x1024x2560] -0.932617 0.306396 -1.067383 ..
|-> 2. 0x1438a5080 (0x285da6740:0) [2x1024x2560] -0.169922 0.555176 -0.112061 ..
|<- 1. 0x1438a50f0 (0x285da6780:0) [2x1024x2560] 0.158447 0.170044 0.119629 ..
CCV_NNC_GEMM_FORWARD [354]: [3] -> [1] (0)
|-> 1. 0x1438a50f0 (0x285da6780:0) [2x1024x2560] 0.158447 0.170044 0.119629 ..
|-> 2. 0x1438c09f0 (0x285d86500:0) [640x2560] 0.039215 -0.043976 0.050629 ..
|-> 3. 0x1438c0a60 (0x285d86540:0) [640] -0.002060 0.010002 -0.000533 ..
|<- 1. 0x1438a5160 (0x285da6680:0) [2x1024x640] -0.767578 -0.584961 0.454346 ..
CCV_NNC_ADD_FORWARD [355]: [2] -> [1] (0)
|-> 1. 0x1438a5160 (0x285da6680:0) [2x1024x640] -0.767578 -0.584961 0.454346 ..
|-> 2. 0x1438a4ec0 (0x285da6400:0) [2x1024x640] 0.038605 -0.109009 -0.736328 ..
|<- 1. 0x1438a5160 (0x285da6680:0) [2x1024x640] -0.729004 -0.693848 -0.281982 ..
CCV_NNC_CONVOLUTION_FORWARD [356]: [3] -> [1] (0)
|-> 1. 0x1438dcdd0 (0x285da6680:0) [2x32x32x640] -0.729004 -0.693848 -0.281982 ..
|-> 2. 0x1438c0ad0 (0x285d86580:0) [640x640x1x1] 0.023605 ..
|-> 3. 0x1438c0b40 (0x285d865c0:0) [640] -0.031860 -0.006199 -0.021896 ..
|<- 1. 0x1438a51d0 (0x285da6480:0) [2x32x32x640] -1.019531 -0.302734 0.253906 ..
CCV_NNC_ADD_FORWARD [357]: [2] -> [1] (0)
|-> 1. 0x1438a51d0 (0x285da6480:0) [2x32x32x640] -1.019531 -0.302734 0.253906 ..
|-> 2. 0x1438a3b10 (0x285da62c0:0) [2x32x32x640] -1.627930 0.731445 0.444336 ..
|<- 1. 0x1438fd7b0 (0x285da5980:0) [2x32x32x640] -2.648438 0.428711 0.698242 ..
CCV_NNC_GROUP_NORM_FORWARD [358]: [3] -> [3] (0)
|-> 1. 0x1438fd7b0 (0x285da5980:0) [2x32x32x640] -2.648438 0.428711 0.698242 ..
|-> 2. 0x1438c0bb0 (0x285d86600:0) [1x1x1x640] 0.208496 0.307617 0.281494 ..
|-> 3. 0x1438c0c20 (0x285d86640:0) [1x1x1x640] -0.066956 -0.038818 -0.037933 ..
|<- 1. 0x1438a5240 (0x285da6480:0) [2x32x32x640] -0.544922 0.127075 0.183716 ..
|<- 2. 0x1438a52b0 (0x285da67c0:0) [2x1x1x32] -0.157104 0.148926 0.143311 ..
|<- 3. 0x1438a5320 (0x285da6800:0) [2x1x1x32] 0.920410 1.851562 1.354492 ..
CCV_NNC_SWISH_FORWARD [359]: [1] -> [1] (0)
|-> 1. 0x1438a5240 (0x285da6480:0) [2x32x32x640] -0.544922 0.127075 0.183716 ..
|<- 1. 0x1438a5240 (0x285da6480:0) [2x32x32x640] -0.199951 0.067566 0.100281 ..
CCV_NNC_CONVOLUTION_FORWARD [360]: [3] -> [1] (0)
|-> 1. 0x1438a5240 (0x285da6480:0) [2x32x32x640] -0.199951 0.067566 0.100281 ..
|-> 2. 0x1438c0d70 (0x285d86700:0) [640x640x3x3] -0.004822 -0.019791 -0.021057 ..
|-> 3. 0x1438c0de0 (0x285d86740:0) [640] 0.027176 0.012741 -0.054749 ..
|<- 1. 0x1438a5400 (0x285da62c0:0) [2x32x32x640] 1.653320 -0.888184 1.012695 ..
CCV_NNC_ADD_FORWARD [361]: [2] -> [1] (0)
Wait: (0, 28)
|-> 1. 0x1438a5400 (0x285da62c0:0) [2x32x32x640] 1.653320 -0.888184 1.012695 ..
|-> 2. 0x1438dce40 (0x285da6840:0) [2x1x1x640] 0.087891 -3.085938 0.536621 ..
|<- 1. 0x1438a5400 (0x285da62c0:0) [2x32x32x640] 1.741211 -3.974609 1.548828 ..
CCV_NNC_GROUP_NORM_FORWARD [362]: [3] -> [3] (0)
|-> 1. 0x1438a5400 (0x285da62c0:0) [2x32x32x640] 1.741211 -3.974609 1.548828 ..
|-> 2. 0x1438c0e50 (0x285d86780:0) [1x1x1x640] 0.551270 0.692871 0.686035 ..
|-> 3. 0x1438c0ec0 (0x285d867c0:0) [1x1x1x640] -0.276367 -0.065369 -0.252930 ..
|<- 1. 0x1438a5470 (0x285da6480:0) [2x32x32x640] 0.421875 -2.527344 0.504395 ..
|<- 2. 0x1438a54e0 (0x285da6880:0) [2x1x1x32] 0.239380 0.424561 0.679199 ..
|<- 3. 0x1438a5550 (0x285da68c0:0) [2x1x1x32] 0.843262 1.119141 1.365234 ..
CCV_NNC_SWISH_FORWARD [363]: [1] -> [1] (0)
|-> 1. 0x1438a5470 (0x285da6480:0) [2x32x32x640] 0.421875 -2.527344 0.504395 ..
|<- 1. 0x1438a5470 (0x285da6480:0) [2x32x32x640] 0.254883 -0.186890 0.314453 ..
CCV_NNC_CONVOLUTION_FORWARD [364]: [3] -> [1] (0)
|-> 1. 0x1438a5470 (0x285da6480:0) [2x32x32x640] 0.254883 -0.186890 0.314453 ..
|-> 2. 0x1438c0f30 (0x285d86800:0) [640x640x3x3] 0.033478 0.012352 -0.008667 ..
|-> 3. 0x1438c0fa0 (0x285d86840:0) [640] -0.000833 -0.002270 0.024445 ..
|<- 1. 0x1438a55c0 (0x285da6900:0) [2x32x32x640] -0.551270 -0.381836 0.529785 ..
CCV_NNC_ADD_FORWARD [365]: [2] -> [1] (0)
|-> 1. 0x1438fd7b0 (0x285da5980:0) [2x32x32x640] -2.648438 0.428711 0.698242 ..
|-> 2. 0x1438a55c0 (0x285da6900:0) [2x32x32x640] -0.551270 -0.381836 0.529785 ..
|<- 1. 0x1438a5630 (0x285da62c0:0) [2x32x32x640] -3.199219 0.046875 1.228516 ..
CCV_NNC_GROUP_NORM_FORWARD [366]: [3] -> [3] (0)
|-> 1. 0x1438a5630 (0x285da62c0:0) [2x32x32x640] -3.199219 0.046875 1.228516 ..
|-> 2. 0x1438c1010 (0x285d86880:0) [1x1x1x640] 0.291504 0.381348 0.403564 ..
|-> 3. 0x1438c1080 (0x285d868c0:0) [1x1x1x640] -0.014030 0.044952 0.045532 ..
|<- 1. 0x1438a56a0 (0x285da6900:0) [2x32x32x640] -0.937988 0.169678 0.691406 ..
|<- 2. 0x1438a5710 (0x285da5700:0) [2x1x1x32] -0.256836 0.051575 0.174438 ..
|<- 3. 0x1438a5780 (0x285da5740:0) [2x1x1x32] 1.077148 1.314453 1.291016 ..
CCV_NNC_CONVOLUTION_FORWARD [367]: [3] -> [1] (0)
|-> 1. 0x1438a56a0 (0x285da6900:0) [2x32x32x640] -0.937988 0.169678 0.691406 ..
|-> 2. 0x1438c10f0 (0x285d86900:0) [640x640x1x1] -0.072144 ..
|-> 3. 0x1438c1160 (0x285d86940:0) [640] 0.026093 -0.050903 -0.041107 ..
|<- 1. 0x1438a57f0 (0x285da6480:0) [2x32x32x640] -0.096313 0.765625 0.216919 ..
CCV_NNC_LAYER_NORM_FORWARD [368]: [3] -> [3] (0)
|-> 1. 0x1438dceb0 (0x285da6480:0) [2x1024x640] -0.096313 0.765625 0.216919 ..
|-> 2. 0x1438c11d0 (0x285d86980:0) [1x1x640] 0.543457 0.561523 0.567383 ..
|-> 3. 0x1438c1240 (0x285d869c0:0) [1x1x640] 0.066528 0.015854 0.001546 ..
|<- 1. 0x1438a5860 (0x285da6900:0) [2x1024x640] 0.049316 0.431396 0.142700 ..
|<- 2. 0x1438a58d0 (0x285da6940:0) [2x1024x1] -0.060944 ..
|<- 3. 0x1438a5940 (0x285da6980:0) [2x1024x1] 0.895508 ..
Emit: (0, 29)
CCV_NNC_GEMM_FORWARD [369]: [2] -> [1] (0)
|-> 1. 0x1438a5860 (0x285da6900:0) [2x1024x640] 0.049316 0.431396 0.142700 ..
|-> 2. 0x1438c12b0 (0x285d86a00:0) [640x640] 0.032898 0.015129 0.023300 ..
|<- 1. 0x1438a59b0 (0x285da69c0:0) [2x1024x640] 0.834961 -1.231445 1.248047 ..
CCV_NNC_SCALAR_MUL_FORWARD [370]: [1] -> [1] (0)
|-> 1. 0x1438a59b0 (0x285da69c0:0) [2x1024x640] 0.834961 -1.231445 1.248047 ..
|<- 1. 0x1438a59b0 (0x285da69c0:0) [2x1024x640] 0.093384 -0.137695 0.139526 ..
CCV_NNC_TRANSPOSE_FORWARD [371]: [1] -> [1] (0)
|-> 1. 0x1438dcf90 (0x285da69c0:0) [2x1024x8x80] 0.093384 -0.137695 0.139526 ..
|<- 1. 0x1438a5b00 (0x285da61c0:0) [2x8x1024x80] 0.093384 -0.137695 0.139526 ..
CCV_NNC_GEMM_FORWARD [372]: [2] -> [1] (1)
Wait: (1, 29)
|-> 1. 0x1438a5860 (0x285da6900:0) [2x1024x640] 0.049316 0.431396 0.142700 ..
|-> 2. 0x1438c1320 (0x285d86a40:0) [640x640] -0.020447 0.138306 -0.020874 ..
|<- 1. 0x1438a5a20 (0x285da63c0:0) [2x1024x640] 0.753906 -2.132812 -1.050781 ..
CCV_NNC_TRANSPOSE_FORWARD [373]: [1] -> [1] (1)
|-> 1. 0x1438dcf20 (0x285da63c0:0) [2x1024x8x80] 0.753906 -2.132812 -1.050781 ..
|<- 1. 0x1438a5a90 (0x285da6a00:0) [2x8x1024x80] 0.753906 -2.132812 -1.050781 ..
Emit: (1, 30)
CCV_NNC_GEMM_FORWARD [374]: [2] -> [1] (2)
Wait: (2, 29)
|-> 1. 0x1438a5860 (0x285da6900:0) [2x1024x640] 0.049316 0.431396 0.142700 ..
|-> 2. 0x1438c1390 (0x285d86a80:0) [640x640] 0.008591 -0.076965 0.013618 ..
|<- 1. 0x1438a5b70 (0x285da64c0:0) [2x1024x640] 0.223389 0.438232 -1.061523 ..
CCV_NNC_TRANSPOSE_FORWARD [375]: [1] -> [1] (2)
|-> 1. 0x1438dd0e0 (0x285da64c0:0) [2x1024x8x80] 0.223389 0.438232 -1.061523 ..
|<- 1. 0x1438a5c50 (0x285da6a80:0) [2x8x1024x80] 0.223389 0.438232 -1.061523 ..
Emit: (2, 31)
CCV_NNC_GEMM_FORWARD [376]: [2] -> [1] (0)
Wait: (0, 30)
|-> 1. 0x1438dd070 (0x285da61c0:0) [1x1024x80] 0.093384 -0.137695 0.139526 ..
|-> 2. 0x1438dd000 (0x285da6a00:0) [1x1024x80] 0.753906 -2.132812 -1.050781 ..
|<- 1. 0x1438a5be0 (0x285da6a40:0) [1x1024x1024] 3.708984 2.576172 2.929688 ..
CCV_NNC_SOFTMAX_FORWARD [377]: [1] -> [1] (0)
|-> 1. 0x1438dd150 (0x285da6a40:0) [1024x1024] 3.708984 2.576172 2.929688 ..
|<- 1. 0x1438dd150 (0x285da6a40:0) [1024x1024] 0.005600 0.001803 0.002567 ..
CCV_NNC_GEMM_FORWARD [378]: [2] -> [1] (0)
Wait: (0, 31)
|-> 1. 0x1438dd230 (0x285da6a40:0) [1x1024x1024] 0.005600 0.001803 0.002567 ..
|-> 2. 0x1438dd1c0 (0x285da6a80:0) [1x1024x80] 0.223389 0.438232 -1.061523 ..
|<- 1. 0x1438dfeb0 (0x285da6900:0) [1x1024x80] 0.265381 0.010628 -0.298096 ..
CCV_NNC_GEMM_FORWARD [379]: [2] -> [1] (0)
|-> 1. 0x1438dd350 (0x285da61c0:0) [1x1024x80] -0.102234 0.056061 -0.065491 ..
|-> 2. 0x1438dd2a0 (0x285da6a00:0) [1x1024x80] -0.977051 0.231567 -0.533691 ..
|<- 1. 0x1438a5cc0 (0x285da6a40:0) [1x1024x1024] 1.554688 1.155273 1.335938 ..
CCV_NNC_SOFTMAX_FORWARD [380]: [1] -> [1] (0)
|-> 1. 0x1438dd400 (0x285da6a40:0) [1024x1024] 1.554688 1.155273 1.335938 ..
|<- 1. 0x1438dd400 (0x285da6a40:0) [1024x1024] 0.003613 0.002422 0.002903 ..
CCV_NNC_GEMM_FORWARD [381]: [2] -> [1] (0)
|-> 1. 0x1438dd520 (0x285da6a40:0) [1x1024x1024] 0.003613 0.002422 0.002903 ..
|-> 2. 0x1438dd470 (0x285da6a80:0) [1x1024x80] -0.706543 0.345947 0.224121 ..
|<- 1. 0x1438dff20 (0x285da6900:0) [1x1024x80] -0.127441 0.074585 0.045319 ..
CCV_NNC_GEMM_FORWARD [382]: [2] -> [1] (0)
|-> 1. 0x1438dd640 (0x285da61c0:0) [1x1024x80] -0.036591 0.026779 -0.229492 ..
|-> 2. 0x1438dd590 (0x285da6a00:0) [1x1024x80] -2.191406 1.556641 0.182617 ..
|<- 1. 0x1438a5d30 (0x285da6a40:0) [1x1024x1024] 4.519531 3.941406 3.863281 ..
CCV_NNC_SOFTMAX_FORWARD [383]: [1] -> [1] (0)
|-> 1. 0x1438dd6f0 (0x285da6a40:0) [1024x1024] 4.519531 3.941406 3.863281 ..
|<- 1. 0x1438dd6f0 (0x285da6a40:0) [1024x1024] 0.004894 0.002745 0.002539 ..
CCV_NNC_GEMM_FORWARD [384]: [2] -> [1] (0)
|-> 1. 0x1438dd810 (0x285da6a40:0) [1x1024x1024] 0.004894 0.002745 0.002539 ..
|-> 2. 0x1438dd760 (0x285da6a80:0) [1x1024x80] 0.266602 0.398438 0.144409 ..
|<- 1. 0x1438dffd0 (0x285da6900:0) [1x1024x80] 0.065369 0.208862 0.217651 ..
CCV_NNC_GEMM_FORWARD [385]: [2] -> [1] (0)
|-> 1. 0x1438dd930 (0x285da61c0:0) [1x1024x80] 0.041473 -0.001205 -0.115967 ..
|-> 2. 0x1438dd880 (0x285da6a00:0) [1x1024x80] 1.298828 -0.989746 -0.521973 ..
|<- 1. 0x1438a5da0 (0x285da6a40:0) [1x1024x1024] 3.648438 1.824219 1.376953 ..
CCV_NNC_SOFTMAX_FORWARD [386]: [1] -> [1] (0)
|-> 1. 0x1438dd9e0 (0x285da6a40:0) [1024x1024] 3.648438 1.824219 1.376953 ..
|<- 1. 0x1438dd9e0 (0x285da6a40:0) [1024x1024] 0.024292 0.003918 0.002506 ..
CCV_NNC_GEMM_FORWARD [387]: [2] -> [1] (0)
|-> 1. 0x1438ddb00 (0x285da6a40:0) [1x1024x1024] 0.024292 0.003918 0.002506 ..
|-> 2. 0x1438dda50 (0x285da6a80:0) [1x1024x80] 0.635254 0.037811 0.057648 ..
|<- 1. 0x1438e0080 (0x285da6900:0) [1x1024x80] 0.120483 0.097351 0.052246 ..
CCV_NNC_GEMM_FORWARD [388]: [2] -> [1] (0)
|-> 1. 0x1438ddc20 (0x285da61c0:0) [1x1024x80] -0.129639 -0.012672 -0.145508 ..
|-> 2. 0x1438ddb70 (0x285da6a00:0) [1x1024x80] -2.470703 -1.506836 -2.023438 ..
|<- 1. 0x1438a5e10 (0x285da6a40:0) [1x1024x1024] 4.156250 1.927734 2.832031 ..
CCV_NNC_SOFTMAX_FORWARD [389]: [1] -> [1] (0)
|-> 1. 0x1438ddcd0 (0x285da6a40:0) [1024x1024] 4.156250 1.927734 2.832031 ..
|<- 1. 0x1438ddcd0 (0x285da6a40:0) [1024x1024] 0.020737 0.002234 0.005516 ..
CCV_NNC_GEMM_FORWARD [390]: [2] -> [1] (0)
|-> 1. 0x1438dddf0 (0x285da6a40:0) [1x1024x1024] 0.020737 0.002234 0.005516 ..
|-> 2. 0x1438ddd40 (0x285da6a80:0) [1x1024x80] 0.094360 0.555664 0.795898 ..
|<- 1. 0x1438e0130 (0x285da6900:0) [1x1024x80] 0.042542 0.075012 -0.051636 ..
CCV_NNC_GEMM_FORWARD [391]: [2] -> [1] (0)
|-> 1. 0x1438ddf10 (0x285da61c0:0) [1x1024x80] 0.051453 -0.110107 -0.027237 ..
|-> 2. 0x1438dde60 (0x285da6a00:0) [1x1024x80] -0.833008 1.696289 -1.751953 ..
|<- 1. 0x1438a5e80 (0x285da6a40:0) [1x1024x1024] 6.093750 4.109375 5.015625 ..
CCV_NNC_SOFTMAX_FORWARD [392]: [1] -> [1] (0)
|-> 1. 0x1438ddfc0 (0x285da6a40:0) [1024x1024] 6.093750 4.109375 5.015625 ..
|<- 1. 0x1438ddfc0 (0x285da6a40:0) [1024x1024] 0.035126 0.004829 0.011955 ..
CCV_NNC_GEMM_FORWARD [393]: [2] -> [1] (0)
|-> 1. 0x1438de0e0 (0x285da6a40:0) [1x1024x1024] 0.035126 0.004829 0.011955 ..
|-> 2. 0x1438de030 (0x285da6a80:0) [1x1024x80] 0.095581 -0.037384 -0.475098 ..
|<- 1. 0x1438e01e0 (0x285da6900:0) [1x1024x80] 0.146240 -0.027695 -0.245850 ..
CCV_NNC_GEMM_FORWARD [394]: [2] -> [1] (0)
|-> 1. 0x1438de200 (0x285da61c0:0) [1x1024x80] -0.039215 -0.091675 -0.002338 ..
|-> 2. 0x1438de150 (0x285da6a00:0) [1x1024x80] -1.115234 -1.572266 1.486328 ..
|<- 1. 0x1438a5ef0 (0x285da6a40:0) [1x1024x1024] 5.199219 2.582031 2.798828 ..
CCV_NNC_SOFTMAX_FORWARD [395]: [1] -> [1] (0)
|-> 1. 0x1438de2b0 (0x285da6a40:0) [1024x1024] 5.199219 2.582031 2.798828 ..
|<- 1. 0x1438de2b0 (0x285da6a40:0) [1024x1024] 0.042633 0.003113 0.003866 ..
CCV_NNC_GEMM_FORWARD [396]: [2] -> [1] (0)
|-> 1. 0x1438de3d0 (0x285da6a40:0) [1x1024x1024] 0.042633 0.003113 0.003866 ..
|-> 2. 0x1438de320 (0x285da6a80:0) [1x1024x80] 0.318115 0.350098 -0.006535 ..
|<- 1. 0x1438e0290 (0x285da6900:0) [1x1024x80] -0.154907 0.117798 0.120850 ..
CCV_NNC_GEMM_FORWARD [397]: [2] -> [1] (0)
|-> 1. 0x1438de4f0 (0x285da61c0:0) [1x1024x80] -0.017166 -0.081970 0.087646 ..
|-> 2. 0x1438de440 (0x285da6a00:0) [1x1024x80] 1.744141 -0.133789 1.097656 ..
|<- 1. 0x1438a5f60 (0x285da6a40:0) [1x1024x1024] 3.775391 2.425781 2.640625 ..
CCV_NNC_SOFTMAX_FORWARD [398]: [1] -> [1] (0)
|-> 1. 0x1438de5a0 (0x285da6a40:0) [1024x1024] 3.775391 2.425781 2.640625 ..
|<- 1. 0x1438de5a0 (0x285da6a40:0) [1024x1024] 0.020065 0.005203 0.006451 ..
CCV_NNC_GEMM_FORWARD [399]: [2] -> [1] (0)
|-> 1. 0x1438de6c0 (0x285da6a40:0) [1x1024x1024] 0.020065 0.005203 0.006451 ..
|-> 2. 0x1438de610 (0x285da6a80:0) [1x1024x80] -0.410400 0.046173 0.415527 ..
|<- 1. 0x1438e0340 (0x285da6900:0) [1x1024x80] -0.011215 0.166138 0.009338 ..
CCV_NNC_GEMM_FORWARD [400]: [2] -> [1] (0)
|-> 1. 0x1438de7e0 (0x285da61c0:0) [1x1024x80] 0.087097 -0.124390 0.137573 ..
|-> 2. 0x1438de730 (0x285da6a00:0) [1x1024x80] 0.666016 -1.976562 -1.167969 ..
|<- 1. 0x1438a5fd0 (0x285da6a40:0) [1x1024x1024] 3.236328 2.248047 2.550781 ..
CCV_NNC_SOFTMAX_FORWARD [401]: [1] -> [1] (0)
|-> 1. 0x1438de890 (0x285da6a40:0) [1024x1024] 3.236328 2.248047 2.550781 ..
|<- 1. 0x1438de890 (0x285da6a40:0) [1024x1024] 0.005947 0.002214 0.002996 ..
CCV_NNC_GEMM_FORWARD [402]: [2] -> [1] (0)
|-> 1. 0x1438de9b0 (0x285da6a40:0) [1x1024x1024] 0.005947 0.002214 0.002996 ..
|-> 2. 0x1438de900 (0x285da6a80:0) [1x1024x80] 0.152222 0.447998 -0.931152 ..
|<- 1. 0x1438e03f0 (0x285da6900:0) [1x1024x80] 0.197144 0.156372 -0.209839 ..
CCV_NNC_GEMM_FORWARD [403]: [2] -> [1] (0)
|-> 1. 0x1438dead0 (0x285da61c0:0) [1x1024x80] -0.092834 0.040253 -0.051239 ..
|-> 2. 0x1438dea20 (0x285da6a00:0) [1x1024x80] -0.705566 0.117432 -0.708008 ..
|<- 1. 0x1438a6040 (0x285da6a40:0) [1x1024x1024] 1.405273 1.069336 1.289062 ..
CCV_NNC_SOFTMAX_FORWARD [404]: [1] -> [1] (0)
|-> 1. 0x1438deb80 (0x285da6a40:0) [1024x1024] 1.405273 1.069336 1.289062 ..
|<- 1. 0x1438deb80 (0x285da6a40:0) [1024x1024] 0.002813 0.002010 0.002504 ..
CCV_NNC_GEMM_FORWARD [405]: [2] -> [1] (0)
|-> 1. 0x1438deca0 (0x285da6a40:0) [1x1024x1024] 0.002813 0.002010 0.002504 ..
|-> 2. 0x1438debf0 (0x285da6a80:0) [1x1024x80] -0.702148 0.228027 0.257080 ..
|<- 1. 0x1438e04a0 (0x285da6900:0) [1x1024x80] -0.105469 0.167114 0.158203 ..
CCV_NNC_GEMM_FORWARD [406]: [2] -> [1] (0)
|-> 1. 0x1438dedc0 (0x285da61c0:0) [1x1024x80] -0.032654 -0.016022 -0.220581 ..
|-> 2. 0x1438ded10 (0x285da6a00:0) [1x1024x80] -2.205078 1.277344 0.299072 ..
|<- 1. 0x1438a60b0 (0x285da6a40:0) [1x1024x1024] 4.171875 3.775391 3.832031 ..
CCV_NNC_SOFTMAX_FORWARD [407]: [1] -> [1] (0)
|-> 1. 0x1438dee70 (0x285da6a40:0) [1024x1024] 4.171875 3.775391 3.832031 ..
|<- 1. 0x1438dee70 (0x285da6a40:0) [1024x1024] 0.004757 0.003199 0.003386 ..
CCV_NNC_GEMM_FORWARD [408]: [2] -> [1] (0)
|-> 1. 0x1438def90 (0x285da6a40:0) [1x1024x1024] 0.004757 0.003199 0.003386 ..
|-> 2. 0x1438deee0 (0x285da6a80:0) [1x1024x80] 0.172607 0.293945 0.113037 ..
|<- 1. 0x1438e0550 (0x285da6900:0) [1x1024x80] -0.015930 0.073975 0.182617 ..
CCV_NNC_GEMM_FORWARD [409]: [2] -> [1] (0)
|-> 1. 0x1438df0b0 (0x285da61c0:0) [1x1024x80] 0.027542 0.017517 -0.111816 ..
|-> 2. 0x1438df000 (0x285da6a00:0) [1x1024x80] 1.426758 -0.935059 -0.490967 ..
|<- 1. 0x1438a6120 (0x285da6a40:0) [1x1024x1024] 3.460938 1.697266 1.443359 ..
CCV_NNC_SOFTMAX_FORWARD [410]: [1] -> [1] (0)
|-> 1. 0x1438df160 (0x285da6a40:0) [1024x1024] 3.460938 1.697266 1.443359 ..
|<- 1. 0x1438df160 (0x285da6a40:0) [1024x1024] 0.018478 0.003166 0.002457 ..
CCV_NNC_GEMM_FORWARD [411]: [2] -> [1] (0)
|-> 1. 0x1438df280 (0x285da6a40:0) [1x1024x1024] 0.018478 0.003166 0.002457 ..
|-> 2. 0x1438df1d0 (0x285da6a80:0) [1x1024x80] 0.607910 0.047882 0.110474 ..
|<- 1. 0x1438e0600 (0x285da6900:0) [1x1024x80] 0.119263 0.173218 0.064758 ..
CCV_NNC_GEMM_FORWARD [412]: [2] -> [1] (0)
|-> 1. 0x1438df3a0 (0x285da61c0:0) [1x1024x80] -0.106445 -0.013931 -0.134888 ..
|-> 2. 0x1438df2f0 (0x285da6a00:0) [1x1024x80] -2.423828 -1.475586 -2.005859 ..
|<- 1. 0x1438a6190 (0x285da6a40:0) [1x1024x1024] 4.218750 2.298828 3.312500 ..
CCV_NNC_SOFTMAX_FORWARD [413]: [1] -> [1] (0)
|-> 1. 0x1438df450 (0x285da6a40:0) [1024x1024] 4.218750 2.298828 3.312500 ..
|<- 1. 0x1438df450 (0x285da6a40:0) [1024x1024] 0.017838 0.002615 0.007206 ..
CCV_NNC_GEMM_FORWARD [414]: [2] -> [1] (0)
|-> 1. 0x1438df570 (0x285da6a40:0) [1x1024x1024] 0.017838 0.002615 0.007206 ..
|-> 2. 0x1438df4c0 (0x285da6a80:0) [1x1024x80] 0.096375 0.453369 0.812500 ..
|<- 1. 0x1438e06b0 (0x285da6900:0) [1x1024x80] 0.111572 0.018936 0.000479 ..
CCV_NNC_GEMM_FORWARD [415]: [2] -> [1] (0)
|-> 1. 0x1438df690 (0x285da61c0:0) [1x1024x80] 0.038483 -0.093567 -0.032227 ..
|-> 2. 0x1438df5e0 (0x285da6a00:0) [1x1024x80] -0.815918 1.705078 -1.846680 ..
|<- 1. 0x1438a6200 (0x285da6a40:0) [1x1024x1024] 5.933594 4.253906 4.980469 ..
CCV_NNC_SOFTMAX_FORWARD [416]: [1] -> [1] (0)
|-> 1. 0x1438df740 (0x285da6a40:0) [1024x1024] 5.933594 4.253906 4.980469 ..
|<- 1. 0x1438df740 (0x285da6a40:0) [1024x1024] 0.033173 0.006184 0.012787 ..
CCV_NNC_GEMM_FORWARD [417]: [2] -> [1] (0)
|-> 1. 0x1438df860 (0x285da6a40:0) [1x1024x1024] 0.033173 0.006184 0.012787 ..
|-> 2. 0x1438df7b0 (0x285da6a80:0) [1x1024x80] -0.008102 0.009789 -0.357422 ..
|<- 1. 0x1438e0760 (0x285da6900:0) [1x1024x80] 0.023224 -0.078186 -0.232178 ..
CCV_NNC_GEMM_FORWARD [418]: [2] -> [1] (0)
|-> 1. 0x1438df980 (0x285da61c0:0) [1x1024x80] -0.027267 -0.082520 0.016251 ..
|-> 2. 0x1438df8d0 (0x285da6a00:0) [1x1024x80] -0.986328 -1.624023 1.705078 ..
|<- 1. 0x1438a6270 (0x285da6a40:0) [1x1024x1024] 4.851562 2.693359 2.812500 ..
CCV_NNC_SOFTMAX_FORWARD [419]: [1] -> [1] (0)
|-> 1. 0x1438dfa30 (0x285da6a40:0) [1024x1024] 4.851562 2.693359 2.812500 ..
|<- 1. 0x1438dfa30 (0x285da6a40:0) [1024x1024] 0.029175 0.003372 0.003798 ..
CCV_NNC_GEMM_FORWARD [420]: [2] -> [1] (0)
|-> 1. 0x1438dfb50 (0x285da6a40:0) [1x1024x1024] 0.029175 0.003372 0.003798 ..
|-> 2. 0x1438dfaa0 (0x285da6a80:0) [1x1024x80] 0.325195 0.280273 0.072632 ..
|<- 1. 0x1438e0810 (0x285da6900:0) [1x1024x80] -0.245361 0.074158 0.215332 ..
CCV_NNC_GEMM_FORWARD [421]: [2] -> [1] (0)
|-> 1. 0x1438dfc70 (0x285da61c0:0) [1x1024x80] -0.017166 -0.070496 0.091309 ..
|-> 2. 0x1438dfbc0 (0x285da6a00:0) [1x1024x80] 1.819336 -0.112854 1.263672 ..
|<- 1. 0x1438a62e0 (0x285da6a40:0) [1x1024x1024] 3.550781 2.378906 2.474609 ..
CCV_NNC_SOFTMAX_FORWARD [422]: [1] -> [1] (0)
|-> 1. 0x1438dfd20 (0x285da6a40:0) [1024x1024] 3.550781 2.378906 2.474609 ..
|<- 1. 0x1438dfd20 (0x285da6a40:0) [1024x1024] 0.017593 0.005447 0.005997 ..
CCV_NNC_GEMM_FORWARD [423]: [2] -> [1] (0)
|-> 1. 0x1438dfe40 (0x285da6a40:0) [1x1024x1024] 0.017593 0.005447 0.005997 ..
|-> 2. 0x1438dfd90 (0x285da6a80:0) [1x1024x80] -0.548340 0.207520 0.329590 ..
|<- 1. 0x1438e08c0 (0x285da6900:0) [1x1024x80] -0.087341 0.180542 0.006233 ..
CCV_NNC_TRANSPOSE_FORWARD [424]: [1] -> [1] (0)
|-> 1. 0x1438e0970 (0x285da6900:0) [2x8x1024x80] 0.265381 0.010628 -0.298096 ..
|<- 1. 0x1438a63c0 (0x285da6a80:0) [2x1024x8x80] 0.265381 0.010628 -0.298096 ..
CCV_NNC_GEMM_FORWARD [425]: [3] -> [1] (0)
|-> 1. 0x1438e09e0 (0x285da6a80:0) [2x1024x640] 0.265381 0.010628 -0.298096 ..
|-> 2. 0x1438c1400 (0x285d86ac0:0) [640x640] 0.014511 -0.044617 -0.003338 ..
|-> 3. 0x1438c1470 (0x285d86b00:0) [640] 0.025314 -0.092285 0.005138 ..
|<- 1. 0x1438a6430 (0x285da6900:0) [2x1024x640] 0.065735 -0.153809 0.075806 ..
CCV_NNC_ADD_FORWARD [426]: [2] -> [1] (0)
|-> 1. 0x1438a6430 (0x285da6900:0) [2x1024x640] 0.065735 -0.153809 0.075806 ..
|-> 2. 0x1438dceb0 (0x285da6480:0) [2x1024x640] -0.096313 0.765625 0.216919 ..
|<- 1. 0x1438a6430 (0x285da6900:0) [2x1024x640] -0.030579 0.611816 0.292725 ..
CCV_NNC_LAYER_NORM_FORWARD [427]: [3] -> [3] (0)
|-> 1. 0x1438a6430 (0x285da6900:0) [2x1024x640] -0.030579 0.611816 0.292725 ..
|-> 2. 0x1438c14e0 (0x285d86b40:0) [1x1x640] 0.397217 0.405762 0.360596 ..
|-> 3. 0x1438c1550 (0x285d86b80:0) [1x1x640] 0.145630 0.032623 -0.199097 ..
|<- 1. 0x1438a64a0 (0x285da6480:0) [2x1024x640] 0.158325 0.280273 -0.082581 ..
|<- 2. 0x1438a6510 (0x285da6ac0:0) [2x1024x1] -0.065979 ..
|<- 3. 0x1438a6580 (0x285da6b00:0) [2x1024x1] 0.900879 ..
CCV_NNC_GEMM_FORWARD [428]: [2] -> [1] (0)
|-> 1. 0x1438a64a0 (0x285da6480:0) [2x1024x640] 0.158325 0.280273 -0.082581 ..
|-> 2. 0x1438c15c0 (0x285d86bc0:0) [640x640] -0.017227 0.001777 -0.034637 ..
|<- 1. 0x1438a65f0 (0x285da6a00:0) [2x1024x640] -0.191772 0.359131 -0.877441 ..
CCV_NNC_SCALAR_MUL_FORWARD [429]: [1] -> [1] (0)
|-> 1. 0x1438a65f0 (0x285da6a00:0) [2x1024x640] -0.191772 0.359131 -0.877441 ..
|<- 1. 0x1438a65f0 (0x285da6a00:0) [2x1024x640] -0.021439 0.040161 -0.098083 ..
CCV_NNC_TRANSPOSE_FORWARD [430]: [1] -> [1] (0)
|-> 1. 0x1438e0ac0 (0x285da6a00:0) [2x1024x8x80] -0.021439 0.040161 -0.098083 ..
|<- 1. 0x1438a6740 (0x285da6a80:0) [2x8x1024x80] -0.021439 0.040161 -0.098083 ..
CCV_NNC_GEMM_FORWARD [431]: [2] -> [1] (0)
Wait: (0, 32)
|-> 1. 0x1438a6740 (0x285da6a80:0) [2x8x1024x80] -0.021439 0.040161 -0.098083 ..
|-> 2. 0x1438a66d0 (0x285da6b80:0) [2x8x133x80] -0.381836 -0.479736 0.379883 ..
|<- 1. 0x1438a67b0 (0x285da6bc0:0) [2x8x1024x133] 7.480469 0.335205 1.155273 ..
CCV_NNC_SOFTMAX_FORWARD [432]: [1] -> [1] (0)
|-> 1. 0x1438e0b30 (0x285da6bc0:0) [16384x133] 7.480469 0.335205 1.155273 ..
|<- 1. 0x1438e0b30 (0x285da6bc0:0) [16384x133] 0.817871 0.000645 0.001464 ..
CCV_NNC_GEMM_FORWARD [433]: [2] -> [1] (0)
Wait: (0, 33)
|-> 1. 0x1438e0c10 (0x285da6bc0:0) [2x8x1024x133] 0.817871 0.000645 0.001464 ..
|-> 2. 0x1438a6890 (0x285da6c40:0) [2x8x133x80] 0.031586 0.014740 -0.047302 ..
|<- 1. 0x1438a6900 (0x285da6a80:0) [2x8x1024x80] 0.018341 0.024033 -0.024689 ..
CCV_NNC_TRANSPOSE_FORWARD [434]: [1] -> [1] (0)
|-> 1. 0x1438e0c80 (0x285da6a80:0) [2x8x1024x80] 0.018341 0.024033 -0.024689 ..
|<- 1. 0x1438a6970 (0x285da6480:0) [2x1024x8x80] 0.018341 0.024033 -0.024689 ..
CCV_NNC_GEMM_FORWARD [435]: [3] -> [1] (0)
|-> 1. 0x1438e0cf0 (0x285da6480:0) [2x1024x640] 0.018341 0.024033 -0.024689 ..
|-> 2. 0x1438c1710 (0x285d86c80:0) [640x640] 0.006489 0.004543 -0.020630 ..
|-> 3. 0x1438c1780 (0x285d86cc0:0) [640] -0.030243 -0.027390 -0.015312 ..
|<- 1. 0x1438a69e0 (0x285da69c0:0) [2x1024x640] 0.121094 -0.053955 -0.106079 ..
CCV_NNC_ADD_FORWARD [436]: [2] -> [1] (0)
|-> 1. 0x1438a69e0 (0x285da69c0:0) [2x1024x640] 0.121094 -0.053955 -0.106079 ..
|-> 2. 0x1438a6430 (0x285da6900:0) [2x1024x640] -0.030579 0.611816 0.292725 ..
|<- 1. 0x1438a69e0 (0x285da69c0:0) [2x1024x640] 0.090515 0.557617 0.186646 ..
CCV_NNC_LAYER_NORM_FORWARD [437]: [3] -> [3] (0)
|-> 1. 0x1438a69e0 (0x285da69c0:0) [2x1024x640] 0.090515 0.557617 0.186646 ..
|-> 2. 0x1438c17f0 (0x285d86d00:0) [1x1x640] 0.336426 0.341064 0.359131 ..
|-> 3. 0x1438c1860 (0x285d86d40:0) [1x1x640] 0.066956 0.044464 -0.004032 ..
|<- 1. 0x1438a6a50 (0x285da6c80:0) [2x1024x640] 0.118164 0.241577 0.082092 ..
|<- 2. 0x1438a6ac0 (0x285da6cc0:0) [2x1024x1] -0.076477 ..
|<- 3. 0x1438a6b30 (0x285da6d00:0) [2x1024x1] 0.911621 ..
Emit: (0, 34)
CCV_NNC_GEMM_FORWARD [438]: [3] -> [1] (0)
|-> 1. 0x1438a6a50 (0x285da6c80:0) [2x1024x640] 0.118164 0.241577 0.082092 ..
|-> 2. 0x1438c18d0 (0x285d86d80:0) [2560x640] 0.056854 0.001586 -0.018921 ..
|-> 3. 0x1438c1940 (0x285d86dc0:0) [2560] 0.042633 0.058716 0.007183 ..
|<- 1. 0x1438a6ba0 (0x285da6740:0) [2x1024x2560] -0.250000 -0.606934 -0.143677 ..
CCV_NNC_GELU_FORWARD [439]: [1] -> [1] (0)
|-> 1. 0x1438a6ba0 (0x285da6740:0) [2x1024x2560] -0.250000 -0.606934 -0.143677 ..
|<- 1. 0x1438a6ba0 (0x285da6740:0) [2x1024x2560] -0.100342 -0.165039 -0.063660 ..
CCV_NNC_GEMM_FORWARD [440]: [3] -> [1] (1)
Wait: (1, 34)
|-> 1. 0x1438a6a50 (0x285da6c80:0) [2x1024x640] 0.118164 0.241577 0.082092 ..
|-> 2. 0x1438c19b0 (0x285d86e00:0) [2560x640] -0.040924 -0.039307 0.095337 ..
|-> 3. 0x1438c1a20 (0x285d86e40:0) [2560] -0.001872 0.017807 0.035004 ..
|<- 1. 0x1438a6c10 (0x285da6780:0) [2x1024x2560] -0.643555 0.389648 0.595215 ..
Emit: (1, 35)
CCV_NNC_MUL_FORWARD [441]: [2] -> [1] (0)
Wait: (0, 35)
|-> 1. 0x1438a6c10 (0x285da6780:0) [2x1024x2560] -0.643555 0.389648 0.595215 ..
|-> 2. 0x1438a6ba0 (0x285da6740:0) [2x1024x2560] -0.100342 -0.165039 -0.063660 ..
|<- 1. 0x1438a6c10 (0x285da6780:0) [2x1024x2560] 0.064575 -0.064331 -0.037903 ..
CCV_NNC_GEMM_FORWARD [442]: [3] -> [1] (0)
|-> 1. 0x1438a6c10 (0x285da6780:0) [2x1024x2560] 0.064575 -0.064331 -0.037903 ..
|-> 2. 0x1438c1a90 (0x285d86e80:0) [640x2560] 0.041840 0.020172 0.001719 ..
|-> 3. 0x1438c1b00 (0x285d86ec0:0) [640] -0.002460 0.025970 0.007858 ..
|<- 1. 0x1438a6c80 (0x285da61c0:0) [2x1024x640] 0.011269 -1.174805 -1.065430 ..
CCV_NNC_ADD_FORWARD [443]: [2] -> [1] (0)
|-> 1. 0x1438a6c80 (0x285da61c0:0) [2x1024x640] 0.011269 -1.174805 -1.065430 ..
|-> 2. 0x1438a69e0 (0x285da69c0:0) [2x1024x640] 0.090515 0.557617 0.186646 ..
|<- 1. 0x1438a6c80 (0x285da61c0:0) [2x1024x640] 0.101807 -0.617188 -0.878906 ..
CCV_NNC_CONVOLUTION_FORWARD [444]: [3] -> [1] (0)
|-> 1. 0x1438e0d60 (0x285da61c0:0) [2x32x32x640] 0.101807 -0.617188 -0.878906 ..
|-> 2. 0x1438c1b70 (0x285d86f00:0) [640x640x1x1] -0.002705 ..
|-> 3. 0x1438c1be0 (0x285d86f40:0) [640] -0.061615 -0.015152 0.004658 ..
|<- 1. 0x1438a6cf0 (0x285da69c0:0) [2x32x32x640] 1.405273 0.543457 -0.504883 ..
CCV_NNC_ADD_FORWARD [445]: [2] -> [1] (0)
|-> 1. 0x1438a6cf0 (0x285da69c0:0) [2x32x32x640] 1.405273 0.543457 -0.504883 ..
|-> 2. 0x1438a5630 (0x285da62c0:0) [2x32x32x640] -3.199219 0.046875 1.228516 ..
|<- 1. 0x1438f96c0 (0x285d8a540:0) [2x32x32x640] -1.793945 0.590332 0.723633 ..
CCV_NNC_CONVOLUTION_FORWARD [446]: [3] -> [1] (0)
|-> 1. 0x1438f96c0 (0x285d8a540:0) [2x32x32x640] -1.793945 0.590332 0.723633 ..
|-> 2. 0x1438c1c50 (0x285d86f80:0) [640x640x3x3] 0.002350 -0.003546 -0.003578 ..
|-> 3. 0x1438c1cc0 (0x285d86fc0:0) [640] 0.015541 -0.005711 0.016861 ..
|<- 1. 0x1438f55d0 (0x285d8f6c0:0) [2x16x16x640] 0.511230 1.206055 0.435791 ..
Emit: (0, 37)
CCV_NNC_GROUP_NORM_FORWARD [447]: [3] -> [3] (0)
|-> 1. 0x1438f55d0 (0x285d8f6c0:0) [2x16x16x640] 0.511230 1.206055 0.435791 ..
|-> 2. 0x1438c1d30 (0x285d87000:0) [1x1x1x640] 0.273926 0.466309 0.314697 ..
|-> 3. 0x1438c1da0 (0x285d87040:0) [1x1x1x640] -0.018585 -0.111938 -0.034729 ..
|<- 1. 0x1438a6d60 (0x285da6d40:0) [2x16x16x640] 0.130005 0.520996 0.108154 ..
|<- 2. 0x1438a6dd0 (0x285da6800:0) [2x1x1x32] 0.048676 0.003143 0.062347 ..
|<- 3. 0x1438a6e40 (0x285da67c0:0) [2x1x1x32] 1.172852 1.277344 1.097656 ..
CCV_NNC_SWISH_FORWARD [448]: [1] -> [1] (0)
|-> 1. 0x1438a6d60 (0x285da6d40:0) [2x16x16x640] 0.130005 0.520996 0.108154 ..
|<- 1. 0x1438a6d60 (0x285da6d40:0) [2x16x16x640] 0.069214 0.326904 0.057007 ..
CCV_NNC_CONVOLUTION_FORWARD [449]: [3] -> [1] (0)
|-> 1. 0x1438a6d60 (0x285da6d40:0) [2x16x16x640] 0.069214 0.326904 0.057007 ..
|-> 2. 0x1438c1ef0 (0x285d87100:0) [1280x640x3x3] -0.047272 0.032166 0.071716 ..
|-> 3. 0x1438c1f60 (0x285d87140:0) [1280] 0.016006 0.001427 0.001047 ..
|<- 1. 0x1438a6f20 (0x285da6dc0:0) [2x16x16x1280] 0.482910 0.290771 -0.923828 ..
CCV_NNC_ADD_FORWARD [450]: [2] -> [1] (0)
Wait: (0, 36)
|-> 1. 0x1438a6f20 (0x285da6dc0:0) [2x16x16x1280] 0.482910 0.290771 -0.923828 ..
|-> 2. 0x1438e0dd0 (0x285da6d80:0) [2x1x1x1280] 0.093994 0.277832 0.315918 ..
|<- 1. 0x1438a6f20 (0x285da6dc0:0) [2x16x16x1280] 0.577148 0.568359 -0.607910 ..
CCV_NNC_GROUP_NORM_FORWARD [451]: [3] -> [3] (0)
|-> 1. 0x1438a6f20 (0x285da6dc0:0) [2x16x16x1280] 0.577148 0.568359 -0.607910 ..
|-> 2. 0x1438c1fd0 (0x285d87180:0) [1x1x1x1280] 0.351807 0.352783 0.389404 ..
|-> 3. 0x1438c2040 (0x285d871c0:0) [1x1x1x1280] -0.060883 -0.064331 -0.050873 ..
|<- 1. 0x1438a6f90 (0x285da6e00:0) [2x16x16x1280] 0.344238 0.337646 -0.254150 ..
|<- 2. 0x1438a7000 (0x285da6e40:0) [2x1x1x32] -0.238403 -0.539062 -0.552734 ..
|<- 3. 0x1438a7070 (0x285da6e80:0) [2x1x1x32] 1.412109 0.240601 0.430664 ..
CCV_NNC_SWISH_FORWARD [452]: [1] -> [1] (0)
|-> 1. 0x1438a6f90 (0x285da6e00:0) [2x16x16x1280] 0.344238 0.337646 -0.254150 ..
|<- 1. 0x1438a6f90 (0x285da6e00:0) [2x16x16x1280] 0.201416 0.197021 -0.111023 ..
CCV_NNC_CONVOLUTION_FORWARD [453]: [3] -> [1] (0)
|-> 1. 0x1438a6f90 (0x285da6e00:0) [2x16x16x1280] 0.201416 0.197021 -0.111023 ..
|-> 2. 0x1438c20b0 (0x285d87200:0) [1280x1280x3x3] 0.057434 -0.026169 -0.027893 ..
|-> 3. 0x1438c2120 (0x285d87240:0) [1280] 0.034912 0.017990 0.040131 ..
|<- 1. 0x1438a70e0 (0x285da6dc0:0) [2x16x16x1280] -0.461914 -0.300781 -1.104492 ..
CCV_NNC_CONVOLUTION_FORWARD [454]: [3] -> [1] (1)
Wait: (1, 37)
|-> 1. 0x1438f55d0 (0x285d8f6c0:0) [2x16x16x640] 0.511230 1.206055 0.435791 ..
|-> 2. 0x1438c2190 (0x285d87280:0) [1280x640x1x1] 0.004993 ..
|-> 3. 0x1438c2200 (0x285d872c0:0) [1280] 0.042450 0.028534 0.049713 ..
|<- 1. 0x1438a7150 (0x285da6f00:0) [2x16x16x1280] 0.120300 0.447754 0.978516 ..
Emit: (1, 38)
CCV_NNC_ADD_FORWARD [455]: [2] -> [1] (0)
Wait: (0, 38)
|-> 1. 0x1438a7150 (0x285da6f00:0) [2x16x16x1280] 0.120300 0.447754 0.978516 ..
|-> 2. 0x1438a70e0 (0x285da6dc0:0) [2x16x16x1280] -0.461914 -0.300781 -1.104492 ..
|<- 1. 0x1438a7150 (0x285da6f00:0) [2x16x16x1280] -0.341553 0.146973 -0.125977 ..
CCV_NNC_GROUP_NORM_FORWARD [456]: [3] -> [3] (0)
|-> 1. 0x1438a7150 (0x285da6f00:0) [2x16x16x1280] -0.341553 0.146973 -0.125977 ..
|-> 2. 0x1438c2270 (0x285d87300:0) [1x1x1x1280] 0.224976 0.224609 0.224731 ..
|-> 3. 0x1438c22e0 (0x285d87340:0) [1x1x1x1280] -0.013771 0.003616 0.001595 ..
|<- 1. 0x1438a71c0 (0x285da6e00:0) [2x16x16x1280] -0.055328 0.083130 0.013512 ..
|<- 2. 0x1438a7230 (0x285da6800:0) [2x1x1x32] -0.174072 -0.127808 -0.152222 ..
|<- 3. 0x1438a72a0 (0x285da67c0:0) [2x1x1x32] 1.102539 1.019531 0.989746 ..
CCV_NNC_CONVOLUTION_FORWARD [457]: [3] -> [1] (0)
|-> 1. 0x1438a71c0 (0x285da6e00:0) [2x16x16x1280] -0.055328 0.083130 0.013512 ..
|-> 2. 0x1438c2350 (0x285d87380:0) [1280x1280x1x1] -0.000048 ..
|-> 3. 0x1438c23c0 (0x285d873c0:0) [1280] -0.010078 -0.024460 0.010605 ..
|<- 1. 0x1438a7310 (0x285da6dc0:0) [2x16x16x1280] 0.916016 0.061157 0.760742 ..
CCV_NNC_LAYER_NORM_FORWARD [458]: [3] -> [3] (0)
|-> 1. 0x1438e0e40 (0x285da6dc0:0) [2x256x1280] 0.916016 0.061157 0.760742 ..
|-> 2. 0x1438c2430 (0x285d87400:0) [1x1x1280] 0.296143 0.296631 0.322021 ..
|-> 3. 0x1438c24a0 (0x285d87440:0) [1x1x1280] 0.009285 -0.026138 0.003679 ..
|<- 1. 0x1438a7380 (0x285da6e00:0) [2x256x1280] 0.315430 -0.002338 0.280762 ..
|<- 2. 0x1438a73f0 (0x285da6f40:0) [2x256x1] -0.010788 ..
|<- 3. 0x1438a7460 (0x285da6f80:0) [2x256x1] 1.115234 ..
Emit: (0, 39)
CCV_NNC_GEMM_FORWARD [459]: [2] -> [1] (0)
|-> 1. 0x1438a7380 (0x285da6e00:0) [2x256x1280] 0.315430 -0.002338 0.280762 ..
|-> 2. 0x1438c2510 (0x285d87480:0) [1280x1280] -0.022614 -0.011375 0.041016 ..
|<- 1. 0x1438a74d0 (0x285da6fc0:0) [2x256x1280] 0.355957 -0.752930 -0.484131 ..
CCV_NNC_SCALAR_MUL_FORWARD [460]: [1] -> [1] (0)
|-> 1. 0x1438a74d0 (0x285da6fc0:0) [2x256x1280] 0.355957 -0.752930 -0.484131 ..
|<- 1. 0x1438a74d0 (0x285da6fc0:0) [2x256x1280] 0.028137 -0.059509 -0.038269 ..
CCV_NNC_TRANSPOSE_FORWARD [461]: [1] -> [1] (0)
|-> 1. 0x1438e0f20 (0x285da6fc0:0) [2x256x8x160] 0.028137 -0.059509 -0.038269 ..
|<- 1. 0x1438a7620 (0x285da7080:0) [2x8x256x160] 0.028137 -0.059509 -0.038269 ..
CCV_NNC_GEMM_FORWARD [462]: [2] -> [1] (1)
Wait: (1, 39)
|-> 1. 0x1438a7380 (0x285da6e00:0) [2x256x1280] 0.315430 -0.002338 0.280762 ..
|-> 2. 0x1438c2580 (0x285d874c0:0) [1280x1280] 0.106079 -0.006134 -0.057587 ..
|<- 1. 0x1438a7540 (0x285da7000:0) [2x256x1280] 0.707031 -0.326416 0.686035 ..
CCV_NNC_TRANSPOSE_FORWARD [463]: [1] -> [1] (1)
|-> 1. 0x1438e0eb0 (0x285da7000:0) [2x256x8x160] 0.707031 -0.326416 0.686035 ..
|<- 1. 0x1438a75b0 (0x285da7040:0) [2x8x256x160] 0.707031 -0.326416 0.686035 ..
Emit: (1, 40)
CCV_NNC_GEMM_FORWARD [464]: [2] -> [1] (2)
Wait: (2, 39)
|-> 1. 0x1438a7380 (0x285da6e00:0) [2x256x1280] 0.315430 -0.002338 0.280762 ..
|-> 2. 0x1438c25f0 (0x285d87500:0) [1280x1280] 0.055420 0.017975 0.068176 ..
|<- 1. 0x1438a7690 (0x285da70c0:0) [2x256x1280] -0.751953 0.787109 0.171875 ..
CCV_NNC_TRANSPOSE_FORWARD [465]: [1] -> [1] (2)
|-> 1. 0x1438e1070 (0x285da70c0:0) [2x256x8x160] -0.751953 0.787109 0.171875 ..
|<- 1. 0x1438a7770 (0x285da7140:0) [2x8x256x160] -0.751953 0.787109 0.171875 ..
Emit: (2, 41)
CCV_NNC_GEMM_FORWARD [466]: [2] -> [1] (0)
Wait: (0, 40)
|-> 1. 0x1438e1000 (0x285da7080:0) [1x256x160] 0.028137 -0.059509 -0.038269 ..
|-> 2. 0x1438e0f90 (0x285da7040:0) [1x256x160] 0.707031 -0.326416 0.686035 ..
|<- 1. 0x1438a7700 (0x285da7100:0) [1x256x256] 4.882812 2.759766 3.513672 ..
CCV_NNC_SOFTMAX_FORWARD [467]: [1] -> [1] (0)
|-> 1. 0x1438e10e0 (0x285da7100:0) [256x256] 4.882812 2.759766 3.513672 ..
|<- 1. 0x1438e10e0 (0x285da7100:0) [256x256] 0.094788 0.011345 0.024109 ..
CCV_NNC_GEMM_FORWARD [468]: [2] -> [1] (0)
Wait: (0, 41)
|-> 1. 0x1438e11c0 (0x285da7100:0) [1x256x256] 0.094788 0.011345 0.024109 ..
|-> 2. 0x1438e1150 (0x285da7140:0) [1x256x160] -0.751953 0.787109 0.171875 ..
|<- 1. 0x1438e3e40 (0x285da6e00:0) [1x256x160] -0.256104 0.208862 0.047241 ..
CCV_NNC_GEMM_FORWARD [469]: [2] -> [1] (0)
|-> 1. 0x1438e12e0 (0x285da7080:0) [1x256x160] -0.042328 0.019577 -0.101440 ..
|-> 2. 0x1438e1230 (0x285da7040:0) [1x256x160] -0.701172 1.413086 0.542969 ..
|<- 1. 0x1438a77e0 (0x285da7100:0) [1x256x256] 6.472656 4.500000 5.277344 ..
CCV_NNC_SOFTMAX_FORWARD [470]: [1] -> [1] (0)
|-> 1. 0x1438e1390 (0x285da7100:0) [256x256] 6.472656 4.500000 5.277344 ..
|<- 1. 0x1438e1390 (0x285da7100:0) [256x256] 0.058502 0.008141 0.017700 ..
CCV_NNC_GEMM_FORWARD [471]: [2] -> [1] (0)
|-> 1. 0x1438e14b0 (0x285da7100:0) [1x256x256] 0.058502 0.008141 0.017700 ..
|-> 2. 0x1438e1400 (0x285da7140:0) [1x256x160] 0.479492 -0.240845 0.208130 ..
|<- 1. 0x1438e3eb0 (0x285da6e00:0) [1x256x160] 0.035278 -0.018234 0.306641 ..
CCV_NNC_GEMM_FORWARD [472]: [2] -> [1] (0)
|-> 1. 0x1438e15d0 (0x285da7080:0) [1x256x160] -0.039490 -0.046509 -0.083435 ..
|-> 2. 0x1438e1520 (0x285da7040:0) [1x256x160] 1.148438 -1.852539 -2.455078 ..
|<- 1. 0x1438a7850 (0x285da7100:0) [1x256x256] 3.619141 -0.240723 0.866211 ..
CCV_NNC_SOFTMAX_FORWARD [473]: [1] -> [1] (0)
|-> 1. 0x1438e1680 (0x285da7100:0) [256x256] 3.619141 -0.240723 0.866211 ..
|<- 1. 0x1438e1680 (0x285da7100:0) [256x256] 0.013039 0.000275 0.000831 ..
CCV_NNC_GEMM_FORWARD [474]: [2] -> [1] (0)
|-> 1. 0x1438e17a0 (0x285da7100:0) [1x256x256] 0.013039 0.000275 0.000831 ..
|-> 2. 0x1438e16f0 (0x285da7140:0) [1x256x160] 0.175171 0.172974 -0.729004 ..
|<- 1. 0x1438e3f60 (0x285da6e00:0) [1x256x160] -0.153076 -0.212891 0.104187 ..
CCV_NNC_GEMM_FORWARD [475]: [2] -> [1] (0)
|-> 1. 0x1438e18c0 (0x285da7080:0) [1x256x160] -0.005409 -0.000726 0.022507 ..
|-> 2. 0x1438e1810 (0x285da7040:0) [1x256x160] 0.128418 -1.059570 -0.328613 ..
|<- 1. 0x1438a78c0 (0x285da7100:0) [1x256x256] 1.959961 1.376953 1.509766 ..
CCV_NNC_SOFTMAX_FORWARD [476]: [1] -> [1] (0)
|-> 1. 0x1438e1970 (0x285da7100:0) [256x256] 1.959961 1.376953 1.509766 ..
|<- 1. 0x1438e1970 (0x285da7100:0) [256x256] 0.012146 0.006779 0.007744 ..
CCV_NNC_GEMM_FORWARD [477]: [2] -> [1] (0)
|-> 1. 0x1438e1a90 (0x285da7100:0) [1x256x256] 0.012146 0.006779 0.007744 ..
|-> 2. 0x1438e19e0 (0x285da7140:0) [1x256x160] 0.505371 0.581055 -0.445312 ..
|<- 1. 0x1438e4010 (0x285da6e00:0) [1x256x160] 0.362793 0.014778 0.280518 ..
CCV_NNC_GEMM_FORWARD [478]: [2] -> [1] (0)
|-> 1. 0x1438e1bb0 (0x285da7080:0) [1x256x160] 0.002422 0.013702 0.031921 ..
|-> 2. 0x1438e1b00 (0x285da7040:0) [1x256x160] 1.154297 0.705566 -0.611328 ..
|<- 1. 0x1438a7930 (0x285da7100:0) [1x256x256] 4.734375 1.331055 1.833008 ..
CCV_NNC_SOFTMAX_FORWARD [479]: [1] -> [1] (0)
|-> 1. 0x1438e1c60 (0x285da7100:0) [256x256] 4.734375 1.331055 1.833008 ..
|<- 1. 0x1438e1c60 (0x285da7100:0) [256x256] 0.128662 0.004276 0.007065 ..
CCV_NNC_GEMM_FORWARD [480]: [2] -> [1] (0)
|-> 1. 0x1438e1d80 (0x285da7100:0) [1x256x256] 0.128662 0.004276 0.007065 ..
|-> 2. 0x1438e1cd0 (0x285da7140:0) [1x256x160] -0.613281 0.469727 0.428467 ..
|<- 1. 0x1438e40c0 (0x285da6e00:0) [1x256x160] -0.031250 0.179688 0.014679 ..
CCV_NNC_GEMM_FORWARD [481]: [2] -> [1] (0)
|-> 1. 0x1438e1ea0 (0x285da7080:0) [1x256x160] 0.100281 -0.066895 -0.050751 ..
|-> 2. 0x1438e1df0 (0x285da7040:0) [1x256x160] -0.807617 -0.915527 -0.214478 ..
|<- 1. 0x1438a79a0 (0x285da7100:0) [1x256x256] 1.790039 0.644043 0.502441 ..
CCV_NNC_SOFTMAX_FORWARD [482]: [1] -> [1] (0)
|-> 1. 0x1438e1f50 (0x285da7100:0) [256x256] 1.790039 0.644043 0.502441 ..
|<- 1. 0x1438e1f50 (0x285da7100:0) [256x256] 0.008904 0.002831 0.002457 ..
CCV_NNC_GEMM_FORWARD [483]: [2] -> [1] (0)
|-> 1. 0x1438e2070 (0x285da7100:0) [1x256x256] 0.008904 0.002831 0.002457 ..
|-> 2. 0x1438e1fc0 (0x285da7140:0) [1x256x160] 0.596191 -0.624023 0.214111 ..
|<- 1. 0x1438e4170 (0x285da6e00:0) [1x256x160] -0.063843 -0.168335 -0.070435 ..
CCV_NNC_GEMM_FORWARD [484]: [2] -> [1] (0)
|-> 1. 0x1438e2190 (0x285da7080:0) [1x256x160] 0.038116 0.057861 0.024002 ..
|-> 2. 0x1438e20e0 (0x285da7040:0) [1x256x160] -2.386719 0.047760 -0.548828 ..
|<- 1. 0x1438a7a10 (0x285da7100:0) [1x256x256] 5.691406 4.570312 4.808594 ..
CCV_NNC_SOFTMAX_FORWARD [485]: [1] -> [1] (0)
|-> 1. 0x1438e2240 (0x285da7100:0) [256x256] 5.691406 4.570312 4.808594 ..
|<- 1. 0x1438e2240 (0x285da7100:0) [256x256] 0.016617 0.005417 0.006874 ..
CCV_NNC_GEMM_FORWARD [486]: [2] -> [1] (0)
|-> 1. 0x1438e2360 (0x285da7100:0) [1x256x256] 0.016617 0.005417 0.006874 ..
|-> 2. 0x1438e22b0 (0x285da7140:0) [1x256x160] -0.256592 -0.104736 -0.637695 ..
|<- 1. 0x1438e4220 (0x285da6e00:0) [1x256x160] -0.047211 -0.195923 -0.123291 ..
CCV_NNC_GEMM_FORWARD [487]: [2] -> [1] (0)
|-> 1. 0x1438e2480 (0x285da7080:0) [1x256x160] -0.047668 0.008713 0.019104 ..
|-> 2. 0x1438e23d0 (0x285da7040:0) [1x256x160] 0.291992 0.872070 0.010788 ..
|<- 1. 0x1438a7a80 (0x285da7100:0) [1x256x256] 0.074707 -0.410156 -0.641113 ..
CCV_NNC_SOFTMAX_FORWARD [488]: [1] -> [1] (0)
|-> 1. 0x1438e2530 (0x285da7100:0) [256x256] 0.074707 -0.410156 -0.641113 ..
|<- 1. 0x1438e2530 (0x285da7100:0) [256x256] 0.006721 0.004139 0.003284 ..
CCV_NNC_GEMM_FORWARD [489]: [2] -> [1] (0)
|-> 1. 0x1438e2650 (0x285da7100:0) [1x256x256] 0.006721 0.004139 0.003284 ..
|-> 2. 0x1438e25a0 (0x285da7140:0) [1x256x160] -0.481689 -0.672852 -0.152954 ..
|<- 1. 0x1438e42d0 (0x285da6e00:0) [1x256x160] -0.108215 -0.042847 -0.190308 ..
CCV_NNC_GEMM_FORWARD [490]: [2] -> [1] (0)
|-> 1. 0x1438e2770 (0x285da7080:0) [1x256x160] 0.032257 -0.060242 -0.044037 ..
|-> 2. 0x1438e26c0 (0x285da7040:0) [1x256x160] 0.795410 -0.431152 0.629883 ..
|<- 1. 0x1438a7af0 (0x285da7100:0) [1x256x256] 4.914062 2.873047 3.279297 ..
CCV_NNC_SOFTMAX_FORWARD [491]: [1] -> [1] (0)
|-> 1. 0x1438e2820 (0x285da7100:0) [256x256] 4.914062 2.873047 3.279297 ..
|<- 1. 0x1438e2820 (0x285da7100:0) [256x256] 0.107849 0.014008 0.021027 ..
CCV_NNC_GEMM_FORWARD [492]: [2] -> [1] (0)
|-> 1. 0x1438e2940 (0x285da7100:0) [1x256x256] 0.107849 0.014008 0.021027 ..
|-> 2. 0x1438e2890 (0x285da7140:0) [1x256x160] -0.669922 0.712402 0.161255 ..
|<- 1. 0x1438e4380 (0x285da6e00:0) [1x256x160] -0.199951 0.126953 0.041595 ..
CCV_NNC_GEMM_FORWARD [493]: [2] -> [1] (0)
|-> 1. 0x1438e2a60 (0x285da7080:0) [1x256x160] -0.038391 0.020187 -0.100281 ..
|-> 2. 0x1438e29b0 (0x285da7040:0) [1x256x160] -0.332275 1.332031 0.343018 ..
|<- 1. 0x1438a7b60 (0x285da7100:0) [1x256x256] 6.468750 4.593750 5.273438 ..
CCV_NNC_SOFTMAX_FORWARD [494]: [1] -> [1] (0)
|-> 1. 0x1438e2b10 (0x285da7100:0) [256x256] 6.468750 4.593750 5.273438 ..
|<- 1. 0x1438e2b10 (0x285da7100:0) [256x256] 0.065979 0.010117 0.019958 ..
CCV_NNC_GEMM_FORWARD [495]: [2] -> [1] (0)
|-> 1. 0x1438e2c30 (0x285da7100:0) [1x256x256] 0.065979 0.010117 0.019958 ..
|-> 2. 0x1438e2b80 (0x285da7140:0) [1x256x160] 0.428467 -0.251465 0.082031 ..
|<- 1. 0x1438e4430 (0x285da6e00:0) [1x256x160] -0.021912 -0.003967 0.127075 ..
CCV_NNC_GEMM_FORWARD [496]: [2] -> [1] (0)
|-> 1. 0x1438e2d50 (0x285da7080:0) [1x256x160] -0.041290 -0.048462 -0.083313 ..
|-> 2. 0x1438e2ca0 (0x285da7040:0) [1x256x160] 1.102539 -2.031250 -2.511719 ..
|<- 1. 0x1438a7bd0 (0x285da7100:0) [1x256x256] 3.585938 -0.072998 0.993164 ..
CCV_NNC_SOFTMAX_FORWARD [497]: [1] -> [1] (0)
|-> 1. 0x1438e2e00 (0x285da7100:0) [256x256] 3.585938 -0.072998 0.993164 ..
|<- 1. 0x1438e2e00 (0x285da7100:0) [256x256] 0.012482 0.000322 0.000934 ..
CCV_NNC_GEMM_FORWARD [498]: [2] -> [1] (0)
|-> 1. 0x1438e2f20 (0x285da7100:0) [1x256x256] 0.012482 0.000322 0.000934 ..
|-> 2. 0x1438e2e70 (0x285da7140:0) [1x256x160] 0.198364 -0.013878 -0.708496 ..
|<- 1. 0x1438e44e0 (0x285da6e00:0) [1x256x160] -0.229980 -0.289551 0.093201 ..
CCV_NNC_GEMM_FORWARD [499]: [2] -> [1] (0)
|-> 1. 0x1438e3040 (0x285da7080:0) [1x256x160] -0.005821 -0.014534 0.018280 ..
|-> 2. 0x1438e2f90 (0x285da7040:0) [1x256x160] 0.269775 -1.095703 -0.198120 ..
|<- 1. 0x1438a7c40 (0x285da7100:0) [1x256x256] 2.164062 1.581055 1.705078 ..
CCV_NNC_SOFTMAX_FORWARD [500]: [1] -> [1] (0)
|-> 1. 0x1438e30f0 (0x285da7100:0) [256x256] 2.164062 1.581055 1.705078 ..
|<- 1. 0x1438e30f0 (0x285da7100:0) [256x256] 0.015244 0.008514 0.009636 ..
CCV_NNC_GEMM_FORWARD [501]: [2] -> [1] (0)
|-> 1. 0x1438e3210 (0x285da7100:0) [1x256x256] 0.015244 0.008514 0.009636 ..
|-> 2. 0x1438e3160 (0x285da7140:0) [1x256x160] 0.503418 0.542480 -0.369141 ..
|<- 1. 0x1438e4590 (0x285da6e00:0) [1x256x160] 0.316406 -0.060425 0.264648 ..
CCV_NNC_GEMM_FORWARD [502]: [2] -> [1] (0)
|-> 1. 0x1438e3330 (0x285da7080:0) [1x256x160] 0.001838 0.020554 0.028427 ..
|-> 2. 0x1438e3280 (0x285da7040:0) [1x256x160] 1.364258 0.760254 -0.581543 ..
|<- 1. 0x1438a7cb0 (0x285da7100:0) [1x256x256] 4.667969 1.554688 2.054688 ..
CCV_NNC_SOFTMAX_FORWARD [503]: [1] -> [1] (0)
|-> 1. 0x1438e33e0 (0x285da7100:0) [256x256] 4.667969 1.554688 2.054688 ..
|<- 1. 0x1438e33e0 (0x285da7100:0) [256x256] 0.131592 0.005848 0.009644 ..
CCV_NNC_GEMM_FORWARD [504]: [2] -> [1] (0)
|-> 1. 0x1438e3500 (0x285da7100:0) [1x256x256] 0.131592 0.005848 0.009644 ..
|-> 2. 0x1438e3450 (0x285da7140:0) [1x256x160] -0.534180 0.441162 0.400391 ..
|<- 1. 0x1438e4640 (0x285da6e00:0) [1x256x160] -0.003521 0.156860 -0.056000 ..
CCV_NNC_GEMM_FORWARD [505]: [2] -> [1] (0)
|-> 1. 0x1438e3620 (0x285da7080:0) [1x256x160] 0.087830 -0.050659 -0.052521 ..
|-> 2. 0x1438e3570 (0x285da7040:0) [1x256x160] -0.844727 -0.783203 -0.423096 ..
|<- 1. 0x1438a7d20 (0x285da7100:0) [1x256x256] 1.906250 1.033203 0.901855 ..
CCV_NNC_SOFTMAX_FORWARD [506]: [1] -> [1] (0)
|-> 1. 0x1438e36d0 (0x285da7100:0) [256x256] 1.906250 1.033203 0.901855 ..
|<- 1. 0x1438e36d0 (0x285da7100:0) [256x256] 0.007812 0.003263 0.002861 ..
CCV_NNC_GEMM_FORWARD [507]: [2] -> [1] (0)
|-> 1. 0x1438e37f0 (0x285da7100:0) [1x256x256] 0.007812 0.003263 0.002861 ..
|-> 2. 0x1438e3740 (0x285da7140:0) [1x256x160] 0.654785 -0.521484 0.268311 ..
|<- 1. 0x1438e46f0 (0x285da6e00:0) [1x256x160] -0.063782 -0.092041 0.057983 ..
CCV_NNC_GEMM_FORWARD [508]: [2] -> [1] (0)
|-> 1. 0x1438e3910 (0x285da7080:0) [1x256x160] 0.038544 0.041870 0.012657 ..
|-> 2. 0x1438e3860 (0x285da7040:0) [1x256x160] -2.333984 0.066101 -0.386230 ..
|<- 1. 0x1438a7d90 (0x285da7100:0) [1x256x256] 5.812500 4.636719 5.191406 ..
CCV_NNC_SOFTMAX_FORWARD [509]: [1] -> [1] (0)
|-> 1. 0x1438e39c0 (0x285da7100:0) [256x256] 5.812500 4.636719 5.191406 ..
|<- 1. 0x1438e39c0 (0x285da7100:0) [256x256] 0.017822 0.005497 0.009575 ..
CCV_NNC_GEMM_FORWARD [510]: [2] -> [1] (0)
|-> 1. 0x1438e3ae0 (0x285da7100:0) [1x256x256] 0.017822 0.005497 0.009575 ..
|-> 2. 0x1438e3a30 (0x285da7140:0) [1x256x160] -0.254150 -0.162598 -0.588867 ..
|<- 1. 0x1438e47a0 (0x285da6e00:0) [1x256x160] -0.045349 -0.212646 -0.063049 ..
CCV_NNC_GEMM_FORWARD [511]: [2] -> [1] (0)
|-> 1. 0x1438e3c00 (0x285da7080:0) [1x256x160] -0.048370 0.008675 0.014503 ..
|-> 2. 0x1438e3b50 (0x285da7040:0) [1x256x160] 0.213135 0.942871 0.182495 ..
|<- 1. 0x1438a7e00 (0x285da7100:0) [1x256x256] 0.286133 -0.336914 -0.302002 ..
CCV_NNC_SOFTMAX_FORWARD [512]: [1] -> [1] (0)
|-> 1. 0x1438e3cb0 (0x285da7100:0) [256x256] 0.286133 -0.336914 -0.302002 ..
|<- 1. 0x1438e3cb0 (0x285da7100:0) [256x256] 0.007343 0.003937 0.004078 ..
CCV_NNC_GEMM_FORWARD [513]: [2] -> [1] (0)
|-> 1. 0x1438e3dd0 (0x285da7100:0) [1x256x256] 0.007343 0.003937 0.004078 ..
|-> 2. 0x1438e3d20 (0x285da7140:0) [1x256x160] -0.340088 -0.412598 -0.144287 ..
|<- 1. 0x1438e4850 (0x285da6e00:0) [1x256x160] -0.008133 0.087646 -0.112488 ..
CCV_NNC_TRANSPOSE_FORWARD [514]: [1] -> [1] (0)
|-> 1. 0x1438e4900 (0x285da6e00:0) [2x8x256x160] -0.256104 0.208862 0.047241 ..
|<- 1. 0x1438a7ee0 (0x285da7140:0) [2x256x8x160] -0.256104 0.208862 0.047241 ..
CCV_NNC_GEMM_FORWARD [515]: [3] -> [1] (0)
|-> 1. 0x1438e4970 (0x285da7140:0) [2x256x1280] -0.256104 0.208862 0.047241 ..
|-> 2. 0x1438c2660 (0x285d87540:0) [1280x1280] -0.033295 -0.005096 0.008888 ..
|-> 3. 0x1438c26d0 (0x285d87580:0) [1280] 0.042267 -0.030930 0.017395 ..
|<- 1. 0x1438a7f50 (0x285da6e00:0) [2x256x1280] 0.172607 -0.576660 0.459961 ..
CCV_NNC_ADD_FORWARD [516]: [2] -> [1] (0)
|-> 1. 0x1438a7f50 (0x285da6e00:0) [2x256x1280] 0.172607 -0.576660 0.459961 ..
|-> 2. 0x1438e0e40 (0x285da6dc0:0) [2x256x1280] 0.916016 0.061157 0.760742 ..
|<- 1. 0x1438a7f50 (0x285da6e00:0) [2x256x1280] 1.088867 -0.515625 1.220703 ..
CCV_NNC_LAYER_NORM_FORWARD [517]: [3] -> [3] (0)
|-> 1. 0x1438a7f50 (0x285da6e00:0) [2x256x1280] 1.088867 -0.515625 1.220703 ..
|-> 2. 0x1438c2740 (0x285d875c0:0) [1x1x1280] 0.298828 0.334473 0.325195 ..
|-> 3. 0x1438c27b0 (0x285d87600:0) [1x1x1280] 0.028320 -0.101685 0.016495 ..
|<- 1. 0x1438a7fc0 (0x285da6dc0:0) [2x256x1280] 0.471436 -0.338379 0.557129 ..
|<- 2. 0x1438a8030 (0x285da6f40:0) [2x256x1] 0.002930 ..
|<- 3. 0x1438a80a0 (0x285da6f80:0) [2x256x1] 1.365234 ..
CCV_NNC_GEMM_FORWARD [518]: [2] -> [1] (0)
|-> 1. 0x1438a7fc0 (0x285da6dc0:0) [2x256x1280] 0.471436 -0.338379 0.557129 ..
|-> 2. 0x1438c2820 (0x285d87640:0) [1280x1280] -0.016846 -0.033051 -0.043243 ..
|<- 1. 0x1438a8110 (0x285da7140:0) [2x256x1280] 0.489746 1.373047 0.477539 ..
CCV_NNC_SCALAR_MUL_FORWARD [519]: [1] -> [1] (0)
|-> 1. 0x1438a8110 (0x285da7140:0) [2x256x1280] 0.489746 1.373047 0.477539 ..
|<- 1. 0x1438a8110 (0x285da7140:0) [2x256x1280] 0.038696 0.108521 0.037750 ..
CCV_NNC_TRANSPOSE_FORWARD [520]: [1] -> [1] (0)
|-> 1. 0x1438e4a50 (0x285da7140:0) [2x256x8x160] 0.038696 0.108521 0.037750 ..
|<- 1. 0x1438a8260 (0x285da6dc0:0) [2x8x256x160] 0.038696 0.108521 0.037750 ..
CCV_NNC_GEMM_FORWARD [521]: [2] -> [1] (0)
Wait: (0, 42)
|-> 1. 0x1438a8260 (0x285da6dc0:0) [2x8x256x160] 0.038696 0.108521 0.037750 ..
|-> 2. 0x1438a81f0 (0x285da71c0:0) [2x8x133x160] -0.213623 0.277832 -0.094299 ..
|<- 1. 0x1438a82d0 (0x285da7200:0) [2x8x256x133] 10.367188 2.091797 0.305908 ..
CCV_NNC_SOFTMAX_FORWARD [522]: [1] -> [1] (0)
|-> 1. 0x1438e4ac0 (0x285da7200:0) [4096x133] 10.367188 2.091797 0.305908 ..
|<- 1. 0x1438e4ac0 (0x285da7200:0) [4096x133] 0.488037 0.000124 0.000021 ..
CCV_NNC_GEMM_FORWARD [523]: [2] -> [1] (0)
Wait: (0, 43)
|-> 1. 0x1438e4ba0 (0x285da7200:0) [2x8x256x133] 0.488037 0.000124 0.000021 ..
|-> 2. 0x1438a83b0 (0x285da7280:0) [2x8x133x160] -0.006889 -0.040039 0.008888 ..
|<- 1. 0x1438a8420 (0x285da6dc0:0) [2x8x256x160] 0.411377 0.048035 0.267090 ..
CCV_NNC_TRANSPOSE_FORWARD [524]: [1] -> [1] (0)
|-> 1. 0x1438e4c10 (0x285da6dc0:0) [2x8x256x160] 0.411377 0.048035 0.267090 ..
|<- 1. 0x1438a8490 (0x285da7140:0) [2x256x8x160] 0.411377 0.048035 0.267090 ..
CCV_NNC_GEMM_FORWARD [525]: [3] -> [1] (0)
|-> 1. 0x1438e4c80 (0x285da7140:0) [2x256x1280] 0.411377 0.048035 0.267090 ..
|-> 2. 0x1438c2970 (0x285d87700:0) [1280x1280] 0.012047 -0.022003 -0.013741 ..
|-> 3. 0x1438c29e0 (0x285d87740:0) [1280] 0.027283 -0.020676 0.019165 ..
|<- 1. 0x1438a8500 (0x285da7000:0) [2x256x1280] 0.229858 -0.220703 -0.032501 ..
CCV_NNC_ADD_FORWARD [526]: [2] -> [1] (0)
|-> 1. 0x1438a8500 (0x285da7000:0) [2x256x1280] 0.229858 -0.220703 -0.032501 ..
|-> 2. 0x1438a7f50 (0x285da6e00:0) [2x256x1280] 1.088867 -0.515625 1.220703 ..
|<- 1. 0x1438a8500 (0x285da7000:0) [2x256x1280] 1.318359 -0.736328 1.188477 ..
CCV_NNC_LAYER_NORM_FORWARD [527]: [3] -> [3] (0)
|-> 1. 0x1438a8500 (0x285da7000:0) [2x256x1280] 1.318359 -0.736328 1.188477 ..
|-> 2. 0x1438c2a50 (0x285d87780:0) [1x1x1280] 0.214355 0.206787 0.204468 ..
|-> 3. 0x1438c2ac0 (0x285d877c0:0) [1x1x1280] -0.040192 0.012550 -0.007683 ..
|<- 1. 0x1438a8570 (0x285da72c0:0) [2x256x1280] 0.326904 -0.185669 0.307861 ..
|<- 2. 0x1438a85e0 (0x285da7300:0) [2x256x1] 0.000971 ..
|<- 3. 0x1438a8650 (0x285da7340:0) [2x256x1] 1.299805 ..
Emit: (0, 44)
CCV_NNC_GEMM_FORWARD [528]: [3] -> [1] (0)
|-> 1. 0x1438a8570 (0x285da72c0:0) [2x256x1280] 0.326904 -0.185669 0.307861 ..
|-> 2. 0x1438c2b30 (0x285d87800:0) [5120x1280] 0.086304 -0.005783 0.019226 ..
|-> 3. 0x1438c2ba0 (0x285d87840:0) [5120] 0.013763 0.002728 0.104187 ..
|<- 1. 0x1438a86c0 (0x285da7380:0) [2x256x5120] -0.285889 0.167847 0.058746 ..
CCV_NNC_GELU_FORWARD [529]: [1] -> [1] (0)
|-> 1. 0x1438a86c0 (0x285da7380:0) [2x256x5120] -0.285889 0.167847 0.058746 ..
|<- 1. 0x1438a86c0 (0x285da7380:0) [2x256x5120] -0.110779 0.095093 0.030746 ..
CCV_NNC_GEMM_FORWARD [530]: [3] -> [1] (1)
Wait: (1, 44)
|-> 1. 0x1438a8570 (0x285da72c0:0) [2x256x1280] 0.326904 -0.185669 0.307861 ..
|-> 2. 0x1438c2c10 (0x285d87880:0) [5120x1280] -0.046326 -0.024994 -0.023727 ..
|-> 3. 0x1438c2c80 (0x285d878c0:0) [5120] 0.017410 -0.023102 0.002996 ..
|<- 1. 0x1438a8730 (0x285da5ac0:0) [2x256x5120] 0.425537 -0.358887 0.792480 ..
Emit: (1, 45)
CCV_NNC_MUL_FORWARD [531]: [2] -> [1] (0)
Wait: (0, 45)
|-> 1. 0x1438a8730 (0x285da5ac0:0) [2x256x5120] 0.425537 -0.358887 0.792480 ..
|-> 2. 0x1438a86c0 (0x285da7380:0) [2x256x5120] -0.110779 0.095093 0.030746 ..
|<- 1. 0x1438a8730 (0x285da5ac0:0) [2x256x5120] -0.047150 -0.034119 0.024368 ..
CCV_NNC_GEMM_FORWARD [532]: [3] -> [1] (0)
|-> 1. 0x1438a8730 (0x285da5ac0:0) [2x256x5120] -0.047150 -0.034119 0.024368 ..
|-> 2. 0x1438c2cf0 (0x285d87900:0) [1280x5120] -0.042450 -0.023239 0.037201 ..
|-> 3. 0x1438c2d60 (0x285d87940:0) [1280] -0.003574 -0.007950 0.008675 ..
|<- 1. 0x1438a87a0 (0x285da72c0:0) [2x256x1280] -1.554688 -0.173950 -1.076172 ..
CCV_NNC_ADD_FORWARD [533]: [2] -> [1] (0)
|-> 1. 0x1438a87a0 (0x285da72c0:0) [2x256x1280] -1.554688 -0.173950 -1.076172 ..
|-> 2. 0x1438a8500 (0x285da7000:0) [2x256x1280] 1.318359 -0.736328 1.188477 ..
|<- 1. 0x1438a87a0 (0x285da72c0:0) [2x256x1280] -0.236328 -0.910156 0.112305 ..
CCV_NNC_CONVOLUTION_FORWARD [534]: [3] -> [1] (0)
|-> 1. 0x1438e4cf0 (0x285da72c0:0) [2x16x16x1280] -0.236328 -0.910156 0.112305 ..
|-> 2. 0x1438c2dd0 (0x285d87980:0) [1280x1280x1x1] 0.000402 ..
|-> 3. 0x1438c2e40 (0x285d879c0:0) [1280] 0.016434 0.028961 0.004444 ..
|<- 1. 0x1438a8810 (0x285da6e00:0) [2x16x16x1280] 2.337891 1.597656 -1.694336 ..
CCV_NNC_ADD_FORWARD [535]: [2] -> [1] (0)
|-> 1. 0x1438a8810 (0x285da6e00:0) [2x16x16x1280] 2.337891 1.597656 -1.694336 ..
|-> 2. 0x1438a7150 (0x285da6f00:0) [2x16x16x1280] -0.341553 0.146973 -0.125977 ..
|<- 1. 0x1438f14e0 (0x285da64c0:0) [2x16x16x1280] 1.996094 1.744141 -1.820312 ..
CCV_NNC_GROUP_NORM_FORWARD [536]: [3] -> [3] (0)
|-> 1. 0x1438f14e0 (0x285da64c0:0) [2x16x16x1280] 1.996094 1.744141 -1.820312 ..
|-> 2. 0x1438c2eb0 (0x285d87a00:0) [1x1x1x1280] 0.333008 0.327637 0.387939 ..
|-> 3. 0x1438c2f20 (0x285d87a40:0) [1x1x1x1280] -0.034149 -0.050507 -0.072388 ..
|<- 1. 0x1438a8880 (0x285da6e00:0) [2x16x16x1280] 0.492676 0.400391 -0.667969 ..
|<- 2. 0x1438a88f0 (0x285da73c0:0) [2x1x1x32] 0.059357 -0.062683 -0.005947 ..
|<- 3. 0x1438a8960 (0x285da7400:0) [2x1x1x32] 0.816895 0.872070 0.783691 ..
CCV_NNC_SWISH_FORWARD [537]: [1] -> [1] (0)
|-> 1. 0x1438a8880 (0x285da6e00:0) [2x16x16x1280] 0.492676 0.400391 -0.667969 ..
|<- 1. 0x1438a8880 (0x285da6e00:0) [2x16x16x1280] 0.305908 0.239746 -0.226440 ..
CCV_NNC_CONVOLUTION_FORWARD [538]: [3] -> [1] (0)
|-> 1. 0x1438a8880 (0x285da6e00:0) [2x16x16x1280] 0.305908 0.239746 -0.226440 ..
|-> 2. 0x1438c3070 (0x285d87b00:0) [1280x1280x3x3] -0.036163 0.019897 0.004116 ..
|-> 3. 0x1438c30e0 (0x285d87b40:0) [1280] 0.052185 -0.014023 0.033203 ..
|<- 1. 0x1438a8a40 (0x285da6f00:0) [2x16x16x1280] -0.425781 -0.730957 -0.226562 ..
CCV_NNC_ADD_FORWARD [539]: [2] -> [1] (0)
Wait: (0, 46)
|-> 1. 0x1438a8a40 (0x285da6f00:0) [2x16x16x1280] -0.425781 -0.730957 -0.226562 ..
|-> 2. 0x1438e4d60 (0x285da7440:0) [2x1x1x1280] 0.601562 -0.082703 0.705078 ..
|<- 1. 0x1438a8a40 (0x285da6f00:0) [2x16x16x1280] 0.175781 -0.813477 0.478516 ..
CCV_NNC_GROUP_NORM_FORWARD [540]: [3] -> [3] (0)
|-> 1. 0x1438a8a40 (0x285da6f00:0) [2x16x16x1280] 0.175781 -0.813477 0.478516 ..
|-> 2. 0x1438c3150 (0x285d87b80:0) [1x1x1x1280] 0.284668 0.658203 0.624023 ..
|-> 3. 0x1438c31c0 (0x285d87bc0:0) [1x1x1x1280] -0.110962 -0.154785 -0.171997 ..
|<- 1. 0x1438a8ab0 (0x285da6e00:0) [2x16x16x1280] -0.144409 -0.709473 -0.106750 ..
|<- 2. 0x1438a8b20 (0x285da6800:0) [2x1x1x32] 0.335938 0.340576 0.368408 ..
|<- 3. 0x1438a8b90 (0x285da67c0:0) [2x1x1x32] 0.733398 0.658691 0.897461 ..
CCV_NNC_SWISH_FORWARD [541]: [1] -> [1] (0)
|-> 1. 0x1438a8ab0 (0x285da6e00:0) [2x16x16x1280] -0.144409 -0.709473 -0.106750 ..
|<- 1. 0x1438a8ab0 (0x285da6e00:0) [2x16x16x1280] -0.067017 -0.233887 -0.050537 ..
CCV_NNC_CONVOLUTION_FORWARD [542]: [3] -> [1] (0)
|-> 1. 0x1438a8ab0 (0x285da6e00:0) [2x16x16x1280] -0.067017 -0.233887 -0.050537 ..
|-> 2. 0x1438c3230 (0x285d87c00:0) [1280x1280x3x3] -0.012634 0.007359 -0.021210 ..
|-> 3. 0x1438c32a0 (0x285d87c40:0) [1280] 0.004417 -0.009216 0.003883 ..
|<- 1. 0x1438a8c00 (0x285da6dc0:0) [2x16x16x1280] -0.556152 0.048492 -0.749023 ..
CCV_NNC_ADD_FORWARD [543]: [2] -> [1] (0)
|-> 1. 0x1438f14e0 (0x285da64c0:0) [2x16x16x1280] 1.996094 1.744141 -1.820312 ..
|-> 2. 0x1438a8c00 (0x285da6dc0:0) [2x16x16x1280] -0.556152 0.048492 -0.749023 ..
|<- 1. 0x1438a8c70 (0x285da6f00:0) [2x16x16x1280] 1.439453 1.792969 -2.570312 ..
CCV_NNC_GROUP_NORM_FORWARD [544]: [3] -> [3] (0)
|-> 1. 0x1438a8c70 (0x285da6f00:0) [2x16x16x1280] 1.439453 1.792969 -2.570312 ..
|-> 2. 0x1438c3310 (0x285d87c80:0) [1x1x1x1280] 0.274902 0.281982 0.277588 ..
|-> 3. 0x1438c3380 (0x285d87cc0:0) [1x1x1x1280] -0.027802 0.013046 -0.012108 ..
|<- 1. 0x1438a8ce0 (0x285da6dc0:0) [2x16x16x1280] 0.266113 0.388184 -0.538086 ..
|<- 2. 0x1438a8d50 (0x285da6100:0) [2x1x1x32] -0.006233 -0.164307 -0.001076 ..
|<- 3. 0x1438a8dc0 (0x285da6140:0) [2x1x1x32] 0.739258 0.812500 0.757812 ..
CCV_NNC_CONVOLUTION_FORWARD [545]: [3] -> [1] (0)
|-> 1. 0x1438a8ce0 (0x285da6dc0:0) [2x16x16x1280] 0.266113 0.388184 -0.538086 ..
|-> 2. 0x1438c33f0 (0x285d87d00:0) [1280x1280x1x1] -0.043732 ..
|-> 3. 0x1438c3460 (0x285d87d40:0) [1280] -0.055511 0.011642 0.023346 ..
|<- 1. 0x1438a8e30 (0x285da6e00:0) [2x16x16x1280] -0.364502 -0.283447 0.436768 ..
CCV_NNC_LAYER_NORM_FORWARD [546]: [3] -> [3] (0)
|-> 1. 0x1438e4dd0 (0x285da6e00:0) [2x256x1280] -0.364502 -0.283447 0.436768 ..
|-> 2. 0x1438c34d0 (0x285d87d80:0) [1x1x1280] 0.291748 0.307373 0.281494 ..
|-> 3. 0x1438c3540 (0x285d87dc0:0) [1x1x1280] 0.017899 0.019028 -0.010086 ..
|<- 1. 0x1438a8ea0 (0x285da6dc0:0) [2x256x1280] -0.095398 -0.074036 0.118713 ..
|<- 2. 0x1438a8f10 (0x285da7480:0) [2x256x1] 0.003412 ..
|<- 3. 0x1438a8f80 (0x285da74c0:0) [2x256x1] 1.055664 ..
Emit: (0, 47)
CCV_NNC_GEMM_FORWARD [547]: [2] -> [1] (0)
|-> 1. 0x1438a8ea0 (0x285da6dc0:0) [2x256x1280] -0.095398 -0.074036 0.118713 ..
|-> 2. 0x1438c35b0 (0x285d87e00:0) [1280x1280] -0.015358 0.006359 -0.070374 ..
|<- 1. 0x1438a8ff0 (0x285da7040:0) [2x256x1280] 0.133667 1.254883 -0.314697 ..
CCV_NNC_SCALAR_MUL_FORWARD [548]: [1] -> [1] (0)
|-> 1. 0x1438a8ff0 (0x285da7040:0) [2x256x1280] 0.133667 1.254883 -0.314697 ..
|<- 1. 0x1438a8ff0 (0x285da7040:0) [2x256x1280] 0.010567 0.099182 -0.024872 ..
CCV_NNC_TRANSPOSE_FORWARD [549]: [1] -> [1] (0)
|-> 1. 0x1438e4eb0 (0x285da7040:0) [2x256x8x160] 0.010567 0.099182 -0.024872 ..
|<- 1. 0x1438a9140 (0x285da70c0:0) [2x8x256x160] 0.010567 0.099182 -0.024872 ..
CCV_NNC_GEMM_FORWARD [550]: [2] -> [1] (1)
Wait: (1, 47)
|-> 1. 0x1438a8ea0 (0x285da6dc0:0) [2x256x1280] -0.095398 -0.074036 0.118713 ..
|-> 2. 0x1438c3620 (0x285d87e40:0) [1280x1280] 0.025864 0.021133 0.003876 ..
|<- 1. 0x1438a9060 (0x285da7080:0) [2x256x1280] -2.302734 -0.755371 -2.503906 ..
CCV_NNC_TRANSPOSE_FORWARD [551]: [1] -> [1] (1)
|-> 1. 0x1438e4e40 (0x285da7080:0) [2x256x8x160] -2.302734 -0.755371 -2.503906 ..
|<- 1. 0x1438a90d0 (0x285da7500:0) [2x8x256x160] -2.302734 -0.755371 -2.503906 ..
Emit: (1, 48)
CCV_NNC_GEMM_FORWARD [552]: [2] -> [1] (2)
Wait: (2, 47)
|-> 1. 0x1438a8ea0 (0x285da6dc0:0) [2x256x1280] -0.095398 -0.074036 0.118713 ..
|-> 2. 0x1438c3690 (0x285d87e80:0) [1280x1280] 0.038574 -0.058319 -0.039154 ..
|<- 1. 0x1438a91b0 (0x285da7140:0) [2x256x1280] -0.527344 0.304688 -0.289795 ..
CCV_NNC_TRANSPOSE_FORWARD [553]: [1] -> [1] (2)
|-> 1. 0x1438e5000 (0x285da7140:0) [2x256x8x160] -0.527344 0.304688 -0.289795 ..
|<- 1. 0x1438a9290 (0x285da6fc0:0) [2x8x256x160] -0.527344 0.304688 -0.289795 ..
Emit: (2, 49)
CCV_NNC_GEMM_FORWARD [554]: [2] -> [1] (0)
Wait: (0, 48)
|-> 1. 0x1438e4f90 (0x285da70c0:0) [1x256x160] 0.010567 0.099182 -0.024872 ..
|-> 2. 0x1438e4f20 (0x285da7500:0) [1x256x160] -2.302734 -0.755371 -2.503906 ..
|<- 1. 0x1438a9220 (0x285da7540:0) [1x256x256] 4.894531 2.089844 2.791016 ..
CCV_NNC_SOFTMAX_FORWARD [555]: [1] -> [1] (0)
|-> 1. 0x1438e5070 (0x285da7540:0) [256x256] 4.894531 2.089844 2.791016 ..
|<- 1. 0x1438e5070 (0x285da7540:0) [256x256] 0.150513 0.009109 0.018372 ..
CCV_NNC_GEMM_FORWARD [556]: [2] -> [1] (0)
Wait: (0, 49)
|-> 1. 0x1438e5150 (0x285da7540:0) [1x256x256] 0.150513 0.009109 0.018372 ..
|-> 2. 0x1438e50e0 (0x285da6fc0:0) [1x256x160] -0.527344 0.304688 -0.289795 ..
|<- 1. 0x1438e7dd0 (0x285da6dc0:0) [1x256x160] -0.100159 0.029770 -0.032318 ..
CCV_NNC_GEMM_FORWARD [557]: [2] -> [1] (0)
|-> 1. 0x1438e5270 (0x285da70c0:0) [1x256x160] 0.060364 -0.017807 -0.125244 ..
|-> 2. 0x1438e51c0 (0x285da7500:0) [1x256x160] -0.488770 0.827637 -0.550293 ..
|<- 1. 0x1438a9300 (0x285da7580:0) [1x256x256] 3.794922 2.361328 2.544922 ..
CCV_NNC_SOFTMAX_FORWARD [558]: [1] -> [1] (0)
|-> 1. 0x1438e5320 (0x285da7580:0) [256x256] 3.794922 2.361328 2.544922 ..
|<- 1. 0x1438e5320 (0x285da7580:0) [256x256] 0.053955 0.012863 0.015457 ..
CCV_NNC_GEMM_FORWARD [559]: [2] -> [1] (0)
|-> 1. 0x1438e5440 (0x285da7580:0) [1x256x256] 0.053955 0.012863 0.015457 ..
|-> 2. 0x1438e5390 (0x285da6fc0:0) [1x256x160] 1.671875 -0.443359 -0.339600 ..
|<- 1. 0x1438e7e40 (0x285da6dc0:0) [1x256x160] 0.442627 -0.208984 0.044159 ..
CCV_NNC_GEMM_FORWARD [560]: [2] -> [1] (0)
|-> 1. 0x1438e5560 (0x285da70c0:0) [1x256x160] -0.029770 0.065918 -0.002853 ..
|-> 2. 0x1438e54b0 (0x285da7500:0) [1x256x160] -0.056305 0.210815 -0.447021 ..
|<- 1. 0x1438a9370 (0x285da7580:0) [1x256x256] 0.416992 0.937988 1.477539 ..
CCV_NNC_SOFTMAX_FORWARD [561]: [1] -> [1] (0)
|-> 1. 0x1438e5610 (0x285da7580:0) [256x256] 0.416992 0.937988 1.477539 ..
|<- 1. 0x1438e5610 (0x285da7580:0) [256x256] 0.004230 0.007122 0.012215 ..
CCV_NNC_GEMM_FORWARD [562]: [2] -> [1] (0)
|-> 1. 0x1438e5730 (0x285da7580:0) [1x256x256] 0.004230 0.007122 0.012215 ..
|-> 2. 0x1438e5680 (0x285da6fc0:0) [1x256x160] 0.977051 0.479736 -0.059082 ..
|<- 1. 0x1438e7ef0 (0x285da6dc0:0) [1x256x160] 0.174927 0.110413 -0.197388 ..
CCV_NNC_GEMM_FORWARD [563]: [2] -> [1] (0)
|-> 1. 0x1438e5850 (0x285da70c0:0) [1x256x160] 0.001321 -0.062500 -0.055420 ..
|-> 2. 0x1438e57a0 (0x285da7500:0) [1x256x160] -0.796387 1.776367 -1.452148 ..
|<- 1. 0x1438a93e0 (0x285da7580:0) [1x256x256] 4.015625 2.263672 1.491211 ..
CCV_NNC_SOFTMAX_FORWARD [564]: [1] -> [1] (0)
|-> 1. 0x1438e5900 (0x285da7580:0) [256x256] 4.015625 2.263672 1.491211 ..
|<- 1. 0x1438e5900 (0x285da7580:0) [256x256] 0.096619 0.016754 0.007740 ..
CCV_NNC_GEMM_FORWARD [565]: [2] -> [1] (0)
|-> 1. 0x1438e5a20 (0x285da7580:0) [1x256x256] 0.096619 0.016754 0.007740 ..
|-> 2. 0x1438e5970 (0x285da6fc0:0) [1x256x160] -0.647949 0.601562 -0.448486 ..
|<- 1. 0x1438e7fa0 (0x285da6dc0:0) [1x256x160] -0.178589 0.133667 -0.261475 ..
CCV_NNC_GEMM_FORWARD [566]: [2] -> [1] (0)
|-> 1. 0x1438e5b40 (0x285da70c0:0) [1x256x160] 0.036041 -0.091003 -0.021805 ..
|-> 2. 0x1438e5a90 (0x285da7500:0) [1x256x160] 1.529297 -0.785156 -0.509766 ..
|<- 1. 0x1438a9450 (0x285da7580:0) [1x256x256] 1.646484 0.920410 0.490479 ..
CCV_NNC_SOFTMAX_FORWARD [567]: [1] -> [1] (0)
|-> 1. 0x1438e5bf0 (0x285da7580:0) [256x256] 1.646484 0.920410 0.490479 ..
|<- 1. 0x1438e5bf0 (0x285da7580:0) [256x256] 0.013008 0.006290 0.004093 ..
CCV_NNC_GEMM_FORWARD [568]: [2] -> [1] (0)
|-> 1. 0x1438e5d10 (0x285da7580:0) [1x256x256] 0.013008 0.006290 0.004093 ..
|-> 2. 0x1438e5c60 (0x285da6fc0:0) [1x256x160] 0.245117 -0.159668 -0.031799 ..
|<- 1. 0x1438e8050 (0x285da6dc0:0) [1x256x160] 0.120544 0.106873 -0.191162 ..
CCV_NNC_GEMM_FORWARD [569]: [2] -> [1] (0)
|-> 1. 0x1438e5e30 (0x285da70c0:0) [1x256x160] -0.022400 -0.059692 0.108887 ..
|-> 2. 0x1438e5d80 (0x285da7500:0) [1x256x160] 2.158203 -0.620117 -0.736328 ..
|<- 1. 0x1438a94c0 (0x285da7580:0) [1x256x256] 4.046875 2.863281 2.845703 ..
CCV_NNC_SOFTMAX_FORWARD [570]: [1] -> [1] (0)
|-> 1. 0x1438e5ee0 (0x285da7580:0) [256x256] 4.046875 2.863281 2.845703 ..
|<- 1. 0x1438e5ee0 (0x285da7580:0) [256x256] 0.064026 0.019608 0.019257 ..
CCV_NNC_GEMM_FORWARD [571]: [2] -> [1] (0)
|-> 1. 0x1438e6000 (0x285da7580:0) [1x256x256] 0.064026 0.019608 0.019257 ..
|-> 2. 0x1438e5f50 (0x285da6fc0:0) [1x256x160] -0.402588 0.544922 0.652344 ..
|<- 1. 0x1438e8100 (0x285da6dc0:0) [1x256x160] -0.246094 0.122498 0.167969 ..
CCV_NNC_GEMM_FORWARD [572]: [2] -> [1] (0)
|-> 1. 0x1438e6120 (0x285da70c0:0) [1x256x160] -0.048553 0.041901 -0.054443 ..
|-> 2. 0x1438e6070 (0x285da7500:0) [1x256x160] -0.235596 -1.250977 0.411621 ..
|<- 1. 0x1438a9530 (0x285da7580:0) [1x256x256] 2.195312 0.461914 1.040039 ..
CCV_NNC_SOFTMAX_FORWARD [573]: [1] -> [1] (0)
|-> 1. 0x1438e61d0 (0x285da7580:0) [256x256] 2.195312 0.461914 1.040039 ..
|<- 1. 0x1438e61d0 (0x285da7580:0) [256x256] 0.025986 0.004593 0.008186 ..
CCV_NNC_GEMM_FORWARD [574]: [2] -> [1] (0)
|-> 1. 0x1438e62f0 (0x285da7580:0) [1x256x256] 0.025986 0.004593 0.008186 ..
|-> 2. 0x1438e6240 (0x285da6fc0:0) [1x256x160] 0.405029 0.111938 -0.727539 ..
|<- 1. 0x1438e81b0 (0x285da6dc0:0) [1x256x160] 0.085144 0.086792 -0.215942 ..
CCV_NNC_GEMM_FORWARD [575]: [2] -> [1] (0)
|-> 1. 0x1438e6410 (0x285da70c0:0) [1x256x160] -0.049408 -0.056091 0.026978 ..
|-> 2. 0x1438e6360 (0x285da7500:0) [1x256x160] 0.274902 1.085938 0.201660 ..
|<- 1. 0x1438a95a0 (0x285da7580:0) [1x256x256] 0.449463 -0.291992 0.279297 ..
CCV_NNC_SOFTMAX_FORWARD [576]: [1] -> [1] (0)
|-> 1. 0x1438e64c0 (0x285da7580:0) [256x256] 0.449463 -0.291992 0.279297 ..
|<- 1. 0x1438e64c0 (0x285da7580:0) [256x256] 0.007122 0.003393 0.006008 ..
CCV_NNC_GEMM_FORWARD [577]: [2] -> [1] (0)
|-> 1. 0x1438e65e0 (0x285da7580:0) [1x256x256] 0.007122 0.003393 0.006008 ..
|-> 2. 0x1438e6530 (0x285da6fc0:0) [1x256x160] -0.062256 -0.687988 0.006107 ..
|<- 1. 0x1438e8260 (0x285da6dc0:0) [1x256x160] 0.142456 0.228638 0.217896 ..
CCV_NNC_GEMM_FORWARD [578]: [2] -> [1] (0)
|-> 1. 0x1438e6700 (0x285da70c0:0) [1x256x160] 0.006504 0.094727 0.000420 ..
|-> 2. 0x1438e6650 (0x285da7500:0) [1x256x160] -1.830078 -0.961914 -2.369141 ..
|<- 1. 0x1438a9610 (0x285da7580:0) [1x256x256] 3.703125 1.928711 2.630859 ..
CCV_NNC_SOFTMAX_FORWARD [579]: [1] -> [1] (0)
|-> 1. 0x1438e67b0 (0x285da7580:0) [256x256] 3.703125 1.928711 2.630859 ..
|<- 1. 0x1438e67b0 (0x285da7580:0) [256x256] 0.064453 0.010925 0.022049 ..
CCV_NNC_GEMM_FORWARD [580]: [2] -> [1] (0)
|-> 1. 0x1438e68d0 (0x285da7580:0) [1x256x256] 0.064453 0.010925 0.022049 ..
|-> 2. 0x1438e6820 (0x285da6fc0:0) [1x256x160] 0.068298 0.421387 -0.546875 ..
|<- 1. 0x1438e8310 (0x285da6dc0:0) [1x256x160] 0.269287 0.084229 -0.165527 ..
CCV_NNC_GEMM_FORWARD [581]: [2] -> [1] (0)
|-> 1. 0x1438e69f0 (0x285da70c0:0) [1x256x160] 0.027283 -0.056458 -0.107361 ..
|-> 2. 0x1438e6940 (0x285da7500:0) [1x256x160] -0.593750 0.997559 -0.401367 ..
|<- 1. 0x1438a9680 (0x285da7580:0) [1x256x256] 3.335938 2.433594 2.679688 ..
CCV_NNC_SOFTMAX_FORWARD [582]: [1] -> [1] (0)
|-> 1. 0x1438e6aa0 (0x285da7580:0) [256x256] 3.335938 2.433594 2.679688 ..
|<- 1. 0x1438e6aa0 (0x285da7580:0) [256x256] 0.029083 0.011795 0.015083 ..
CCV_NNC_GEMM_FORWARD [583]: [2] -> [1] (0)
|-> 1. 0x1438e6bc0 (0x285da7580:0) [1x256x256] 0.029083 0.011795 0.015083 ..
|-> 2. 0x1438e6b10 (0x285da6fc0:0) [1x256x160] 1.571289 -0.274170 -0.147339 ..
|<- 1. 0x1438e83c0 (0x285da6dc0:0) [1x256x160] 0.405029 -0.203491 0.009926 ..
CCV_NNC_GEMM_FORWARD [584]: [2] -> [1] (0)
|-> 1. 0x1438e6ce0 (0x285da70c0:0) [1x256x160] -0.041870 0.017044 0.002636 ..
|-> 2. 0x1438e6c30 (0x285da7500:0) [1x256x160] 0.144165 0.397949 -0.394287 ..
|<- 1. 0x1438a96f0 (0x285da7580:0) [1x256x256] 0.147827 0.866211 1.292969 ..
CCV_NNC_SOFTMAX_FORWARD [585]: [1] -> [1] (0)
|-> 1. 0x1438e6d90 (0x285da7580:0) [256x256] 0.147827 0.866211 1.292969 ..
|<- 1. 0x1438e6d90 (0x285da7580:0) [256x256] 0.003628 0.007442 0.011406 ..
CCV_NNC_GEMM_FORWARD [586]: [2] -> [1] (0)
|-> 1. 0x1438e6eb0 (0x285da7580:0) [1x256x256] 0.003628 0.007442 0.011406 ..
|-> 2. 0x1438e6e00 (0x285da6fc0:0) [1x256x160] 0.803711 0.322998 0.055878 ..
|<- 1. 0x1438e8470 (0x285da6dc0:0) [1x256x160] 0.079590 -0.215210 -0.254395 ..
CCV_NNC_GEMM_FORWARD [587]: [2] -> [1] (0)
|-> 1. 0x1438e6fd0 (0x285da70c0:0) [1x256x160] -0.017853 -0.044434 -0.070007 ..
|-> 2. 0x1438e6f20 (0x285da7500:0) [1x256x160] -0.208130 1.618164 -0.839355 ..
|<- 1. 0x1438a9760 (0x285da7580:0) [1x256x256] 3.435547 2.369141 2.031250 ..
CCV_NNC_SOFTMAX_FORWARD [588]: [1] -> [1] (0)
|-> 1. 0x1438e7080 (0x285da7580:0) [256x256] 3.435547 2.369141 2.031250 ..
|<- 1. 0x1438e7080 (0x285da7580:0) [256x256] 0.050537 0.017395 0.012405 ..
CCV_NNC_GEMM_FORWARD [589]: [2] -> [1] (0)
|-> 1. 0x1438e71a0 (0x285da7580:0) [1x256x256] 0.050537 0.017395 0.012405 ..
|-> 2. 0x1438e70f0 (0x285da6fc0:0) [1x256x160] -0.221924 0.450928 -0.369873 ..
|<- 1. 0x1438e8520 (0x285da6dc0:0) [1x256x160] -0.151733 -0.010597 -0.077820 ..
CCV_NNC_GEMM_FORWARD [590]: [2] -> [1] (0)
|-> 1. 0x1438e72c0 (0x285da70c0:0) [1x256x160] 0.013718 -0.084595 -0.019669 ..
|-> 2. 0x1438e7210 (0x285da7500:0) [1x256x160] 1.333984 -0.531250 -0.787109 ..
|<- 1. 0x1438a97d0 (0x285da7580:0) [1x256x256] 1.380859 0.741211 0.596680 ..
CCV_NNC_SOFTMAX_FORWARD [591]: [1] -> [1] (0)
|-> 1. 0x1438e7370 (0x285da7580:0) [256x256] 1.380859 0.741211 0.596680 ..
|<- 1. 0x1438e7370 (0x285da7580:0) [256x256] 0.011063 0.005833 0.005051 ..
CCV_NNC_GEMM_FORWARD [592]: [2] -> [1] (0)
|-> 1. 0x1438e7490 (0x285da7580:0) [1x256x256] 0.011063 0.005833 0.005051 ..
|-> 2. 0x1438e73e0 (0x285da6fc0:0) [1x256x160] 0.061432 0.197632 0.123413 ..
|<- 1. 0x1438e85d0 (0x285da6dc0:0) [1x256x160] -0.003710 0.210205 -0.161499 ..
CCV_NNC_GEMM_FORWARD [593]: [2] -> [1] (0)
|-> 1. 0x1438e75b0 (0x285da70c0:0) [1x256x160] -0.015137 -0.041901 0.080566 ..
|-> 2. 0x1438e7500 (0x285da7500:0) [1x256x160] 1.485352 -0.556152 -0.729004 ..
|<- 1. 0x1438a9840 (0x285da7580:0) [1x256x256] 3.076172 2.332031 2.509766 ..
CCV_NNC_SOFTMAX_FORWARD [594]: [1] -> [1] (0)
|-> 1. 0x1438e7660 (0x285da7580:0) [256x256] 3.076172 2.332031 2.509766 ..
|<- 1. 0x1438e7660 (0x285da7580:0) [256x256] 0.037445 0.017792 0.021240 ..
CCV_NNC_GEMM_FORWARD [595]: [2] -> [1] (0)
|-> 1. 0x1438e7780 (0x285da7580:0) [1x256x256] 0.037445 0.017792 0.021240 ..
|-> 2. 0x1438e76d0 (0x285da6fc0:0) [1x256x160] -0.040405 0.395996 0.506348 ..
|<- 1. 0x1438e8680 (0x285da6dc0:0) [1x256x160] 0.000468 0.043640 -0.069946 ..
CCV_NNC_GEMM_FORWARD [596]: [2] -> [1] (0)
|-> 1. 0x1438e78a0 (0x285da70c0:0) [1x256x160] -0.033600 0.044037 -0.009346 ..
|-> 2. 0x1438e77f0 (0x285da7500:0) [1x256x160] -0.108948 -1.175781 0.637207 ..
|<- 1. 0x1438a98b0 (0x285da7580:0) [1x256x256] 1.259766 0.194092 0.427246 ..
CCV_NNC_SOFTMAX_FORWARD [597]: [1] -> [1] (0)
|-> 1. 0x1438e7950 (0x285da7580:0) [256x256] 1.259766 0.194092 0.427246 ..
|<- 1. 0x1438e7950 (0x285da7580:0) [256x256] 0.014397 0.004959 0.006260 ..
CCV_NNC_GEMM_FORWARD [598]: [2] -> [1] (0)
|-> 1. 0x1438e7a70 (0x285da7580:0) [1x256x256] 0.014397 0.004959 0.006260 ..
|-> 2. 0x1438e79c0 (0x285da6fc0:0) [1x256x160] 0.186890 -0.200806 -0.648438 ..
|<- 1. 0x1438e8730 (0x285da6dc0:0) [1x256x160] 0.004116 -0.114197 -0.297119 ..
CCV_NNC_GEMM_FORWARD [599]: [2] -> [1] (0)
|-> 1. 0x1438e7b90 (0x285da70c0:0) [1x256x160] -0.020721 -0.068787 0.010681 ..
|-> 2. 0x1438e7ae0 (0x285da7500:0) [1x256x160] 0.197998 0.843262 0.037109 ..
|<- 1. 0x1438a9920 (0x285da7580:0) [1x256x256] 0.241943 -0.459473 0.271729 ..
CCV_NNC_SOFTMAX_FORWARD [600]: [1] -> [1] (0)
|-> 1. 0x1438e7c40 (0x285da7580:0) [256x256] 0.241943 -0.459473 0.271729 ..
|<- 1. 0x1438e7c40 (0x285da7580:0) [256x256] 0.005272 0.002615 0.005432 ..
CCV_NNC_GEMM_FORWARD [601]: [2] -> [1] (0)
|-> 1. 0x1438e7d60 (0x285da7580:0) [1x256x256] 0.005272 0.002615 0.005432 ..
|-> 2. 0x1438e7cb0 (0x285da6fc0:0) [1x256x160] -0.120789 -0.682129 0.342041 ..
|<- 1. 0x1438e87e0 (0x285da6dc0:0) [1x256x160] -0.112000 0.312012 0.225830 ..
CCV_NNC_TRANSPOSE_FORWARD [602]: [1] -> [1] (0)
|-> 1. 0x1438e8890 (0x285da6dc0:0) [2x8x256x160] -0.100159 0.029770 -0.032318 ..
|<- 1. 0x1438a9a00 (0x285da6fc0:0) [2x256x8x160] -0.100159 0.029770 -0.032318 ..
CCV_NNC_GEMM_FORWARD [603]: [3] -> [1] (0)
|-> 1. 0x1438e8900 (0x285da6fc0:0) [2x256x1280] -0.100159 0.029770 -0.032318 ..
|-> 2. 0x1438c3700 (0x285d87ec0:0) [1280x1280] -0.012550 0.027084 -0.008194 ..
|-> 3. 0x1438c3770 (0x285d87f00:0) [1280] -0.020645 -0.020111 0.022873 ..
|<- 1. 0x1438a9a70 (0x285da6dc0:0) [2x256x1280] -0.150757 -0.070435 0.160278 ..
CCV_NNC_ADD_FORWARD [604]: [2] -> [1] (0)
|-> 1. 0x1438a9a70 (0x285da6dc0:0) [2x256x1280] -0.150757 -0.070435 0.160278 ..
|-> 2. 0x1438e4dd0 (0x285da6e00:0) [2x256x1280] -0.364502 -0.283447 0.436768 ..
|<- 1. 0x1438a9a70 (0x285da6dc0:0) [2x256x1280] -0.515137 -0.354004 0.597168 ..
CCV_NNC_LAYER_NORM_FORWARD [605]: [3] -> [3] (0)
|-> 1. 0x1438a9a70 (0x285da6dc0:0) [2x256x1280] -0.515137 -0.354004 0.597168 ..
|-> 2. 0x1438c37e0 (0x285d87f40:0) [1x1x1280] 0.366943 0.374268 0.404053 ..
|-> 3. 0x1438c3850 (0x285d87f80:0) [1x1x1280] 0.053497 0.086670 0.045715 ..
|<- 1. 0x1438a9ae0 (0x285da6e00:0) [2x256x1280] -0.168701 -0.067566 0.340820 ..
|<- 2. 0x1438a9b50 (0x285da75c0:0) [2x256x1] -0.010880 ..
|<- 3. 0x1438a9bc0 (0x285da7600:0) [2x256x1] 1.201172 ..
CCV_NNC_GEMM_FORWARD [606]: [2] -> [1] (0)
|-> 1. 0x1438a9ae0 (0x285da6e00:0) [2x256x1280] -0.168701 -0.067566 0.340820 ..
|-> 2. 0x1438c38c0 (0x285d87fc0:0) [1280x1280] -0.109070 -0.095642 0.015358 ..
|<- 1. 0x1438a9c30 (0x285da6fc0:0) [2x256x1280] -0.723145 0.180664 -1.426758 ..
CCV_NNC_SCALAR_MUL_FORWARD [607]: [1] -> [1] (0)
|-> 1. 0x1438a9c30 (0x285da6fc0:0) [2x256x1280] -0.723145 0.180664 -1.426758 ..
|<- 1. 0x1438a9c30 (0x285da6fc0:0) [2x256x1280] -0.057159 0.014282 -0.112793 ..
CCV_NNC_TRANSPOSE_FORWARD [608]: [1] -> [1] (0)
|-> 1. 0x1438e89e0 (0x285da6fc0:0) [2x256x8x160] -0.057159 0.014282 -0.112793 ..
|<- 1. 0x1438a9d80 (0x285da6e00:0) [2x8x256x160] -0.057159 0.014282 -0.112793 ..
CCV_NNC_GEMM_FORWARD [609]: [2] -> [1] (0)
Wait: (0, 50)
|-> 1. 0x1438a9d80 (0x285da6e00:0) [2x8x256x160] -0.057159 0.014282 -0.112793 ..
|-> 2. 0x1438a9d10 (0x285da7680:0) [2x8x133x160] 0.191650 0.108704 -0.219238 ..
|<- 1. 0x1438a9df0 (0x285da76c0:0) [2x8x256x133] 5.523438 -2.220703 1.056641 ..
CCV_NNC_SOFTMAX_FORWARD [610]: [1] -> [1] (0)
|-> 1. 0x1438e8a50 (0x285da76c0:0) [4096x133] 5.523438 -2.220703 1.056641 ..
|<- 1. 0x1438e8a50 (0x285da76c0:0) [4096x133] 0.313232 0.000136 0.003597 ..
CCV_NNC_GEMM_FORWARD [611]: [2] -> [1] (0)
Wait: (0, 51)
|-> 1. 0x1438e8b30 (0x285da76c0:0) [2x8x256x133] 0.313232 0.000136 0.003597 ..
|-> 2. 0x1438a9ed0 (0x285da7740:0) [2x8x133x160] -0.091675 0.026260 0.035645 ..
|<- 1. 0x1438a9f40 (0x285da6e00:0) [2x8x256x160] -0.397217 -0.514160 -0.087708 ..
CCV_NNC_TRANSPOSE_FORWARD [612]: [1] -> [1] (0)
|-> 1. 0x1438e8ba0 (0x285da6e00:0) [2x8x256x160] -0.397217 -0.514160 -0.087708 ..
|<- 1. 0x1438a9fb0 (0x285da6fc0:0) [2x256x8x160] -0.397217 -0.514160 -0.087708 ..
CCV_NNC_GEMM_FORWARD [613]: [3] -> [1] (0)
|-> 1. 0x1438e8c10 (0x285da6fc0:0) [2x256x1280] -0.397217 -0.514160 -0.087708 ..
|-> 2. 0x1438c3a10 (0x285d8e040:0) [1280x1280] 0.031433 -0.050446 -0.028473 ..
|-> 3. 0x1438c3a80 (0x285d8ca80:0) [1280] -0.027130 -0.031281 0.020508 ..
|<- 1. 0x1438aa020 (0x285da7780:0) [2x256x1280] -0.458984 0.142212 -0.198608 ..
CCV_NNC_ADD_FORWARD [614]: [2] -> [1] (0)
|-> 1. 0x1438aa020 (0x285da7780:0) [2x256x1280] -0.458984 0.142212 -0.198608 ..
|-> 2. 0x1438a9a70 (0x285da6dc0:0) [2x256x1280] -0.515137 -0.354004 0.597168 ..
|<- 1. 0x1438aa020 (0x285da7780:0) [2x256x1280] -0.974121 -0.211792 0.398438 ..
CCV_NNC_LAYER_NORM_FORWARD [615]: [3] -> [3] (0)
|-> 1. 0x1438aa020 (0x285da7780:0) [2x256x1280] -0.974121 -0.211792 0.398438 ..
|-> 2. 0x1438c3af0 (0x285d8ca40:0) [1x1x1280] 0.270264 0.272949 0.266113 ..
|-> 3. 0x1438c3b60 (0x285d894c0:0) [1x1x1280] 0.040833 0.036346 -0.000885 ..
|<- 1. 0x1438aa090 (0x285da77c0:0) [2x256x1280] -0.247681 -0.026260 0.116638 ..
|<- 2. 0x1438aa100 (0x285da7800:0) [2x256x1] -0.003222 ..
|<- 3. 0x1438aa170 (0x285da7840:0) [2x256x1] 1.099609 ..
Emit: (0, 52)
CCV_NNC_GEMM_FORWARD [616]: [3] -> [1] (0)
|-> 1. 0x1438aa090 (0x285da77c0:0) [2x256x1280] -0.247681 -0.026260 0.116638 ..
|-> 2. 0x1438c3bd0 (0x285d8b3c0:0) [5120x1280] 0.022415 0.104980 0.020538 ..
|-> 3. 0x1438c3c40 (0x285d8b5c0:0) [5120] -0.012016 -0.047729 -0.024719 ..
|<- 1. 0x1438aa1e0 (0x285da7380:0) [2x256x5120] 0.011574 0.051270 -0.283203 ..
CCV_NNC_GELU_FORWARD [617]: [1] -> [1] (0)
|-> 1. 0x1438aa1e0 (0x285da7380:0) [2x256x5120] 0.011574 0.051270 -0.283203 ..
|<- 1. 0x1438aa1e0 (0x285da7380:0) [2x256x5120] 0.005840 0.026688 -0.110046 ..
CCV_NNC_GEMM_FORWARD [618]: [3] -> [1] (1)
Wait: (1, 52)
|-> 1. 0x1438aa090 (0x285da77c0:0) [2x256x1280] -0.247681 -0.026260 0.116638 ..
|-> 2. 0x1438c3cb0 (0x285d8aac0:0) [5120x1280] -0.012741 -0.106445 0.001978 ..
|-> 3. 0x1438c3d20 (0x285d8b9c0:0) [5120] -0.004272 0.021820 0.003801 ..
|<- 1. 0x1438aa250 (0x285da5ac0:0) [2x256x5120] -0.095154 0.661133 0.175903 ..
Emit: (1, 53)
CCV_NNC_MUL_FORWARD [619]: [2] -> [1] (0)
Wait: (0, 53)
|-> 1. 0x1438aa250 (0x285da5ac0:0) [2x256x5120] -0.095154 0.661133 0.175903 ..
|-> 2. 0x1438aa1e0 (0x285da7380:0) [2x256x5120] 0.005840 0.026688 -0.110046 ..
|<- 1. 0x1438aa250 (0x285da5ac0:0) [2x256x5120] -0.000556 0.017639 -0.019363 ..
CCV_NNC_GEMM_FORWARD [620]: [3] -> [1] (0)
|-> 1. 0x1438aa250 (0x285da5ac0:0) [2x256x5120] -0.000556 0.017639 -0.019363 ..
|-> 2. 0x1438c3d90 (0x285d896c0:0) [1280x5120] -0.018845 -0.054626 0.055389 ..
|-> 3. 0x1438c3e00 (0x285d8b900:0) [1280] 0.008690 -0.017319 0.016159 ..
|<- 1. 0x1438aa2c0 (0x285da6dc0:0) [2x256x1280] 0.151489 0.550293 0.319824 ..
CCV_NNC_ADD_FORWARD [621]: [2] -> [1] (0)
|-> 1. 0x1438aa2c0 (0x285da6dc0:0) [2x256x1280] 0.151489 0.550293 0.319824 ..
|-> 2. 0x1438aa020 (0x285da7780:0) [2x256x1280] -0.974121 -0.211792 0.398438 ..
|<- 1. 0x1438aa2c0 (0x285da6dc0:0) [2x256x1280] -0.822754 0.338379 0.718262 ..
CCV_NNC_CONVOLUTION_FORWARD [622]: [3] -> [1] (0)
|-> 1. 0x1438e8c80 (0x285da6dc0:0) [2x16x16x1280] -0.822754 0.338379 0.718262 ..
|-> 2. 0x1438c3e70 (0x285d8a880:0) [1280x1280x1x1] 0.033752 ..
|-> 3. 0x1438c3ee0 (0x285d8a7c0:0) [1280] -0.081055 0.000585 0.003956 ..
|<- 1. 0x1438aa330 (0x285da6fc0:0) [2x16x16x1280] -2.039062 -2.007812 2.421875 ..
CCV_NNC_ADD_FORWARD [623]: [2] -> [1] (0)
|-> 1. 0x1438aa330 (0x285da6fc0:0) [2x16x16x1280] -2.039062 -2.007812 2.421875 ..
|-> 2. 0x1438a8c70 (0x285da6f00:0) [2x16x16x1280] 1.439453 1.792969 -2.570312 ..
|<- 1. 0x1438ed3f0 (0x285da61c0:0) [2x16x16x1280] -0.599609 -0.214844 -0.148438 ..
CCV_NNC_CONVOLUTION_FORWARD [624]: [3] -> [1] (0)
|-> 1. 0x1438ed3f0 (0x285da61c0:0) [2x16x16x1280] -0.599609 -0.214844 -0.148438 ..
|-> 2. 0x1438c3f50 (0x285d89d00:0) [1280x1280x3x3] -0.013542 -0.019775 -0.012993 ..
|-> 3. 0x1438c3fc0 (0x285d8a6c0:0) [1280] -0.010803 -0.018738 -0.024414 ..
|<- 1. 0x1438ed220 (0x285d83dc0:0) [2x8x8x1280] -0.415771 -0.962891 1.918945 ..
CCV_NNC_GROUP_NORM_FORWARD [625]: [3] -> [3] (0)
|-> 1. 0x1438ed220 (0x285d83dc0:0) [2x8x8x1280] -0.415771 -0.962891 1.918945 ..
|-> 2. 0x1438c4030 (0x285d89dc0:0) [1x1x1x1280] 0.356445 0.575195 0.341064 ..
|-> 3. 0x1438c40a0 (0x285d89b40:0) [1x1x1x1280] -0.049286 -0.172241 -0.042419 ..
|<- 1. 0x1438aa3a0 (0x285da7880:0) [2x8x8x1280] -0.102966 -0.444580 0.375977 ..
|<- 2. 0x1438aa410 (0x285da78c0:0) [2x1x1x32] -0.160400 -0.602539 -0.460938 ..
|<- 3. 0x1438aa480 (0x285da7900:0) [2x1x1x32] 0.589844 0.599121 0.614746 ..
CCV_NNC_SWISH_FORWARD [626]: [1] -> [1] (0)
|-> 1. 0x1438aa3a0 (0x285da7880:0) [2x8x8x1280] -0.102966 -0.444580 0.375977 ..
|<- 1. 0x1438aa3a0 (0x285da7880:0) [2x8x8x1280] -0.048828 -0.173706 0.222900 ..
CCV_NNC_CONVOLUTION_FORWARD [627]: [3] -> [1] (0)
|-> 1. 0x1438aa3a0 (0x285da7880:0) [2x8x8x1280] -0.048828 -0.173706 0.222900 ..
|-> 2. 0x1438c41f0 (0x285d8adc0:0) [1280x1280x3x3] -0.041321 -0.024048 -0.009758 ..
|-> 3. 0x1438c4260 (0x285d8ad00:0) [1280] 0.068237 -0.042267 -0.026306 ..
|<- 1. 0x1438aa560 (0x285da7980:0) [2x8x8x1280] 0.378662 -0.772949 1.360352 ..
CCV_NNC_ADD_FORWARD [628]: [2] -> [1] (0)
Wait: (0, 54)
|-> 1. 0x1438aa560 (0x285da7980:0) [2x8x8x1280] 0.378662 -0.772949 1.360352 ..
|-> 2. 0x1438e8cf0 (0x285da7940:0) [2x1x1x1280] 0.770020 0.276611 0.438477 ..
|<- 1. 0x1438aa560 (0x285da7980:0) [2x8x8x1280] 1.148438 -0.496338 1.798828 ..
CCV_NNC_GROUP_NORM_FORWARD [629]: [3] -> [3] (0)
|-> 1. 0x1438aa560 (0x285da7980:0) [2x8x8x1280] 1.148438 -0.496338 1.798828 ..
|-> 2. 0x1438c42d0 (0x285d8b040:0) [1x1x1x1280] 0.588379 0.901367 0.817383 ..
|-> 3. 0x1438c4340 (0x285d8af80:0) [1x1x1x1280] -0.204224 -0.406982 -0.299072 ..
|<- 1. 0x1438aa5d0 (0x285da7880:0) [2x8x8x1280] 0.072388 -1.202148 0.522461 ..
|<- 2. 0x1438aa640 (0x285da79c0:0) [2x1x1x32] 0.576660 0.451416 0.241577 ..
|<- 3. 0x1438aa6b0 (0x285da7a00:0) [2x1x1x32] 0.822266 1.111328 0.558105 ..
CCV_NNC_SWISH_FORWARD [630]: [1] -> [1] (0)
|-> 1. 0x1438aa5d0 (0x285da7880:0) [2x8x8x1280] 0.072388 -1.202148 0.522461 ..
|<- 1. 0x1438aa5d0 (0x285da7880:0) [2x8x8x1280] 0.037506 -0.277832 0.327881 ..
CCV_NNC_CONVOLUTION_FORWARD [631]: [3] -> [1] (0)
|-> 1. 0x1438aa5d0 (0x285da7880:0) [2x8x8x1280] 0.037506 -0.277832 0.327881 ..
|-> 2. 0x1438c43b0 (0x285d8a740:0) [1280x1280x3x3] -0.007942 -0.025864 -0.020462 ..
|-> 3. 0x1438c4420 (0x285df7900:0) [1280] 0.032349 0.049072 0.003355 ..
|<- 1. 0x1438aa720 (0x285da7a40:0) [2x8x8x1280] -0.593750 0.087769 -0.660156 ..
CCV_NNC_ADD_FORWARD [632]: [2] -> [1] (0)
|-> 1. 0x1438ed220 (0x285d83dc0:0) [2x8x8x1280] -0.415771 -0.962891 1.918945 ..
|-> 2. 0x1438aa720 (0x285da7a40:0) [2x8x8x1280] -0.593750 0.087769 -0.660156 ..
|<- 1. 0x1438ed050 (0x285d81340:0) [2x8x8x1280] -1.009766 -0.875000 1.258789 ..
CCV_NNC_GROUP_NORM_FORWARD [633]: [3] -> [3] (0)
|-> 1. 0x1438ed050 (0x285d81340:0) [2x8x8x1280] -1.009766 -0.875000 1.258789 ..
|-> 2. 0x1438c4490 (0x285df6980:0) [1x1x1x1280] 0.375000 0.524902 0.364502 ..
|-> 3. 0x1438c4500 (0x285df5540:0) [1x1x1x1280] -0.052826 -0.081726 -0.053253 ..
|<- 1. 0x1438aa790 (0x285da7a40:0) [2x8x8x1280] -0.244141 -0.308594 0.238037 ..
|<- 2. 0x1438aa800 (0x285da67c0:0) [2x1x1x32] -0.125854 -0.469971 -0.328613 ..
|<- 3. 0x1438aa870 (0x285da6800:0) [2x1x1x32] 0.577148 0.594727 0.626953 ..
CCV_NNC_SWISH_FORWARD [634]: [1] -> [1] (0)
|-> 1. 0x1438aa790 (0x285da7a40:0) [2x8x8x1280] -0.244141 -0.308594 0.238037 ..
|<- 1. 0x1438aa790 (0x285da7a40:0) [2x8x8x1280] -0.107239 -0.130737 0.133057 ..
CCV_NNC_CONVOLUTION_FORWARD [635]: [3] -> [1] (0)
|-> 1. 0x1438aa790 (0x285da7a40:0) [2x8x8x1280] -0.107239 -0.130737 0.133057 ..
|-> 2. 0x1438c4650 (0x285df5440:0) [1280x1280x3x3] -0.037018 -0.017319 -0.041565 ..
|-> 3. 0x1438c46c0 (0x285df6d40:0) [1280] -0.069641 0.033020 0.103821 ..
|<- 1. 0x1438aa950 (0x285da7ac0:0) [2x8x8x1280] -0.646973 0.340088 0.199463 ..
CCV_NNC_ADD_FORWARD [636]: [2] -> [1] (0)
Wait: (0, 55)
|-> 1. 0x1438aa950 (0x285da7ac0:0) [2x8x8x1280] -0.646973 0.340088 0.199463 ..
|-> 2. 0x1438e8d60 (0x285da7a80:0) [2x1x1x1280] -0.554199 0.637207 0.615234 ..
|<- 1. 0x1438aa950 (0x285da7ac0:0) [2x8x8x1280] -1.201172 0.977539 0.814453 ..
CCV_NNC_GROUP_NORM_FORWARD [637]: [3] -> [3] (0)
|-> 1. 0x1438aa950 (0x285da7ac0:0) [2x8x8x1280] -1.201172 0.977539 0.814453 ..
|-> 2. 0x1438c4730 (0x285df68c0:0) [1x1x1x1280] 1.188477 0.872559 0.577637 ..
|-> 3. 0x1438c47a0 (0x285df5640:0) [1x1x1x1280] -0.458496 -0.503418 -0.258057 ..
|<- 1. 0x1438aa9c0 (0x285da7a40:0) [2x8x8x1280] -2.001953 -0.152344 -0.099182 ..
|<- 2. 0x1438aaa30 (0x285da7400:0) [2x1x1x32] 0.462158 0.926270 0.564453 ..
|<- 3. 0x1438aaaa0 (0x285da73c0:0) [2x1x1x32] 0.780762 0.915039 0.851074 ..
CCV_NNC_SWISH_FORWARD [638]: [1] -> [1] (0)
|-> 1. 0x1438aa9c0 (0x285da7a40:0) [2x8x8x1280] -2.001953 -0.152344 -0.099182 ..
|<- 1. 0x1438aa9c0 (0x285da7a40:0) [2x8x8x1280] -0.238281 -0.070374 -0.047119 ..
CCV_NNC_CONVOLUTION_FORWARD [639]: [3] -> [1] (0)
|-> 1. 0x1438aa9c0 (0x285da7a40:0) [2x8x8x1280] -0.238281 -0.070374 -0.047119 ..
|-> 2. 0x1438c4810 (0x285dfcc40:0) [1280x1280x3x3] -0.015480 0.022446 0.044220 ..
|-> 3. 0x1438c4880 (0x285dfe440:0) [1280] 0.082153 -0.000108 0.050964 ..
|<- 1. 0x1438aab10 (0x285da7b00:0) [2x8x8x1280] 0.281006 -0.273682 0.623047 ..
CCV_NNC_ADD_FORWARD [640]: [2] -> [1] (0)
|-> 1. 0x1438ed050 (0x285d81340:0) [2x8x8x1280] -1.009766 -0.875000 1.258789 ..
|-> 2. 0x1438aab10 (0x285da7b00:0) [2x8x8x1280] 0.281006 -0.273682 0.623047 ..
|<- 1. 0x1438ece80 (0x285d81380:0) [2x8x8x1280] -0.728516 -1.148438 1.881836 ..
CCV_NNC_GROUP_NORM_FORWARD [641]: [3] -> [3] (0)
|-> 1. 0x1438ece80 (0x285d81380:0) [2x8x8x1280] -0.728516 -1.148438 1.881836 ..
|-> 2. 0x1438c48f0 (0x285dfef40:0) [1x1x1x1280] 0.395996 0.522461 0.387939 ..
|-> 3. 0x1438c4960 (0x285dfe480:0) [1x1x1x1280] -0.032867 -0.152466 -0.053741 ..
|<- 1. 0x1438aab80 (0x285da7b00:0) [2x8x8x1280] -0.187622 -0.470459 0.320312 ..
|<- 2. 0x1438aabf0 (0x285da7b40:0) [2x1x1x32] 0.024628 -0.541504 -0.468750 ..
|<- 3. 0x1438aac60 (0x285da7b80:0) [2x1x1x32] 0.519043 0.539062 0.569824 ..
CCV_NNC_SWISH_FORWARD [642]: [1] -> [1] (0)
|-> 1. 0x1438aab80 (0x285da7b00:0) [2x8x8x1280] -0.187622 -0.470459 0.320312 ..
|<- 1. 0x1438aab80 (0x285da7b00:0) [2x8x8x1280] -0.085022 -0.180908 0.185547 ..
CCV_NNC_CONVOLUTION_FORWARD [643]: [3] -> [1] (0)
|-> 1. 0x1438aab80 (0x285da7b00:0) [2x8x8x1280] -0.085022 -0.180908 0.185547 ..
|-> 2. 0x1438c4ab0 (0x285e6d8c0:0) [1280x1280x3x3] 0.019470 0.036560 0.024933 ..
|-> 3. 0x1438c4b20 (0x285e6da00:0) [1280] 0.072510 0.083374 -0.002544 ..
|<- 1. 0x1438aad40 (0x285da7c00:0) [2x8x8x1280] 1.964844 1.085938 1.739258 ..
CCV_NNC_ADD_FORWARD [644]: [2] -> [1] (0)
Wait: (0, 56)
|-> 1. 0x1438aad40 (0x285da7c00:0) [2x8x8x1280] 1.964844 1.085938 1.739258 ..
|-> 2. 0x1438e8dd0 (0x285da7bc0:0) [2x1x1x1280] 0.581543 1.150391 0.077393 ..
|<- 1. 0x1438aad40 (0x285da7c00:0) [2x8x8x1280] 2.546875 2.236328 1.816406 ..
CCV_NNC_GROUP_NORM_FORWARD [645]: [3] -> [3] (0)
|-> 1. 0x1438aad40 (0x285da7c00:0) [2x8x8x1280] 2.546875 2.236328 1.816406 ..
|-> 2. 0x1438c4b90 (0x285e6d980:0) [1x1x1x1280] 0.350830 0.572266 0.883789 ..
|-> 3. 0x1438c4c00 (0x285e6d740:0) [1x1x1x1280] -0.258301 -0.269287 -0.452881 ..
|<- 1. 0x1438aadb0 (0x285da7b00:0) [2x8x8x1280] 0.063660 0.144531 -0.046509 ..
|<- 2. 0x1438aae20 (0x285da6880:0) [2x1x1x32] 1.083008 0.687988 0.489258 ..
|<- 3. 0x1438aae90 (0x285da68c0:0) [2x1x1x32] 0.626953 0.719238 0.718750 ..
CCV_NNC_SWISH_FORWARD [646]: [1] -> [1] (0)
|-> 1. 0x1438aadb0 (0x285da7b00:0) [2x8x8x1280] 0.063660 0.144531 -0.046509 ..
|<- 1. 0x1438aadb0 (0x285da7b00:0) [2x8x8x1280] 0.032837 0.077454 -0.022720 ..
CCV_NNC_CONVOLUTION_FORWARD [647]: [3] -> [1] (0)
|-> 1. 0x1438aadb0 (0x285da7b00:0) [2x8x8x1280] 0.032837 0.077454 -0.022720 ..
|-> 2. 0x1438c4c70 (0x285e6a4c0:0) [1280x1280x3x3] 0.009064 -0.005798 0.006561 ..
|-> 3. 0x1438c4ce0 (0x285e69a40:0) [1280] 0.033661 0.001286 0.012787 ..
|<- 1. 0x1438aaf00 (0x285da7c40:0) [2x8x8x1280] -0.475586 1.485352 0.928711 ..
CCV_NNC_ADD_FORWARD [648]: [2] -> [1] (0)
|-> 1. 0x1438ece80 (0x285d81380:0) [2x8x8x1280] -0.728516 -1.148438 1.881836 ..
|-> 2. 0x1438aaf00 (0x285da7c40:0) [2x8x8x1280] -0.475586 1.485352 0.928711 ..
|<- 1. 0x1438aaf70 (0x285da7c00:0) [2x8x8x1280] -1.204102 0.336914 2.810547 ..
CCV_NNC_GROUP_NORM_FORWARD [649]: [3] -> [3] (0)
|-> 1. 0x1438aaf70 (0x285da7c00:0) [2x8x8x1280] -1.204102 0.336914 2.810547 ..
|-> 2. 0x1438c4d50 (0x285e69f40:0) [1x1x1x1280] 0.379883 0.236816 0.363037 ..
|-> 3. 0x1438c4dc0 (0x285e6a200:0) [1x1x1x1280] -0.019196 -0.055298 -0.023285 ..
|<- 1. 0x1438aafe0 (0x285da7c40:0) [2x8x8x1280] -0.208252 -0.025070 0.387451 ..
|<- 2. 0x1438ab050 (0x285da73c0:0) [2x1x1x32] 0.022263 -0.726074 -0.319092 ..
|<- 3. 0x1438ab0c0 (0x285da7400:0) [2x1x1x32] 0.405762 0.396484 0.438232 ..
CCV_NNC_CONVOLUTION_FORWARD [650]: [3] -> [1] (0)
|-> 1. 0x1438aafe0 (0x285da7c40:0) [2x8x8x1280] -0.208252 -0.025070 0.387451 ..
|-> 2. 0x1438c4e30 (0x285e69980:0) [1280x1280x1x1] 0.035675 ..
|-> 3. 0x1438c4ea0 (0x285e69b40:0) [1280] 0.062561 -0.012909 0.075867 ..
|<- 1. 0x1438ab130 (0x285da7b00:0) [2x8x8x1280] 0.255371 -2.494141 0.954590 ..
CCV_NNC_LAYER_NORM_FORWARD [651]: [3] -> [3] (0)
|-> 1. 0x1438e8e40 (0x285da7b00:0) [2x64x1280] 0.255371 -2.494141 0.954590 ..
|-> 2. 0x1438c4f10 (0x285e69900:0) [1x1x1280] 0.276611 0.290771 0.278564 ..
|-> 3. 0x1438c4f80 (0x285e69c40:0) [1x1x1280] 0.014793 -0.018753 0.015091 ..
|<- 1. 0x1438ab1a0 (0x285da7c40:0) [2x64x1280] 0.080811 -0.657227 0.253906 ..
|<- 2. 0x1438ab210 (0x285da7c80:0) [2x64x1] -0.014259 ..
|<- 3. 0x1438ab280 (0x285da7cc0:0) [2x64x1] 0.885254 ..
Emit: (0, 57)
CCV_NNC_GEMM_FORWARD [652]: [2] -> [1] (0)
|-> 1. 0x1438ab1a0 (0x285da7c40:0) [2x64x1280] 0.080811 -0.657227 0.253906 ..
|-> 2. 0x1438c4ff0 (0x285e69b80:0) [1280x1280] 0.006420 0.047607 -0.014336 ..
|<- 1. 0x1438ab2f0 (0x285da7d00:0) [2x64x1280] -1.171875 -0.037689 0.780762 ..
CCV_NNC_SCALAR_MUL_FORWARD [653]: [1] -> [1] (0)
|-> 1. 0x1438ab2f0 (0x285da7d00:0) [2x64x1280] -1.171875 -0.037689 0.780762 ..
|<- 1. 0x1438ab2f0 (0x285da7d00:0) [2x64x1280] -0.092651 -0.002979 0.061707 ..
CCV_NNC_TRANSPOSE_FORWARD [654]: [1] -> [1] (0)
|-> 1. 0x1438e8f20 (0x285da7d00:0) [2x64x8x160] -0.092651 -0.002979 0.061707 ..
|<- 1. 0x1438ab440 (0x285da7dc0:0) [2x8x64x160] -0.092651 -0.002979 0.061707 ..
CCV_NNC_GEMM_FORWARD [655]: [2] -> [1] (1)
Wait: (1, 57)
|-> 1. 0x1438ab1a0 (0x285da7c40:0) [2x64x1280] 0.080811 -0.657227 0.253906 ..
|-> 2. 0x1438c5060 (0x285e69880:0) [1280x1280] -0.001306 -0.038757 -0.076477 ..
|<- 1. 0x1438ab360 (0x285da7d40:0) [2x64x1280] -1.183594 0.456299 1.410156 ..
CCV_NNC_TRANSPOSE_FORWARD [656]: [1] -> [1] (1)
|-> 1. 0x1438e8eb0 (0x285da7d40:0) [2x64x8x160] -1.183594 0.456299 1.410156 ..
|<- 1. 0x1438ab3d0 (0x285da7d80:0) [2x8x64x160] -1.183594 0.456299 1.410156 ..
Emit: (1, 58)
CCV_NNC_GEMM_FORWARD [657]: [2] -> [1] (2)
Wait: (2, 57)
|-> 1. 0x1438ab1a0 (0x285da7c40:0) [2x64x1280] 0.080811 -0.657227 0.253906 ..
|-> 2. 0x1438c50d0 (0x285e6a340:0) [1280x1280] 0.044281 -0.023407 0.047577 ..
|<- 1. 0x1438ab4b0 (0x285da7e00:0) [2x64x1280] 1.144531 -0.024384 -0.335205 ..
CCV_NNC_TRANSPOSE_FORWARD [658]: [1] -> [1] (2)
|-> 1. 0x1438e9070 (0x285da7e00:0) [2x64x8x160] 1.144531 -0.024384 -0.335205 ..
|<- 1. 0x1438ab590 (0x285da7e80:0) [2x8x64x160] 1.144531 -0.024384 -0.335205 ..
Emit: (2, 59)
CCV_NNC_GEMM_FORWARD [659]: [2] -> [1] (0)
Wait: (0, 58)
|-> 1. 0x1438e9000 (0x285da7dc0:0) [1x64x160] -0.092651 -0.002979 0.061707 ..
|-> 2. 0x1438e8f90 (0x285da7d80:0) [1x64x160] -1.183594 0.456299 1.410156 ..
|<- 1. 0x1438ab520 (0x285da7e40:0) [1x64x64] 4.921875 0.821289 0.454834 ..
CCV_NNC_SOFTMAX_FORWARD [660]: [1] -> [1] (0)
|-> 1. 0x1438e90e0 (0x285da7e40:0) [64x64] 4.921875 0.821289 0.454834 ..
|<- 1. 0x1438e90e0 (0x285da7e40:0) [64x64] 0.506836 0.008400 0.005821 ..
CCV_NNC_GEMM_FORWARD [661]: [2] -> [1] (0)
Wait: (0, 59)
|-> 1. 0x1438e91c0 (0x285da7e40:0) [1x64x64] 0.506836 0.008400 0.005821 ..
|-> 2. 0x1438e9150 (0x285da7e80:0) [1x64x160] 1.144531 -0.024384 -0.335205 ..
|<- 1. 0x1438ebe40 (0x285da7c40:0) [1x64x160] 0.771484 -0.089233 -0.232788 ..
CCV_NNC_GEMM_FORWARD [662]: [2] -> [1] (0)
|-> 1. 0x1438e92e0 (0x285da7dc0:0) [1x64x160] 0.081360 0.004601 -0.015053 ..
|-> 2. 0x1438e9230 (0x285da7d80:0) [1x64x160] 1.039062 0.099976 -0.261475 ..
|<- 1. 0x1438ab600 (0x285da7ec0:0) [1x64x64] 3.675781 0.514160 0.521484 ..
CCV_NNC_SOFTMAX_FORWARD [663]: [1] -> [1] (0)
|-> 1. 0x1438e9390 (0x285da7ec0:0) [64x64] 3.675781 0.514160 0.521484 ..
|<- 1. 0x1438e9390 (0x285da7ec0:0) [64x64] 0.338379 0.014336 0.014435 ..
CCV_NNC_GEMM_FORWARD [664]: [2] -> [1] (0)
|-> 1. 0x1438e94b0 (0x285da7ec0:0) [1x64x64] 0.338379 0.014336 0.014435 ..
|-> 2. 0x1438e9400 (0x285da7e80:0) [1x64x160] -0.206665 -0.201904 -0.258545 ..
|<- 1. 0x1438ebeb0 (0x285da7c40:0) [1x64x160] 0.018921 -0.016174 -0.269775 ..
CCV_NNC_GEMM_FORWARD [665]: [2] -> [1] (0)
|-> 1. 0x1438e95d0 (0x285da7dc0:0) [1x64x160] 0.072449 -0.079407 0.030930 ..
|-> 2. 0x1438e9520 (0x285da7d80:0) [1x64x160] 1.650391 -0.655762 -0.003675 ..
|<- 1. 0x1438ab670 (0x285da7ec0:0) [1x64x64] 4.578125 1.877930 1.080078 ..
CCV_NNC_SOFTMAX_FORWARD [666]: [1] -> [1] (0)
|-> 1. 0x1438e9680 (0x285da7ec0:0) [64x64] 4.578125 1.877930 1.080078 ..
|<- 1. 0x1438e9680 (0x285da7ec0:0) [64x64] 0.360840 0.024246 0.010918 ..
CCV_NNC_GEMM_FORWARD [667]: [2] -> [1] (0)
|-> 1. 0x1438e97a0 (0x285da7ec0:0) [1x64x64] 0.360840 0.024246 0.010918 ..
|-> 2. 0x1438e96f0 (0x285da7e80:0) [1x64x160] -0.455811 0.178223 0.184937 ..
|<- 1. 0x1438ebf60 (0x285da7c40:0) [1x64x160] -0.097351 0.307861 0.192139 ..
CCV_NNC_GEMM_FORWARD [668]: [2] -> [1] (0)
|-> 1. 0x1438e98c0 (0x285da7dc0:0) [1x64x160] -0.048126 -0.034241 0.043182 ..
|-> 2. 0x1438e9810 (0x285da7d80:0) [1x64x160] 0.581543 1.321289 -0.286865 ..
|<- 1. 0x1438ab6e0 (0x285da7ec0:0) [1x64x64] -0.887207 -1.496094 -0.767090 ..
CCV_NNC_SOFTMAX_FORWARD [669]: [1] -> [1] (0)
|-> 1. 0x1438e9970 (0x285da7ec0:0) [64x64] -0.887207 -1.496094 -0.767090 ..
|<- 1. 0x1438e9970 (0x285da7ec0:0) [64x64] 0.009911 0.005390 0.011177 ..
CCV_NNC_GEMM_FORWARD [670]: [2] -> [1] (0)
|-> 1. 0x1438e9a90 (0x285da7ec0:0) [1x64x64] 0.009911 0.005390 0.011177 ..
|-> 2. 0x1438e99e0 (0x285da7e80:0) [1x64x160] 0.303711 -0.302734 0.347656 ..
|<- 1. 0x1438ec010 (0x285da7c40:0) [1x64x160] 0.081970 0.075928 0.277832 ..
CCV_NNC_GEMM_FORWARD [671]: [2] -> [1] (0)
|-> 1. 0x1438e9bb0 (0x285da7dc0:0) [1x64x160] -0.024445 -0.072693 -0.036713 ..
|-> 2. 0x1438e9b00 (0x285da7d80:0) [1x64x160] -0.772949 0.781738 -0.342285 ..
|<- 1. 0x1438ab750 (0x285da7ec0:0) [1x64x64] 0.751465 0.475098 0.604004 ..
CCV_NNC_SOFTMAX_FORWARD [672]: [1] -> [1] (0)
|-> 1. 0x1438e9c60 (0x285da7ec0:0) [64x64] 0.751465 0.475098 0.604004 ..
|<- 1. 0x1438e9c60 (0x285da7ec0:0) [64x64] 0.025665 0.019470 0.022141 ..
CCV_NNC_GEMM_FORWARD [673]: [2] -> [1] (0)
|-> 1. 0x1438e9d80 (0x285da7ec0:0) [1x64x64] 0.025665 0.019470 0.022141 ..
|-> 2. 0x1438e9cd0 (0x285da7e80:0) [1x64x160] -0.056366 0.073425 0.075195 ..
|<- 1. 0x1438ec0c0 (0x285da7c40:0) [1x64x160] 0.008057 -0.040833 0.268799 ..
CCV_NNC_GEMM_FORWARD [674]: [2] -> [1] (0)
|-> 1. 0x1438e9ea0 (0x285da7dc0:0) [1x64x160] -0.022980 -0.043610 0.012459 ..
|-> 2. 0x1438e9df0 (0x285da7d80:0) [1x64x160] 0.731934 0.079407 0.266357 ..
|<- 1. 0x1438ab7c0 (0x285da7ec0:0) [1x64x64] 1.647461 -0.928711 -0.523438 ..
CCV_NNC_SOFTMAX_FORWARD [675]: [1] -> [1] (0)
|-> 1. 0x1438e9f50 (0x285da7ec0:0) [64x64] 1.647461 -0.928711 -0.523438 ..
|<- 1. 0x1438e9f50 (0x285da7ec0:0) [64x64] 0.058563 0.004456 0.006683 ..
CCV_NNC_GEMM_FORWARD [676]: [2] -> [1] (0)
|-> 1. 0x1438ea070 (0x285da7ec0:0) [1x64x64] 0.058563 0.004456 0.006683 ..
|-> 2. 0x1438e9fc0 (0x285da7e80:0) [1x64x160] 0.875000 -0.196045 -0.160156 ..
|<- 1. 0x1438ec170 (0x285da7c40:0) [1x64x160] 0.091797 0.360352 0.125977 ..
CCV_NNC_GEMM_FORWARD [677]: [2] -> [1] (0)
|-> 1. 0x1438ea190 (0x285da7dc0:0) [1x64x160] -0.040161 -0.032867 0.045258 ..
|-> 2. 0x1438ea0e0 (0x285da7d80:0) [1x64x160] -0.117371 0.128906 0.672852 ..
|<- 1. 0x1438ab830 (0x285da7ec0:0) [1x64x64] 2.802734 1.431641 1.070312 ..
CCV_NNC_SOFTMAX_FORWARD [678]: [1] -> [1] (0)
|-> 1. 0x1438ea240 (0x285da7ec0:0) [64x64] 2.802734 1.431641 1.070312 ..
|<- 1. 0x1438ea240 (0x285da7ec0:0) [64x64] 0.110291 0.028000 0.019516 ..
CCV_NNC_GEMM_FORWARD [679]: [2] -> [1] (0)
|-> 1. 0x1438ea360 (0x285da7ec0:0) [1x64x64] 0.110291 0.028000 0.019516 ..
|-> 2. 0x1438ea2b0 (0x285da7e80:0) [1x64x160] -0.589355 0.023788 0.061707 ..
|<- 1. 0x1438ec220 (0x285da7c40:0) [1x64x160] -0.107483 0.216064 0.083618 ..
CCV_NNC_GEMM_FORWARD [680]: [2] -> [1] (0)
|-> 1. 0x1438ea480 (0x285da7dc0:0) [1x64x160] -0.088745 -0.052551 -0.013008 ..
|-> 2. 0x1438ea3d0 (0x285da7d80:0) [1x64x160] -0.155518 0.811035 -1.858398 ..
|<- 1. 0x1438ab8a0 (0x285da7ec0:0) [1x64x64] 2.761719 -0.678711 -0.555664 ..
CCV_NNC_SOFTMAX_FORWARD [681]: [1] -> [1] (0)
|-> 1. 0x1438ea530 (0x285da7ec0:0) [64x64] 2.761719 -0.678711 -0.555664 ..
|<- 1. 0x1438ea530 (0x285da7ec0:0) [64x64] 0.050140 0.001607 0.001818 ..
CCV_NNC_GEMM_FORWARD [682]: [2] -> [1] (0)
|-> 1. 0x1438ea650 (0x285da7ec0:0) [1x64x64] 0.050140 0.001607 0.001818 ..
|-> 2. 0x1438ea5a0 (0x285da7e80:0) [1x64x160] 0.677246 0.502930 0.453857 ..
|<- 1. 0x1438ec2d0 (0x285da7c40:0) [1x64x160] -0.026596 0.497803 0.205811 ..
CCV_NNC_GEMM_FORWARD [683]: [2] -> [1] (0)
|-> 1. 0x1438ea770 (0x285da7dc0:0) [1x64x160] -0.095642 -0.023819 0.034027 ..
|-> 2. 0x1438ea6c0 (0x285da7d80:0) [1x64x160] -1.501953 0.864258 1.346680 ..
|<- 1. 0x1438ab910 (0x285da7ec0:0) [1x64x64] 3.087891 0.597656 0.728516 ..
CCV_NNC_SOFTMAX_FORWARD [684]: [1] -> [1] (0)
|-> 1. 0x1438ea820 (0x285da7ec0:0) [64x64] 3.087891 0.597656 0.728516 ..
|<- 1. 0x1438ea820 (0x285da7ec0:0) [64x64] 0.206421 0.017105 0.019501 ..
CCV_NNC_GEMM_FORWARD [685]: [2] -> [1] (0)
|-> 1. 0x1438ea940 (0x285da7ec0:0) [1x64x64] 0.206421 0.017105 0.019501 ..
|-> 2. 0x1438ea890 (0x285da7e80:0) [1x64x160] 0.483154 -0.067017 0.061371 ..
|<- 1. 0x1438ec380 (0x285da7c40:0) [1x64x160] -0.058441 0.306152 -0.082397 ..
CCV_NNC_GEMM_FORWARD [686]: [2] -> [1] (0)
|-> 1. 0x1438eaa60 (0x285da7dc0:0) [1x64x160] 0.042145 -0.027435 -0.043488 ..
|-> 2. 0x1438ea9b0 (0x285da7d80:0) [1x64x160] 0.061218 0.116150 -0.393066 ..
|<- 1. 0x1438ab980 (0x285da7ec0:0) [1x64x64] 2.402344 0.373291 0.853516 ..
CCV_NNC_SOFTMAX_FORWARD [687]: [1] -> [1] (0)
|-> 1. 0x1438eab10 (0x285da7ec0:0) [64x64] 2.402344 0.373291 0.853516 ..
|<- 1. 0x1438eab10 (0x285da7ec0:0) [64x64] 0.132690 0.017441 0.028198 ..
CCV_NNC_GEMM_FORWARD [688]: [2] -> [1] (0)
|-> 1. 0x1438eac30 (0x285da7ec0:0) [1x64x64] 0.132690 0.017441 0.028198 ..
|-> 2. 0x1438eab80 (0x285da7e80:0) [1x64x160] -0.909180 -0.328613 -0.143311 ..
|<- 1. 0x1438ec430 (0x285da7c40:0) [1x64x160] -0.264893 0.013748 0.014084 ..
CCV_NNC_GEMM_FORWARD [689]: [2] -> [1] (0)
|-> 1. 0x1438ead50 (0x285da7dc0:0) [1x64x160] 0.072205 -0.069946 -0.007549 ..
|-> 2. 0x1438eaca0 (0x285da7d80:0) [1x64x160] 2.128906 -0.741211 -0.130371 ..
|<- 1. 0x1438ab9f0 (0x285da7ec0:0) [1x64x64] 4.015625 1.983398 1.172852 ..
CCV_NNC_SOFTMAX_FORWARD [690]: [1] -> [1] (0)
|-> 1. 0x1438eae00 (0x285da7ec0:0) [64x64] 4.015625 1.983398 1.172852 ..
|<- 1. 0x1438eae00 (0x285da7ec0:0) [64x64] 0.252930 0.033142 0.014732 ..
CCV_NNC_GEMM_FORWARD [691]: [2] -> [1] (0)
|-> 1. 0x1438eaf20 (0x285da7ec0:0) [1x64x64] 0.252930 0.033142 0.014732 ..
|-> 2. 0x1438eae70 (0x285da7e80:0) [1x64x160] -0.941895 -0.269531 0.044922 ..
|<- 1. 0x1438ec4e0 (0x285da7c40:0) [1x64x160] -0.292236 -0.114929 -0.027756 ..
CCV_NNC_GEMM_FORWARD [692]: [2] -> [1] (0)
|-> 1. 0x1438eb040 (0x285da7dc0:0) [1x64x160] -0.076111 -0.039978 0.017380 ..
|-> 2. 0x1438eaf90 (0x285da7d80:0) [1x64x160] 0.386719 1.047852 -0.522461 ..
|<- 1. 0x1438aba60 (0x285da7ec0:0) [1x64x64] -1.567383 -1.409180 -0.556152 ..
CCV_NNC_SOFTMAX_FORWARD [693]: [1] -> [1] (0)
|-> 1. 0x1438eb0f0 (0x285da7ec0:0) [64x64] -1.567383 -1.409180 -0.556152 ..
|<- 1. 0x1438eb0f0 (0x285da7ec0:0) [64x64] 0.004513 0.005287 0.012405 ..
CCV_NNC_GEMM_FORWARD [694]: [2] -> [1] (0)
|-> 1. 0x1438eb210 (0x285da7ec0:0) [1x64x64] 0.004513 0.005287 0.012405 ..
|-> 2. 0x1438eb160 (0x285da7e80:0) [1x64x160] 0.508789 -0.653809 0.066711 ..
|<- 1. 0x1438ec590 (0x285da7c40:0) [1x64x160] 0.362305 -0.218872 0.285400 ..
CCV_NNC_GEMM_FORWARD [695]: [2] -> [1] (0)
|-> 1. 0x1438eb330 (0x285da7dc0:0) [1x64x160] -0.028793 -0.123047 -0.051422 ..
|-> 2. 0x1438eb280 (0x285da7d80:0) [1x64x160] -0.632812 0.301025 -0.790039 ..
|<- 1. 0x1438abad0 (0x285da7ec0:0) [1x64x64] 1.339844 1.593750 1.214844 ..
CCV_NNC_SOFTMAX_FORWARD [696]: [1] -> [1] (0)
|-> 1. 0x1438eb3e0 (0x285da7ec0:0) [64x64] 1.339844 1.593750 1.214844 ..
|<- 1. 0x1438eb3e0 (0x285da7ec0:0) [64x64] 0.032227 0.041534 0.028427 ..
CCV_NNC_GEMM_FORWARD [697]: [2] -> [1] (0)
|-> 1. 0x1438eb500 (0x285da7ec0:0) [1x64x64] 0.032227 0.041534 0.028427 ..
|-> 2. 0x1438eb450 (0x285da7e80:0) [1x64x160] 0.126465 -0.158203 -0.069092 ..
|<- 1. 0x1438ec640 (0x285da7c40:0) [1x64x160] 0.046753 -0.103516 -0.194336 ..
CCV_NNC_GEMM_FORWARD [698]: [2] -> [1] (0)
|-> 1. 0x1438eb620 (0x285da7dc0:0) [1x64x160] -0.019913 -0.025894 -0.002478 ..
|-> 2. 0x1438eb570 (0x285da7d80:0) [1x64x160] 0.326172 -0.140503 -0.195190 ..
|<- 1. 0x1438abb40 (0x285da7ec0:0) [1x64x64] 0.503906 -1.234375 -0.736328 ..
CCV_NNC_SOFTMAX_FORWARD [699]: [1] -> [1] (0)
|-> 1. 0x1438eb6d0 (0x285da7ec0:0) [64x64] 0.503906 -1.234375 -0.736328 ..
|<- 1. 0x1438eb6d0 (0x285da7ec0:0) [64x64] 0.029678 0.005219 0.008583 ..
CCV_NNC_GEMM_FORWARD [700]: [2] -> [1] (0)
|-> 1. 0x1438eb7f0 (0x285da7ec0:0) [1x64x64] 0.029678 0.005219 0.008583 ..
|-> 2. 0x1438eb740 (0x285da7e80:0) [1x64x160] 0.398193 -0.196899 -0.227051 ..
|<- 1. 0x1438ec6f0 (0x285da7c40:0) [1x64x160] -0.266602 0.050110 0.153320 ..
CCV_NNC_GEMM_FORWARD [701]: [2] -> [1] (0)
|-> 1. 0x1438eb910 (0x285da7dc0:0) [1x64x160] -0.031891 -0.009857 0.023682 ..
|-> 2. 0x1438eb860 (0x285da7d80:0) [1x64x160] -0.242065 0.734375 1.013672 ..
|<- 1. 0x1438abbb0 (0x285da7ec0:0) [1x64x64] 2.162109 1.419922 1.208008 ..
CCV_NNC_SOFTMAX_FORWARD [702]: [1] -> [1] (0)
|-> 1. 0x1438eb9c0 (0x285da7ec0:0) [64x64] 2.162109 1.419922 1.208008 ..
|<- 1. 0x1438eb9c0 (0x285da7ec0:0) [64x64] 0.080261 0.038208 0.030914 ..
CCV_NNC_GEMM_FORWARD [703]: [2] -> [1] (0)
|-> 1. 0x1438ebae0 (0x285da7ec0:0) [1x64x64] 0.080261 0.038208 0.030914 ..
|-> 2. 0x1438eba30 (0x285da7e80:0) [1x64x160] -0.422119 0.079163 -0.132812 ..
|<- 1. 0x1438ec7a0 (0x285da7c40:0) [1x64x160] -0.128662 -0.307129 -0.066833 ..
CCV_NNC_GEMM_FORWARD [704]: [2] -> [1] (0)
|-> 1. 0x1438ebc00 (0x285da7dc0:0) [1x64x160] -0.072937 -0.065369 -0.056854 ..
|-> 2. 0x1438ebb50 (0x285da7d80:0) [1x64x160] -0.361328 0.986816 -2.113281 ..
|<- 1. 0x1438abc20 (0x285da7ec0:0) [1x64x64] 2.521484 -0.208008 0.394531 ..
CCV_NNC_SOFTMAX_FORWARD [705]: [1] -> [1] (0)
|-> 1. 0x1438ebcb0 (0x285da7ec0:0) [64x64] 2.521484 -0.208008 0.394531 ..
|<- 1. 0x1438ebcb0 (0x285da7ec0:0) [64x64] 0.050659 0.003305 0.006039 ..
CCV_NNC_GEMM_FORWARD [706]: [2] -> [1] (0)
|-> 1. 0x1438ebdd0 (0x285da7ec0:0) [1x64x64] 0.050659 0.003305 0.006039 ..
|-> 2. 0x1438ebd20 (0x285da7e80:0) [1x64x160] 1.051758 0.216919 0.411133 ..
|<- 1. 0x1438ec850 (0x285da7c40:0) [1x64x160] 0.444336 0.171265 -0.259277 ..
CCV_NNC_TRANSPOSE_FORWARD [707]: [1] -> [1] (0)
|-> 1. 0x1438ec900 (0x285da7c40:0) [2x8x64x160] 0.771484 -0.089233 -0.232788 ..
|<- 1. 0x1438abd00 (0x285da7e80:0) [2x64x8x160] 0.771484 -0.089233 -0.232788 ..
CCV_NNC_GEMM_FORWARD [708]: [3] -> [1] (0)
|-> 1. 0x1438ec970 (0x285da7e80:0) [2x64x1280] 0.771484 -0.089233 -0.232788 ..
|-> 2. 0x1438c5140 (0x285e6a640:0) [1280x1280] 0.027100 -0.068604 0.031891 ..
|-> 3. 0x1438c51b0 (0x285e69ac0:0) [1280] 0.038483 -0.006405 0.061768 ..
|<- 1. 0x1438abd70 (0x285da7c40:0) [2x64x1280] 0.511230 0.204590 0.643555 ..
CCV_NNC_ADD_FORWARD [709]: [2] -> [1] (0)
|-> 1. 0x1438abd70 (0x285da7c40:0) [2x64x1280] 0.511230 0.204590 0.643555 ..
|-> 2. 0x1438e8e40 (0x285da7b00:0) [2x64x1280] 0.255371 -2.494141 0.954590 ..
|<- 1. 0x1438abd70 (0x285da7c40:0) [2x64x1280] 0.766602 -2.289062 1.597656 ..
CCV_NNC_LAYER_NORM_FORWARD [710]: [3] -> [3] (0)
|-> 1. 0x1438abd70 (0x285da7c40:0) [2x64x1280] 0.766602 -2.289062 1.597656 ..
|-> 2. 0x1438c5220 (0x285e69bc0:0) [1x1x1280] 0.401367 0.364502 0.335205 ..
|-> 3. 0x1438c5290 (0x285e69740:0) [1x1x1280] 0.121277 -0.088562 0.122620 ..
|<- 1. 0x1438abde0 (0x285da7b00:0) [2x64x1280] 0.436523 -0.916992 0.665039 ..
|<- 2. 0x1438abe50 (0x285da7f00:0) [2x64x1] -0.018265 ..
|<- 3. 0x1438abec0 (0x285da7f40:0) [2x64x1] 1.000977 ..
CCV_NNC_GEMM_FORWARD [711]: [2] -> [1] (0)
|-> 1. 0x1438abde0 (0x285da7b00:0) [2x64x1280] 0.436523 -0.916992 0.665039 ..
|-> 2. 0x1438c5300 (0x285e6a580:0) [1280x1280] -0.034912 -0.002848 0.024429 ..
|<- 1. 0x1438abf30 (0x285da7e80:0) [2x64x1280] 0.398193 -0.881836 1.603516 ..
CCV_NNC_SCALAR_MUL_FORWARD [712]: [1] -> [1] (0)
|-> 1. 0x1438abf30 (0x285da7e80:0) [2x64x1280] 0.398193 -0.881836 1.603516 ..
|<- 1. 0x1438abf30 (0x285da7e80:0) [2x64x1280] 0.031464 -0.069702 0.126709 ..
CCV_NNC_TRANSPOSE_FORWARD [713]: [1] -> [1] (0)
|-> 1. 0x1438eca50 (0x285da7e80:0) [2x64x8x160] 0.031464 -0.069702 0.126709 ..
|<- 1. 0x1438ac080 (0x285da7b00:0) [2x8x64x160] 0.031464 -0.069702 0.126709 ..
CCV_NNC_GEMM_FORWARD [714]: [2] -> [1] (0)
Wait: (0, 60)
|-> 1. 0x1438ac080 (0x285da7b00:0) [2x8x64x160] 0.031464 -0.069702 0.126709 ..
|-> 2. 0x1438ac010 (0x285da7fc0:0) [2x8x133x160] -0.178467 0.800293 -1.226562 ..
|<- 1. 0x1438ac0f0 (0x285d85100:0) [2x8x64x133] 2.070312 -1.829102 -4.367188 ..
CCV_NNC_SOFTMAX_FORWARD [715]: [1] -> [1] (0)
|-> 1. 0x1438ecac0 (0x285d85100:0) [1024x133] 2.070312 -1.829102 -4.367188 ..
|<- 1. 0x1438ecac0 (0x285d85100:0) [1024x133] 0.109619 0.002220 0.000175 ..
CCV_NNC_GEMM_FORWARD [716]: [2] -> [1] (0)
Wait: (0, 61)
|-> 1. 0x1438ecba0 (0x285d85100:0) [2x8x64x133] 0.109619 0.002220 0.000175 ..
|-> 2. 0x1438ac1d0 (0x285d84540:0) [2x8x133x160] -0.026199 -0.083679 -0.066772 ..
|<- 1. 0x1438ac240 (0x285da7b00:0) [2x8x64x160] 0.501953 -0.582520 0.049713 ..
CCV_NNC_TRANSPOSE_FORWARD [717]: [1] -> [1] (0)
|-> 1. 0x1438ecc10 (0x285da7b00:0) [2x8x64x160] 0.501953 -0.582520 0.049713 ..
|<- 1. 0x1438ac2b0 (0x285da7e80:0) [2x64x8x160] 0.501953 -0.582520 0.049713 ..
CCV_NNC_GEMM_FORWARD [718]: [3] -> [1] (0)
|-> 1. 0x1438ecc80 (0x285da7e80:0) [2x64x1280] 0.501953 -0.582520 0.049713 ..
|-> 2. 0x1438c5450 (0x285e6b280:0) [1280x1280] -0.032074 -0.023193 0.006802 ..
|-> 3. 0x1438c54c0 (0x285e6a800:0) [1280] 0.004494 0.013809 0.020386 ..
|<- 1. 0x1438ac320 (0x285da7e00:0) [2x64x1280] 0.222412 -0.636230 0.817383 ..
CCV_NNC_ADD_FORWARD [719]: [2] -> [1] (0)
|-> 1. 0x1438ac320 (0x285da7e00:0) [2x64x1280] 0.222412 -0.636230 0.817383 ..
|-> 2. 0x1438abd70 (0x285da7c40:0) [2x64x1280] 0.766602 -2.289062 1.597656 ..
|<- 1. 0x1438ac320 (0x285da7e00:0) [2x64x1280] 0.989258 -2.925781 2.414062 ..
CCV_NNC_LAYER_NORM_FORWARD [720]: [3] -> [3] (0)
|-> 1. 0x1438ac320 (0x285da7e00:0) [2x64x1280] 0.989258 -2.925781 2.414062 ..
|-> 2. 0x1438c5530 (0x285e6a540:0) [1x1x1280] 0.540039 0.525879 0.508301 ..
|-> 3. 0x1438c55a0 (0x285e6a600:0) [1x1x1280] 0.067078 0.049713 0.175293 ..
|<- 1. 0x1438ac390 (0x285d85080:0) [2x64x1280] 0.486572 -1.115234 1.124023 ..
|<- 2. 0x1438ac400 (0x285d84580:0) [2x64x1] -0.027466 ..
|<- 3. 0x1438ac470 (0x285d84f80:0) [2x64x1] 0.764160 ..
Emit: (0, 62)
CCV_NNC_GEMM_FORWARD [721]: [3] -> [1] (0)
|-> 1. 0x1438ac390 (0x285d85080:0) [2x64x1280] 0.486572 -1.115234 1.124023 ..
|-> 2. 0x1438c5610 (0x285e6a140:0) [5120x1280] 0.026459 -0.082642 -0.080505 ..
|-> 3. 0x1438c5680 (0x285e6a000:0) [5120] -0.054657 -0.047638 -0.025925 ..
|<- 1. 0x1438ac4e0 (0x285da6fc0:0) [2x64x5120] -0.712891 -2.017578 -1.770508 ..
CCV_NNC_GELU_FORWARD [722]: [1] -> [1] (0)
|-> 1. 0x1438ac4e0 (0x285da6fc0:0) [2x64x5120] -0.712891 -2.017578 -1.770508 ..
|<- 1. 0x1438ac4e0 (0x285da6fc0:0) [2x64x5120] -0.169678 -0.044037 -0.067871 ..
CCV_NNC_GEMM_FORWARD [723]: [3] -> [1] (1)
Wait: (1, 62)
|-> 1. 0x1438ac390 (0x285d85080:0) [2x64x1280] 0.486572 -1.115234 1.124023 ..
|-> 2. 0x1438c56f0 (0x285e699c0:0) [5120x1280] -0.012024 -0.051239 -0.063782 ..
|-> 3. 0x1438c5760 (0x285e69a00:0) [5120] -0.031647 0.015419 -0.018967 ..
|<- 1. 0x1438ac550 (0x285da6f00:0) [2x64x5120] -1.302734 0.165161 -0.372803 ..
Emit: (1, 63)
CCV_NNC_MUL_FORWARD [724]: [2] -> [1] (0)
Wait: (0, 63)
|-> 1. 0x1438ac550 (0x285da6f00:0) [2x64x5120] -1.302734 0.165161 -0.372803 ..
|-> 2. 0x1438ac4e0 (0x285da6fc0:0) [2x64x5120] -0.169678 -0.044037 -0.067871 ..
|<- 1. 0x1438ac550 (0x285da6f00:0) [2x64x5120] 0.221069 -0.007275 0.025299 ..
CCV_NNC_GEMM_FORWARD [725]: [3] -> [1] (0)
|-> 1. 0x1438ac550 (0x285da6f00:0) [2x64x5120] 0.221069 -0.007275 0.025299 ..
|-> 2. 0x1438c57d0 (0x285e69700:0) [1280x5120] 0.011162 0.010612 -0.047211 ..
|-> 3. 0x1438c5840 (0x285e69dc0:0) [1280] 0.033142 -0.048004 0.002876 ..
|<- 1. 0x1438ac5c0 (0x285da7c40:0) [2x64x1280] 0.304688 0.752441 1.006836 ..
CCV_NNC_ADD_FORWARD [726]: [2] -> [1] (0)
|-> 1. 0x1438ac5c0 (0x285da7c40:0) [2x64x1280] 0.304688 0.752441 1.006836 ..
|-> 2. 0x1438ac320 (0x285da7e00:0) [2x64x1280] 0.989258 -2.925781 2.414062 ..
|<- 1. 0x1438ac5c0 (0x285da7c40:0) [2x64x1280] 1.293945 -2.173828 3.421875 ..
CCV_NNC_CONVOLUTION_FORWARD [727]: [3] -> [1] (0)
|-> 1. 0x1438eccf0 (0x285da7c40:0) [2x8x8x1280] 1.293945 -2.173828 3.421875 ..
|-> 2. 0x1438c58b0 (0x285e6a240:0) [1280x1280x1x1] -0.080017 ..
|-> 3. 0x1438c5920 (0x285e6a1c0:0) [1280] 0.049927 0.032471 -0.001247 ..
|<- 1. 0x1438ac630 (0x285da7b00:0) [2x8x8x1280] -3.859375 0.357178 -1.645508 ..
CCV_NNC_ADD_FORWARD [728]: [2] -> [1] (0)
|-> 1. 0x1438ac630 (0x285da7b00:0) [2x8x8x1280] -3.859375 0.357178 -1.645508 ..
|-> 2. 0x1438aaf70 (0x285da7c00:0) [2x8x8x1280] -1.204102 0.336914 2.810547 ..
|<- 1. 0x1438ac630 (0x285da7b00:0) [2x8x8x1280] -5.062500 0.694336 1.165039 ..
CCV_NNC_GROUP_NORM_FORWARD [729]: [3] -> [3] (0)
|-> 1. 0x1438ac630 (0x285da7b00:0) [2x8x8x1280] -5.062500 0.694336 1.165039 ..
|-> 2. 0x1438c5990 (0x285e69d80:0) [1x1x1x1280] 0.505859 0.487793 0.463867 ..
|-> 3. 0x1438c5a00 (0x285e6a0c0:0) [1x1x1x1280] -0.086914 -0.171875 -0.135620 ..
|<- 1. 0x1438ac6a0 (0x285da7e80:0) [2x8x8x1280] -1.073242 -0.036407 0.077698 ..
|<- 2. 0x1438ac710 (0x285d84fc0:0) [2x1x1x32] -0.023285 -0.905762 -0.315430 ..
|<- 3. 0x1438ac780 (0x285d84240:0) [2x1x1x32] 0.386963 0.354004 0.423584 ..
CCV_NNC_SWISH_FORWARD [730]: [1] -> [1] (0)
|-> 1. 0x1438ac6a0 (0x285da7e80:0) [2x8x8x1280] -1.073242 -0.036407 0.077698 ..
|<- 1. 0x1438ac6a0 (0x285da7e80:0) [2x8x8x1280] -0.273438 -0.017868 0.040344 ..
CCV_NNC_CONVOLUTION_FORWARD [731]: [3] -> [1] (0)
|-> 1. 0x1438ac6a0 (0x285da7e80:0) [2x8x8x1280] -0.273438 -0.017868 0.040344 ..
|-> 2. 0x1438c5b50 (0x285e69ec0:0) [1280x1280x3x3] 0.003563 0.006142 -0.012085 ..
|-> 3. 0x1438c5bc0 (0x285e69e00:0) [1280] 0.134766 -0.074646 0.110718 ..
|<- 1. 0x1438ac860 (0x285da7dc0:0) [2x8x8x1280] 1.010742 0.804199 0.660156 ..
CCV_NNC_ADD_FORWARD [732]: [2] -> [1] (0)
Wait: (0, 64)
|-> 1. 0x1438ac860 (0x285da7dc0:0) [2x8x8x1280] 1.010742 0.804199 0.660156 ..
|-> 2. 0x1438ecd60 (0x285d84340:0) [2x1x1x1280] 0.444092 0.104248 0.304443 ..
|<- 1. 0x1438ac860 (0x285da7dc0:0) [2x8x8x1280] 1.455078 0.908203 0.964844 ..
CCV_NNC_GROUP_NORM_FORWARD [733]: [3] -> [3] (0)
|-> 1. 0x1438ac860 (0x285da7dc0:0) [2x8x8x1280] 1.455078 0.908203 0.964844 ..
|-> 2. 0x1438c5c30 (0x285e69d00:0) [1x1x1x1280] 0.416992 0.950195 0.386475 ..
|-> 3. 0x1438c5ca0 (0x285e69f80:0) [1x1x1x1280] -0.207275 -0.478027 -0.213257 ..
|<- 1. 0x1438ac8d0 (0x285da7e80:0) [2x8x8x1280] 0.152710 -0.064392 -0.027893 ..
|<- 2. 0x1438ac940 (0x285d832c0:0) [2x1x1x32] 0.352051 0.546387 0.645020 ..
|<- 3. 0x1438ac9b0 (0x285d83240:0) [2x1x1x32] 0.782715 0.651855 0.643555 ..
CCV_NNC_SWISH_FORWARD [734]: [1] -> [1] (0)
|-> 1. 0x1438ac8d0 (0x285da7e80:0) [2x8x8x1280] 0.152710 -0.064392 -0.027893 ..
|<- 1. 0x1438ac8d0 (0x285da7e80:0) [2x8x8x1280] 0.082153 -0.031158 -0.013756 ..
CCV_NNC_CONVOLUTION_FORWARD [735]: [3] -> [1] (0)
|-> 1. 0x1438ac8d0 (0x285da7e80:0) [2x8x8x1280] 0.082153 -0.031158 -0.013756 ..
|-> 2. 0x1438c5d10 (0x285e69e40:0) [1280x1280x3x3] -0.029037 0.010658 0.032440 ..
|-> 3. 0x1438c5d80 (0x285e6a300:0) [1280] -0.044220 -0.035431 0.005268 ..
|<- 1. 0x1438aca20 (0x285da7dc0:0) [2x8x8x1280] -0.755371 -1.509766 -1.513672 ..
CCV_NNC_ADD_FORWARD [736]: [2] -> [1] (0)
|-> 1. 0x1438ac630 (0x285da7b00:0) [2x8x8x1280] -5.062500 0.694336 1.165039 ..
|-> 2. 0x1438aca20 (0x285da7dc0:0) [2x8x8x1280] -0.755371 -1.509766 -1.513672 ..
|<- 1. 0x1438ecdd0 (0x285d81380:0) [2x8x8x1280] -5.816406 -0.815430 -0.348633 ..
Emit: (0, 66)
CCV_NNC_GROUP_NORM_FORWARD [737]: [3] -> [3] (0)
|-> 1. 0x1438aca90 (0x285d81380:0) [2x8x8x2560] -5.816406 -0.815430 -0.348633 ..
|-> 2. 0x1438c5df0 (0x285e69fc0:0) [1x1x1x2560] 0.725586 0.622559 0.557617 ..
|-> 3. 0x1438c5e60 (0x285e697c0:0) [1x1x1x2560] -0.407715 -0.212769 -0.123596 ..
|<- 1. 0x1438acb00 (0x285d812c0:0) [2x8x8x2560] -1.832031 -0.351074 -0.156860 ..
|<- 2. 0x1438acb70 (0x285d832c0:0) [2x1x1x32] -0.177368 -0.041290 -0.342773 ..
|<- 3. 0x1438acbe0 (0x285d83240:0) [2x1x1x32] 0.348145 0.389404 0.362793 ..
CCV_NNC_SWISH_FORWARD [738]: [1] -> [1] (0)
|-> 1. 0x1438acb00 (0x285d812c0:0) [2x8x8x2560] -1.832031 -0.351074 -0.156860 ..
|<- 1. 0x1438acb00 (0x285d812c0:0) [2x8x8x2560] -0.252930 -0.145020 -0.072266 ..
CCV_NNC_CONVOLUTION_FORWARD [739]: [3] -> [1] (0)
|-> 1. 0x1438acb00 (0x285d812c0:0) [2x8x8x2560] -0.252930 -0.145020 -0.072266 ..
|-> 2. 0x1438c5fb0 (0x285e6a400:0) [1280x2560x3x3] -0.007729 -0.021667 -0.035583 ..
|-> 3. 0x1438c6020 (0x285e6a3c0:0) [1280] 0.040741 0.076477 0.056396 ..
|<- 1. 0x1438accc0 (0x285da7d80:0) [2x8x8x1280] 1.798828 1.467773 0.705078 ..
CCV_NNC_ADD_FORWARD [740]: [2] -> [1] (0)
Wait: (0, 65)
|-> 1. 0x1438accc0 (0x285da7d80:0) [2x8x8x1280] 1.798828 1.467773 0.705078 ..
|-> 2. 0x1438ecf30 (0x285d82bc0:0) [2x1x1x1280] 0.063354 0.040497 0.044067 ..
|<- 1. 0x1438accc0 (0x285da7d80:0) [2x8x8x1280] 1.862305 1.507812 0.749023 ..
CCV_NNC_GROUP_NORM_FORWARD [741]: [3] -> [3] (0)
|-> 1. 0x1438accc0 (0x285da7d80:0) [2x8x8x1280] 1.862305 1.507812 0.749023 ..
|-> 2. 0x1438c6090 (0x285f79780:0) [1x1x1x1280] 0.964844 0.825195 0.942383 ..
|-> 3. 0x1438c6100 (0x285d98000:0) [1x1x1x1280] -0.362549 -0.331787 -0.382080 ..
|<- 1. 0x1438acd30 (0x285da7b00:0) [2x8x8x1280] 0.399658 0.115356 -0.371826 ..
|<- 2. 0x1438acda0 (0x285d84240:0) [2x1x1x32] 0.733398 0.366211 0.651367 ..
|<- 3. 0x1438ace10 (0x285d84fc0:0) [2x1x1x32] 0.699707 0.741211 0.669922 ..
CCV_NNC_SWISH_FORWARD [742]: [1] -> [1] (0)
|-> 1. 0x1438acd30 (0x285da7b00:0) [2x8x8x1280] 0.399658 0.115356 -0.371826 ..
|<- 1. 0x1438acd30 (0x285da7b00:0) [2x8x8x1280] 0.239258 0.061005 -0.151733 ..
CCV_NNC_CONVOLUTION_FORWARD [743]: [3] -> [1] (0)
|-> 1. 0x1438acd30 (0x285da7b00:0) [2x8x8x1280] 0.239258 0.061005 -0.151733 ..
|-> 2. 0x1438c6170 (0x285d98040:0) [1280x1280x3x3] -0.009697 0.013046 0.010773 ..
|-> 3. 0x1438c61e0 (0x285d98080:0) [1280] 0.000703 0.008232 0.014633 ..
|<- 1. 0x1438ace80 (0x285da7dc0:0) [2x8x8x1280] 1.174805 -2.017578 -1.286133 ..
CCV_NNC_CONVOLUTION_FORWARD [744]: [3] -> [1] (1)
Wait: (1, 66)
|-> 1. 0x1438aca90 (0x285d81380:0) [2x8x8x2560] -5.816406 -0.815430 -0.348633 ..
|-> 2. 0x1438c6250 (0x285d980c0:0) [1280x2560x1x1] 0.010796 ..
|-> 3. 0x1438c62c0 (0x285d98100:0) [1280] 0.006908 0.013184 0.016907 ..
|<- 1. 0x1438acef0 (0x285da7e80:0) [2x8x8x1280] 3.142578 3.273438 1.825195 ..
Emit: (1, 67)
CCV_NNC_ADD_FORWARD [745]: [2] -> [1] (0)
Wait: (0, 67)
|-> 1. 0x1438acef0 (0x285da7e80:0) [2x8x8x1280] 3.142578 3.273438 1.825195 ..
|-> 2. 0x1438ace80 (0x285da7dc0:0) [2x8x8x1280] 1.174805 -2.017578 -1.286133 ..
|<- 1. 0x1438ecfa0 (0x285d81340:0) [2x8x8x1280] 4.316406 1.255859 0.539062 ..
Emit: (0, 69)
CCV_NNC_GROUP_NORM_FORWARD [746]: [3] -> [3] (0)
|-> 1. 0x1438acf60 (0x285d81340:0) [2x8x8x2560] 4.316406 1.255859 0.539062 ..
|-> 2. 0x1438c6330 (0x285d98140:0) [1x1x1x2560] 0.630371 0.571289 0.597656 ..
|-> 3. 0x1438c63a0 (0x285d98180:0) [1x1x1x2560] -0.199951 -0.218018 -0.217773 ..
|<- 1. 0x1438acfd0 (0x285d812c0:0) [2x8x8x2560] 0.794922 0.088684 -0.042725 ..
|<- 2. 0x1438ad040 (0x285d83240:0) [2x1x1x32] -0.321533 -0.579590 -0.222778 ..
|<- 3. 0x1438ad0b0 (0x285d832c0:0) [2x1x1x32] 0.340332 0.350098 0.317627 ..
CCV_NNC_SWISH_FORWARD [747]: [1] -> [1] (0)
|-> 1. 0x1438acfd0 (0x285d812c0:0) [2x8x8x2560] 0.794922 0.088684 -0.042725 ..
|<- 1. 0x1438acfd0 (0x285d812c0:0) [2x8x8x2560] 0.547852 0.046295 -0.020905 ..
CCV_NNC_CONVOLUTION_FORWARD [748]: [3] -> [1] (0)
|-> 1. 0x1438acfd0 (0x285d812c0:0) [2x8x8x2560] 0.547852 0.046295 -0.020905 ..
|-> 2. 0x1438c64f0 (0x285d98240:0) [1280x2560x3x3] 0.036163 0.038696 0.011833 ..
|-> 3. 0x1438c6560 (0x285d98280:0) [1280] 0.019730 -0.014420 -0.040558 ..
|<- 1. 0x1438ad190 (0x285da7d80:0) [2x8x8x1280] 1.212891 1.631836 2.083984 ..
CCV_NNC_ADD_FORWARD [749]: [2] -> [1] (0)
Wait: (0, 68)
|-> 1. 0x1438ad190 (0x285da7d80:0) [2x8x8x1280] 1.212891 1.631836 2.083984 ..
|-> 2. 0x1438ed100 (0x285d837c0:0) [2x1x1x1280] 0.086243 1.029297 0.114319 ..
|<- 1. 0x1438ad190 (0x285da7d80:0) [2x8x8x1280] 1.298828 2.660156 2.199219 ..
CCV_NNC_GROUP_NORM_FORWARD [750]: [3] -> [3] (0)
|-> 1. 0x1438ad190 (0x285da7d80:0) [2x8x8x1280] 1.298828 2.660156 2.199219 ..
|-> 2. 0x1438c65d0 (0x285d982c0:0) [1x1x1x1280] 1.230469 0.995117 1.337891 ..
|-> 3. 0x1438c6640 (0x285d98300:0) [1x1x1x1280] -0.645508 -0.603516 -0.637695 ..
|<- 1. 0x1438ad200 (0x285da7b00:0) [2x8x8x1280] -0.030350 0.647461 0.701172 ..
|<- 2. 0x1438ad270 (0x285d84fc0:0) [2x1x1x32] 0.399902 0.517090 0.236938 ..
|<- 3. 0x1438ad2e0 (0x285d84240:0) [2x1x1x32] 0.556152 0.534180 0.498779 ..
CCV_NNC_SWISH_FORWARD [751]: [1] -> [1] (0)
|-> 1. 0x1438ad200 (0x285da7b00:0) [2x8x8x1280] -0.030350 0.647461 0.701172 ..
|<- 1. 0x1438ad200 (0x285da7b00:0) [2x8x8x1280] -0.014946 0.425049 0.468750 ..
CCV_NNC_CONVOLUTION_FORWARD [752]: [3] -> [1] (0)
|-> 1. 0x1438ad200 (0x285da7b00:0) [2x8x8x1280] -0.014946 0.425049 0.468750 ..
|-> 2. 0x1438c66b0 (0x285d98340:0) [1280x1280x3x3] -0.001245 0.031113 0.086487 ..
|-> 3. 0x1438c6720 (0x285d98380:0) [1280] 0.016449 0.006584 -0.006351 ..
|<- 1. 0x1438ad350 (0x285da7dc0:0) [2x8x8x1280] -0.924805 0.691406 0.143433 ..
CCV_NNC_CONVOLUTION_FORWARD [753]: [3] -> [1] (1)
Wait: (1, 69)
|-> 1. 0x1438acf60 (0x285d81340:0) [2x8x8x2560] 4.316406 1.255859 0.539062 ..
|-> 2. 0x1438c6790 (0x285d983c0:0) [1280x2560x1x1] 0.004192 ..
|-> 3. 0x1438c6800 (0x285d98400:0) [1280] 0.015945 0.002588 -0.009155 ..
|<- 1. 0x1438ad3c0 (0x285da7e80:0) [2x8x8x1280] -0.322998 -0.485596 0.354736 ..
Emit: (1, 70)
CCV_NNC_ADD_FORWARD [754]: [2] -> [1] (0)
Wait: (0, 70)
|-> 1. 0x1438ad3c0 (0x285da7e80:0) [2x8x8x1280] -0.322998 -0.485596 0.354736 ..
|-> 2. 0x1438ad350 (0x285da7dc0:0) [2x8x8x1280] -0.924805 0.691406 0.143433 ..
|<- 1. 0x1438ed170 (0x285d83dc0:0) [2x8x8x1280] -1.248047 0.205811 0.498047 ..
Emit: (0, 72)
CCV_NNC_GROUP_NORM_FORWARD [755]: [3] -> [3] (0)
|-> 1. 0x1438ad430 (0x285d83dc0:0) [2x8x8x2560] -1.248047 0.205811 0.498047 ..
|-> 2. 0x1438c6870 (0x285d98440:0) [1x1x1x2560] 0.756836 0.693848 0.636230 ..
|-> 3. 0x1438c68e0 (0x285d98480:0) [1x1x1x2560] -0.396973 -0.253662 -0.223022 ..
|<- 1. 0x1438ad4a0 (0x285d812c0:0) [2x8x8x2560] -0.695312 -0.104187 -0.007957 ..
|<- 2. 0x1438ad510 (0x285d83500:0) [2x1x1x32] -0.307861 -0.204956 -0.260254 ..
|<- 3. 0x1438ad580 (0x285d83d00:0) [2x1x1x32] 0.419434 0.451660 0.446289 ..
CCV_NNC_SWISH_FORWARD [756]: [1] -> [1] (0)
|-> 1. 0x1438ad4a0 (0x285d812c0:0) [2x8x8x2560] -0.695312 -0.104187 -0.007957 ..
|<- 1. 0x1438ad4a0 (0x285d812c0:0) [2x8x8x2560] -0.231445 -0.049377 -0.003963 ..
CCV_NNC_CONVOLUTION_FORWARD [757]: [3] -> [1] (0)
|-> 1. 0x1438ad4a0 (0x285d812c0:0) [2x8x8x2560] -0.231445 -0.049377 -0.003963 ..
|-> 2. 0x1438c6a30 (0x285d98540:0) [1280x2560x3x3] 0.048737 0.011887 0.002392 ..
|-> 3. 0x1438c6aa0 (0x285d98580:0) [1280] 0.038788 -0.037323 0.055817 ..
|<- 1. 0x1438ad660 (0x285da7e80:0) [2x8x8x1280] 2.671875 -0.760254 2.441406 ..
CCV_NNC_ADD_FORWARD [758]: [2] -> [1] (0)
Wait: (0, 71)
|-> 1. 0x1438ad660 (0x285da7e80:0) [2x8x8x1280] 2.671875 -0.760254 2.441406 ..
|-> 2. 0x1438ed2d0 (0x285d800c0:0) [2x1x1x1280] 0.105347 -0.784180 0.284912 ..
|<- 1. 0x1438ad660 (0x285da7e80:0) [2x8x8x1280] 2.777344 -1.544922 2.726562 ..
CCV_NNC_GROUP_NORM_FORWARD [759]: [3] -> [3] (0)
|-> 1. 0x1438ad660 (0x285da7e80:0) [2x8x8x1280] 2.777344 -1.544922 2.726562 ..
|-> 2. 0x1438c6b10 (0x285d985c0:0) [1x1x1x1280] 0.943359 0.662598 0.296875 ..
|-> 3. 0x1438c6b80 (0x285d98600:0) [1x1x1x1280] -0.367188 -0.289062 -0.301025 ..
|<- 1. 0x1438ad6d0 (0x285da7b00:0) [2x8x8x1280] 1.064453 -0.584473 0.142700 ..
|<- 2. 0x1438ad740 (0x285d84240:0) [2x1x1x32] -0.563477 -0.038116 -0.829590 ..
|<- 3. 0x1438ad7b0 (0x285d84fc0:0) [2x1x1x32] 0.454346 0.275635 0.392578 ..
CCV_NNC_SWISH_FORWARD [760]: [1] -> [1] (0)
|-> 1. 0x1438ad6d0 (0x285da7b00:0) [2x8x8x1280] 1.064453 -0.584473 0.142700 ..
|<- 1. 0x1438ad6d0 (0x285da7b00:0) [2x8x8x1280] 0.791504 -0.209229 0.076416 ..
CCV_NNC_CONVOLUTION_FORWARD [761]: [3] -> [1] (0)
|-> 1. 0x1438ad6d0 (0x285da7b00:0) [2x8x8x1280] 0.791504 -0.209229 0.076416 ..
|-> 2. 0x1438c6bf0 (0x285d98640:0) [1280x1280x3x3] 0.026291 0.028885 -0.000336 ..
|-> 3. 0x1438c6c60 (0x285d98680:0) [1280] -0.024765 0.002316 -0.038116 ..
|<- 1. 0x1438ad820 (0x285da7e80:0) [2x8x8x1280] 0.061951 -0.079834 -0.075317 ..
CCV_NNC_CONVOLUTION_FORWARD [762]: [3] -> [1] (1)
Wait: (1, 72)
|-> 1. 0x1438ad430 (0x285d83dc0:0) [2x8x8x2560] -1.248047 0.205811 0.498047 ..
|-> 2. 0x1438c6cd0 (0x285d986c0:0) [1280x2560x1x1] -0.009468 ..
|-> 3. 0x1438c6d40 (0x285d98700:0) [1280] -0.020859 0.008873 -0.031433 ..
|<- 1. 0x1438ad890 (0x285da7980:0) [2x8x8x1280] -0.045776 -0.911133 0.387451 ..
Emit: (1, 73)
CCV_NNC_ADD_FORWARD [763]: [2] -> [1] (0)
Wait: (0, 73)
|-> 1. 0x1438ad890 (0x285da7980:0) [2x8x8x1280] -0.045776 -0.911133 0.387451 ..
|-> 2. 0x1438ad820 (0x285da7e80:0) [2x8x8x1280] 0.061951 -0.079834 -0.075317 ..
|<- 1. 0x1438ad890 (0x285da7980:0) [2x8x8x1280] 0.016174 -0.991211 0.312012 ..
CCV_NNC_UPSAMPLE_FORWARD [764]: [1] -> [1] (0)
|-> 1. 0x1438ad890 (0x285da7980:0) [2x8x8x1280] 0.016174 -0.991211 0.312012 ..
|<- 1. 0x1438ad900 (0x285da6f00:0) [2x16x16x1280] 0.016174 -0.991211 0.312012 ..
CCV_NNC_CONVOLUTION_FORWARD [765]: [3] -> [1] (0)
|-> 1. 0x1438ad900 (0x285da6f00:0) [2x16x16x1280] 0.016174 -0.991211 0.312012 ..
|-> 2. 0x1438c6db0 (0x285d98740:0) [1280x1280x3x3] 0.011360 -0.007851 0.013893 ..
|-> 3. 0x1438c6e20 (0x285d98780:0) [1280] 0.023331 0.098938 0.001162 ..
|<- 1. 0x1438ed340 (0x285da61c0:0) [2x16x16x1280] 0.657715 1.060547 1.991211 ..
Emit: (0, 75)
CCV_NNC_GROUP_NORM_FORWARD [766]: [3] -> [3] (0)
|-> 1. 0x1438ad970 (0x285da61c0:0) [2x16x16x2560] 0.657715 1.060547 1.991211 ..
|-> 2. 0x1438c6e90 (0x285d987c0:0) [1x1x1x2560] 0.145874 0.612305 0.688965 ..
|-> 3. 0x1438c6f00 (0x285d98800:0) [1x1x1x2560] 0.008514 -0.534668 -0.946777 ..
|<- 1. 0x1438ad9e0 (0x285da6900:0) [2x16x16x2560] 0.073853 -0.169312 -0.299072 ..
|<- 2. 0x1438ada50 (0x285da67c0:0) [2x1x1x32] -0.555664 -0.139893 -0.030365 ..
|<- 3. 0x1438adac0 (0x285da6800:0) [2x1x1x32] 0.369141 0.412109 0.424561 ..
CCV_NNC_SWISH_FORWARD [767]: [1] -> [1] (0)
|-> 1. 0x1438ad9e0 (0x285da6900:0) [2x16x16x2560] 0.073853 -0.169312 -0.299072 ..
|<- 1. 0x1438ad9e0 (0x285da6900:0) [2x16x16x2560] 0.038300 -0.077515 -0.127319 ..
CCV_NNC_CONVOLUTION_FORWARD [768]: [3] -> [1] (0)
|-> 1. 0x1438ad9e0 (0x285da6900:0) [2x16x16x2560] 0.038300 -0.077515 -0.127319 ..
|-> 2. 0x1438c7050 (0x285d988c0:0) [1280x2560x3x3] 0.006912 -0.010529 -0.017319 ..
|-> 3. 0x1438c70c0 (0x285d98900:0) [1280] 0.104980 0.079346 0.080933 ..
|<- 1. 0x1438adba0 (0x285da6dc0:0) [2x16x16x1280] 3.689453 2.458984 2.667969 ..
CCV_NNC_ADD_FORWARD [769]: [2] -> [1] (0)
Wait: (0, 74)
|-> 1. 0x1438adba0 (0x285da6dc0:0) [2x16x16x1280] 3.689453 2.458984 2.667969 ..
|-> 2. 0x1438ed4a0 (0x285d83980:0) [2x1x1x1280] -0.228027 0.609375 0.654297 ..
|<- 1. 0x1438adba0 (0x285da6dc0:0) [2x16x16x1280] 3.460938 3.068359 3.322266 ..
CCV_NNC_GROUP_NORM_FORWARD [770]: [3] -> [3] (0)
|-> 1. 0x1438adba0 (0x285da6dc0:0) [2x16x16x1280] 3.460938 3.068359 3.322266 ..
|-> 2. 0x1438c7130 (0x285d98940:0) [1x1x1x1280] 0.571777 0.612305 0.581055 ..
|-> 3. 0x1438c71a0 (0x285d98980:0) [1x1x1x1280] -0.306396 -0.300537 -0.279541 ..
|<- 1. 0x1438adc10 (0x285da6fc0:0) [2x16x16x1280] 0.236084 0.161987 0.232056 ..
|<- 2. 0x1438adc80 (0x285d82fc0:0) [2x1x1x32] 1.535156 1.185547 1.573242 ..
|<- 3. 0x1438adcf0 (0x285d83840:0) [2x1x1x32] 0.492676 0.521484 0.648438 ..
CCV_NNC_SWISH_FORWARD [771]: [1] -> [1] (0)
|-> 1. 0x1438adc10 (0x285da6fc0:0) [2x16x16x1280] 0.236084 0.161987 0.232056 ..
|<- 1. 0x1438adc10 (0x285da6fc0:0) [2x16x16x1280] 0.131958 0.087524 0.129395 ..
CCV_NNC_CONVOLUTION_FORWARD [772]: [3] -> [1] (0)
|-> 1. 0x1438adc10 (0x285da6fc0:0) [2x16x16x1280] 0.131958 0.087524 0.129395 ..
|-> 2. 0x1438c7210 (0x285d989c0:0) [1280x1280x3x3] -0.014008 -0.055908 -0.003098 ..
|-> 3. 0x1438c7280 (0x285d98a00:0) [1280] 0.028137 0.005749 -0.001112 ..
|<- 1. 0x1438add60 (0x285da6dc0:0) [2x16x16x1280] 1.100586 -5.621094 2.267578 ..
CCV_NNC_CONVOLUTION_FORWARD [773]: [3] -> [1] (1)
Wait: (1, 75)
|-> 1. 0x1438ad970 (0x285da61c0:0) [2x16x16x2560] 0.657715 1.060547 1.991211 ..
|-> 2. 0x1438c72f0 (0x285d98a40:0) [1280x2560x1x1] 0.001811 ..
|-> 3. 0x1438c7360 (0x285d98a80:0) [1280] 0.025864 0.000865 -0.001306 ..
|<- 1. 0x1438addd0 (0x285da6f00:0) [2x16x16x1280] -1.313477 2.810547 1.129883 ..
Emit: (1, 76)
CCV_NNC_ADD_FORWARD [774]: [2] -> [1] (0)
Wait: (0, 76)
|-> 1. 0x1438addd0 (0x285da6f00:0) [2x16x16x1280] -1.313477 2.810547 1.129883 ..
|-> 2. 0x1438add60 (0x285da6dc0:0) [2x16x16x1280] 1.100586 -5.621094 2.267578 ..
|<- 1. 0x1438addd0 (0x285da6f00:0) [2x16x16x1280] -0.212891 -2.810547 3.398438 ..
CCV_NNC_GROUP_NORM_FORWARD [775]: [3] -> [3] (0)
|-> 1. 0x1438addd0 (0x285da6f00:0) [2x16x16x1280] -0.212891 -2.810547 3.398438 ..
|-> 2. 0x1438c73d0 (0x285d98ac0:0) [1x1x1x1280] 0.395020 0.388428 0.350342 ..
|-> 3. 0x1438c7440 (0x285d98b00:0) [1x1x1x1280] -0.027878 0.102356 -0.030334 ..
|<- 1. 0x1438ade40 (0x285da6dc0:0) [2x16x16x1280] -0.145264 -0.454102 0.418457 ..
|<- 2. 0x1438adeb0 (0x285da68c0:0) [2x1x1x32] 0.467285 0.628418 0.006485 ..
|<- 3. 0x1438adf20 (0x285da6880:0) [2x1x1x32] 0.437012 0.450928 0.450439 ..
CCV_NNC_CONVOLUTION_FORWARD [776]: [3] -> [1] (0)
|-> 1. 0x1438ade40 (0x285da6dc0:0) [2x16x16x1280] -0.145264 -0.454102 0.418457 ..
|-> 2. 0x1438c74b0 (0x285d98b40:0) [1280x1280x1x1] 0.041748 ..
|-> 3. 0x1438c7520 (0x285d98b80:0) [1280] 0.007435 0.066956 -0.078247 ..
|<- 1. 0x1438adf90 (0x285da6fc0:0) [2x16x16x1280] 0.678711 2.390625 -1.073242 ..
CCV_NNC_LAYER_NORM_FORWARD [777]: [3] -> [3] (0)
|-> 1. 0x1438ed510 (0x285da6fc0:0) [2x256x1280] 0.678711 2.390625 -1.073242 ..
|-> 2. 0x1438c7590 (0x285d98bc0:0) [1x1x1280] 0.378906 0.375977 0.333496 ..
|-> 3. 0x1438c7600 (0x285d98c00:0) [1x1x1280] -0.024811 -0.004536 0.049866 ..
|<- 1. 0x1438ae000 (0x285da6dc0:0) [2x256x1280] 0.144531 0.608398 -0.205078 ..
|<- 2. 0x1438ae070 (0x285d83e80:0) [2x256x1] 0.032318 ..
|<- 3. 0x1438ae0e0 (0x285d834c0:0) [2x256x1] 0.691406 ..
Emit: (0, 77)
CCV_NNC_GEMM_FORWARD [778]: [2] -> [1] (0)
|-> 1. 0x1438ae000 (0x285da6dc0:0) [2x256x1280] 0.144531 0.608398 -0.205078 ..
|-> 2. 0x1438c7670 (0x285d98c40:0) [1280x1280] -0.094116 0.131348 0.006405 ..
|<- 1. 0x1438ae150 (0x285da7080:0) [2x256x1280] -1.230469 0.131470 -1.105469 ..
CCV_NNC_SCALAR_MUL_FORWARD [779]: [1] -> [1] (0)
|-> 1. 0x1438ae150 (0x285da7080:0) [2x256x1280] -1.230469 0.131470 -1.105469 ..
|<- 1. 0x1438ae150 (0x285da7080:0) [2x256x1280] -0.097229 0.010391 -0.087402 ..
CCV_NNC_TRANSPOSE_FORWARD [780]: [1] -> [1] (0)
|-> 1. 0x1438ed5f0 (0x285da7080:0) [2x256x8x160] -0.097229 0.010391 -0.087402 ..
|<- 1. 0x1438ae2a0 (0x285da7500:0) [2x8x256x160] -0.097229 0.010391 -0.087402 ..
CCV_NNC_GEMM_FORWARD [781]: [2] -> [1] (1)
Wait: (1, 77)
|-> 1. 0x1438ae000 (0x285da6dc0:0) [2x256x1280] 0.144531 0.608398 -0.205078 ..
|-> 2. 0x1438c76e0 (0x285d98c80:0) [1280x1280] -0.054352 -0.041870 -0.058380 ..
|<- 1. 0x1438ae1c0 (0x285da7780:0) [2x256x1280] -0.977051 0.350830 0.115295 ..
CCV_NNC_TRANSPOSE_FORWARD [782]: [1] -> [1] (1)
|-> 1. 0x1438ed580 (0x285da7780:0) [2x256x8x160] -0.977051 0.350830 0.115295 ..
|<- 1. 0x1438ae230 (0x285da6e00:0) [2x8x256x160] -0.977051 0.350830 0.115295 ..
Emit: (1, 78)
CCV_NNC_GEMM_FORWARD [783]: [2] -> [1] (2)
Wait: (2, 77)
|-> 1. 0x1438ae000 (0x285da6dc0:0) [2x256x1280] 0.144531 0.608398 -0.205078 ..
|-> 2. 0x1438c7750 (0x285d98cc0:0) [1280x1280] 0.127930 -0.001692 -0.058960 ..
|<- 1. 0x1438ae310 (0x285da7140:0) [2x256x1280] 0.797852 -0.509766 0.980957 ..
CCV_NNC_TRANSPOSE_FORWARD [784]: [1] -> [1] (2)
|-> 1. 0x1438ed740 (0x285da7140:0) [2x256x8x160] 0.797852 -0.509766 0.980957 ..
|<- 1. 0x1438ae3f0 (0x285da70c0:0) [2x8x256x160] 0.797852 -0.509766 0.980957 ..
Emit: (2, 79)
CCV_NNC_GEMM_FORWARD [785]: [2] -> [1] (0)
Wait: (0, 78)
|-> 1. 0x1438ed6d0 (0x285da7500:0) [1x256x160] -0.097229 0.010391 -0.087402 ..
|-> 2. 0x1438ed660 (0x285da6e00:0) [1x256x160] -0.977051 0.350830 0.115295 ..
|<- 1. 0x1438ae380 (0x285d83fc0:0) [1x256x256] 1.837891 0.683594 1.314453 ..
CCV_NNC_SOFTMAX_FORWARD [786]: [1] -> [1] (0)
|-> 1. 0x1438ed7b0 (0x285d83fc0:0) [256x256] 1.837891 0.683594 1.314453 ..
|<- 1. 0x1438ed7b0 (0x285d83fc0:0) [256x256] 0.007774 0.002451 0.004608 ..
CCV_NNC_GEMM_FORWARD [787]: [2] -> [1] (0)
Wait: (0, 79)
|-> 1. 0x1438ed890 (0x285d83fc0:0) [1x256x256] 0.007774 0.002451 0.004608 ..
|-> 2. 0x1438ed820 (0x285da70c0:0) [1x256x160] 0.797852 -0.509766 0.980957 ..
|<- 1. 0x1438f0510 (0x285da6dc0:0) [1x256x160] 0.364746 -0.385986 0.216309 ..
CCV_NNC_GEMM_FORWARD [788]: [2] -> [1] (0)
|-> 1. 0x1438ed9b0 (0x285da7500:0) [1x256x160] -0.111145 0.151001 0.045044 ..
|-> 2. 0x1438ed900 (0x285da6e00:0) [1x256x160] -0.368896 -0.095337 -0.036163 ..
|<- 1. 0x1438ae460 (0x285d83fc0:0) [1x256x256] 5.625000 3.037109 4.093750 ..
CCV_NNC_SOFTMAX_FORWARD [789]: [1] -> [1] (0)
|-> 1. 0x1438eda60 (0x285d83fc0:0) [256x256] 5.625000 3.037109 4.093750 ..
|<- 1. 0x1438eda60 (0x285d83fc0:0) [256x256] 0.112854 0.008484 0.024399 ..
CCV_NNC_GEMM_FORWARD [790]: [2] -> [1] (0)
|-> 1. 0x1438edb80 (0x285d83fc0:0) [1x256x256] 0.112854 0.008484 0.024399 ..
|-> 2. 0x1438edad0 (0x285da70c0:0) [1x256x160] -0.778809 -0.531250 -0.577637 ..
|<- 1. 0x1438f0580 (0x285da6dc0:0) [1x256x160] -0.312256 -0.344482 -0.180298 ..
CCV_NNC_GEMM_FORWARD [791]: [2] -> [1] (0)
|-> 1. 0x1438edca0 (0x285da7500:0) [1x256x160] 0.022263 0.057800 -0.029083 ..
|-> 2. 0x1438edbf0 (0x285da6e00:0) [1x256x160] -1.000000 0.978027 0.052643 ..
|<- 1. 0x1438ae4d0 (0x285d83fc0:0) [1x256x256] 2.214844 0.110779 1.236328 ..
CCV_NNC_SOFTMAX_FORWARD [792]: [1] -> [1] (0)
|-> 1. 0x1438edd50 (0x285d83fc0:0) [256x256] 2.214844 0.110779 1.236328 ..
|<- 1. 0x1438edd50 (0x285d83fc0:0) [256x256] 0.026764 0.003263 0.010063 ..
CCV_NNC_GEMM_FORWARD [793]: [2] -> [1] (0)
|-> 1. 0x1438ede70 (0x285d83fc0:0) [1x256x256] 0.026764 0.003263 0.010063 ..
|-> 2. 0x1438eddc0 (0x285da70c0:0) [1x256x160] -0.956543 0.541992 0.800781 ..
|<- 1. 0x1438f0630 (0x285da6dc0:0) [1x256x160] -0.204712 0.098877 0.090210 ..
CCV_NNC_GEMM_FORWARD [794]: [2] -> [1] (0)
|-> 1. 0x1438edf90 (0x285da7500:0) [1x256x160] 0.020050 -0.008179 0.035461 ..
|-> 2. 0x1438edee0 (0x285da6e00:0) [1x256x160] -1.206055 0.798828 -0.286621 ..
|<- 1. 0x1438ae540 (0x285d83fc0:0) [1x256x256] 2.001953 1.899414 1.625000 ..
CCV_NNC_SOFTMAX_FORWARD [795]: [1] -> [1] (0)
|-> 1. 0x1438ee040 (0x285d83fc0:0) [256x256] 2.001953 1.899414 1.625000 ..
|<- 1. 0x1438ee040 (0x285d83fc0:0) [256x256] 0.013268 0.011978 0.009102 ..
CCV_NNC_GEMM_FORWARD [796]: [2] -> [1] (0)
|-> 1. 0x1438ee160 (0x285d83fc0:0) [1x256x256] 0.013268 0.011978 0.009102 ..
|-> 2. 0x1438ee0b0 (0x285da70c0:0) [1x256x160] 0.587402 0.912109 0.033264 ..
|<- 1. 0x1438f06e0 (0x285da6dc0:0) [1x256x160] -0.586426 0.127930 0.122009 ..
CCV_NNC_GEMM_FORWARD [797]: [2] -> [1] (0)
|-> 1. 0x1438ee280 (0x285da7500:0) [1x256x160] -0.016830 -0.059692 -0.053040 ..
|-> 2. 0x1438ee1d0 (0x285da6e00:0) [1x256x160] -1.138672 0.018997 -0.366943 ..
|<- 1. 0x1438ae5b0 (0x285d83fc0:0) [1x256x256] 3.019531 0.649902 0.974121 ..
CCV_NNC_SOFTMAX_FORWARD [798]: [1] -> [1] (0)
|-> 1. 0x1438ee330 (0x285d83fc0:0) [256x256] 3.019531 0.649902 0.974121 ..
|<- 1. 0x1438ee330 (0x285d83fc0:0) [256x256] 0.039948 0.003736 0.005165 ..
CCV_NNC_GEMM_FORWARD [799]: [2] -> [1] (0)
|-> 1. 0x1438ee450 (0x285d83fc0:0) [1x256x256] 0.039948 0.003736 0.005165 ..
|-> 2. 0x1438ee3a0 (0x285da70c0:0) [1x256x160] -0.001535 -0.215088 -0.229126 ..
|<- 1. 0x1438f0790 (0x285da6dc0:0) [1x256x160] -0.201904 0.023773 0.121582 ..
CCV_NNC_GEMM_FORWARD [800]: [2] -> [1] (0)
|-> 1. 0x1438ee570 (0x285da7500:0) [1x256x160] 0.043274 -0.020493 -0.025909 ..
|-> 2. 0x1438ee4c0 (0x285da6e00:0) [1x256x160] 1.924805 0.392090 2.083984 ..
|<- 1. 0x1438ae620 (0x285d83fc0:0) [1x256x256] 6.230469 5.019531 3.304688 ..
CCV_NNC_SOFTMAX_FORWARD [801]: [1] -> [1] (0)
|-> 1. 0x1438ee620 (0x285d83fc0:0) [256x256] 6.230469 5.019531 3.304688 ..
|<- 1. 0x1438ee620 (0x285d83fc0:0) [256x256] 0.005970 0.001779 0.000320 ..
CCV_NNC_GEMM_FORWARD [802]: [2] -> [1] (0)
|-> 1. 0x1438ee740 (0x285d83fc0:0) [1x256x256] 0.005970 0.001779 0.000320 ..
|-> 2. 0x1438ee690 (0x285da70c0:0) [1x256x160] 0.452393 -1.077148 1.250000 ..
|<- 1. 0x1438f0840 (0x285da6dc0:0) [1x256x160] 0.919922 -0.720215 0.937012 ..
CCV_NNC_GEMM_FORWARD [803]: [2] -> [1] (0)
|-> 1. 0x1438ee860 (0x285da7500:0) [1x256x160] 0.050568 0.044067 -0.026321 ..
|-> 2. 0x1438ee7b0 (0x285da6e00:0) [1x256x160] -0.879395 -0.274170 -1.352539 ..
|<- 1. 0x1438ae690 (0x285d83fc0:0) [1x256x256] 3.074219 2.117188 2.175781 ..
CCV_NNC_SOFTMAX_FORWARD [804]: [1] -> [1] (0)
|-> 1. 0x1438ee910 (0x285d83fc0:0) [256x256] 3.074219 2.117188 2.175781 ..
|<- 1. 0x1438ee910 (0x285d83fc0:0) [256x256] 0.014877 0.005714 0.006058 ..
CCV_NNC_GEMM_FORWARD [805]: [2] -> [1] (0)
|-> 1. 0x1438eea30 (0x285d83fc0:0) [1x256x256] 0.014877 0.005714 0.006058 ..
|-> 2. 0x1438ee980 (0x285da70c0:0) [1x256x160] -0.046234 2.103516 -0.201294 ..
|<- 1. 0x1438f08f0 (0x285da6dc0:0) [1x256x160] 0.149780 1.164062 -0.080750 ..
CCV_NNC_GEMM_FORWARD [806]: [2] -> [1] (0)
|-> 1. 0x1438eeb50 (0x285da7500:0) [1x256x160] -0.002081 -0.027512 0.003944 ..
|-> 2. 0x1438eeaa0 (0x285da6e00:0) [1x256x160] -0.784180 -0.076111 -0.071716 ..
|<- 1. 0x1438ae700 (0x285d83fc0:0) [1x256x256] 0.780762 0.816406 1.123047 ..
CCV_NNC_SOFTMAX_FORWARD [807]: [1] -> [1] (0)
|-> 1. 0x1438eec00 (0x285d83fc0:0) [256x256] 0.780762 0.816406 1.123047 ..
|<- 1. 0x1438eec00 (0x285d83fc0:0) [256x256] 0.006046 0.006268 0.008514 ..
CCV_NNC_GEMM_FORWARD [808]: [2] -> [1] (0)
|-> 1. 0x1438eed20 (0x285d83fc0:0) [1x256x256] 0.006046 0.006268 0.008514 ..
|-> 2. 0x1438eec70 (0x285da70c0:0) [1x256x160] -0.323730 0.242554 0.097473 ..
|<- 1. 0x1438f09a0 (0x285da6dc0:0) [1x256x160] 0.073914 -0.234619 0.310791 ..
CCV_NNC_GEMM_FORWARD [809]: [2] -> [1] (0)
|-> 1. 0x1438eee40 (0x285da7500:0) [1x256x160] -0.040222 -0.049011 -0.090698 ..
|-> 2. 0x1438eed90 (0x285da6e00:0) [1x256x160] -1.046875 0.098083 -0.772949 ..
|<- 1. 0x1438ae770 (0x285d83fc0:0) [1x256x256] 2.845703 1.583008 2.462891 ..
CCV_NNC_SOFTMAX_FORWARD [810]: [1] -> [1] (0)
|-> 1. 0x1438eeef0 (0x285d83fc0:0) [256x256] 2.845703 1.583008 2.462891 ..
|<- 1. 0x1438eeef0 (0x285d83fc0:0) [256x256] 0.014992 0.004242 0.010223 ..
CCV_NNC_GEMM_FORWARD [811]: [2] -> [1] (0)
|-> 1. 0x1438ef010 (0x285d83fc0:0) [1x256x256] 0.014992 0.004242 0.010223 ..
|-> 2. 0x1438eef60 (0x285da70c0:0) [1x256x160] 0.053955 0.563477 0.208740 ..
|<- 1. 0x1438f0a50 (0x285da6dc0:0) [1x256x160] 0.055420 0.112061 -0.152710 ..
CCV_NNC_GEMM_FORWARD [812]: [2] -> [1] (0)
|-> 1. 0x1438ef130 (0x285da7500:0) [1x256x160] -0.157349 0.186890 0.054047 ..
|-> 2. 0x1438ef080 (0x285da6e00:0) [1x256x160] -0.219360 1.715820 0.469238 ..
|<- 1. 0x1438ae7e0 (0x285d83fc0:0) [1x256x256] 6.277344 4.453125 4.957031 ..
CCV_NNC_SOFTMAX_FORWARD [813]: [1] -> [1] (0)
|-> 1. 0x1438ef1e0 (0x285d83fc0:0) [256x256] 6.277344 4.453125 4.957031 ..
|<- 1. 0x1438ef1e0 (0x285d83fc0:0) [256x256] 0.141846 0.022888 0.037872 ..
CCV_NNC_GEMM_FORWARD [814]: [2] -> [1] (0)
|-> 1. 0x1438ef300 (0x285d83fc0:0) [1x256x256] 0.141846 0.022888 0.037872 ..
|-> 2. 0x1438ef250 (0x285da70c0:0) [1x256x160] -0.645508 -0.892578 -0.301514 ..
|<- 1. 0x1438f0b00 (0x285da6dc0:0) [1x256x160] -0.305664 -0.284180 -0.002802 ..
CCV_NNC_GEMM_FORWARD [815]: [2] -> [1] (0)
|-> 1. 0x1438ef420 (0x285da7500:0) [1x256x160] 0.025024 0.077209 -0.010094 ..
|-> 2. 0x1438ef370 (0x285da6e00:0) [1x256x160] -1.068359 1.015625 -0.277588 ..
|<- 1. 0x1438ae850 (0x285d83fc0:0) [1x256x256] 2.062500 0.636230 0.935059 ..
CCV_NNC_SOFTMAX_FORWARD [816]: [1] -> [1] (0)
|-> 1. 0x1438ef4d0 (0x285d83fc0:0) [256x256] 2.062500 0.636230 0.935059 ..
|<- 1. 0x1438ef4d0 (0x285d83fc0:0) [256x256] 0.029373 0.007057 0.009514 ..
CCV_NNC_GEMM_FORWARD [817]: [2] -> [1] (0)
|-> 1. 0x1438ef5f0 (0x285d83fc0:0) [1x256x256] 0.029373 0.007057 0.009514 ..
|-> 2. 0x1438ef540 (0x285da70c0:0) [1x256x160] -0.634277 -0.051025 0.321289 ..
|<- 1. 0x1438f0bb0 (0x285da6dc0:0) [1x256x160] -0.340332 0.054749 -0.124268 ..
CCV_NNC_GEMM_FORWARD [818]: [2] -> [1] (0)
|-> 1. 0x1438ef710 (0x285da7500:0) [1x256x160] -0.004372 -0.009995 0.077332 ..
|-> 2. 0x1438ef660 (0x285da6e00:0) [1x256x160] -0.905273 0.640137 0.302979 ..
|<- 1. 0x1438ae8c0 (0x285d83fc0:0) [1x256x256] 1.789062 1.703125 1.392578 ..
CCV_NNC_SOFTMAX_FORWARD [819]: [1] -> [1] (0)
|-> 1. 0x1438ef7c0 (0x285d83fc0:0) [256x256] 1.789062 1.703125 1.392578 ..
|<- 1. 0x1438ef7c0 (0x285d83fc0:0) [256x256] 0.013611 0.012489 0.009155 ..
CCV_NNC_GEMM_FORWARD [820]: [2] -> [1] (0)
|-> 1. 0x1438ef8e0 (0x285d83fc0:0) [1x256x256] 0.013611 0.012489 0.009155 ..
|-> 2. 0x1438ef830 (0x285da70c0:0) [1x256x160] -0.277832 1.210938 0.048462 ..
|<- 1. 0x1438f0c60 (0x285da6dc0:0) [1x256x160] -1.001953 0.776367 -0.247070 ..
CCV_NNC_GEMM_FORWARD [821]: [2] -> [1] (0)
|-> 1. 0x1438efa00 (0x285da7500:0) [1x256x160] 0.004326 -0.096436 -0.056488 ..
|-> 2. 0x1438ef950 (0x285da6e00:0) [1x256x160] -1.696289 0.476807 -0.458740 ..
|<- 1. 0x1438ae930 (0x285d83fc0:0) [1x256x256] 2.646484 0.925781 1.340820 ..
CCV_NNC_SOFTMAX_FORWARD [822]: [1] -> [1] (0)
|-> 1. 0x1438efab0 (0x285d83fc0:0) [256x256] 2.646484 0.925781 1.340820 ..
|<- 1. 0x1438efab0 (0x285d83fc0:0) [256x256] 0.038635 0.006916 0.010475 ..
CCV_NNC_GEMM_FORWARD [823]: [2] -> [1] (0)
|-> 1. 0x1438efbd0 (0x285d83fc0:0) [1x256x256] 0.038635 0.006916 0.010475 ..
|-> 2. 0x1438efb20 (0x285da70c0:0) [1x256x160] 0.293701 -0.098877 0.205200 ..
|<- 1. 0x1438f0d10 (0x285da6dc0:0) [1x256x160] 0.208740 0.450928 -0.202515 ..
CCV_NNC_GEMM_FORWARD [824]: [2] -> [1] (0)
|-> 1. 0x1438efcf0 (0x285da7500:0) [1x256x160] 0.085083 -0.038391 -0.026459 ..
|-> 2. 0x1438efc40 (0x285da6e00:0) [1x256x160] 2.134766 0.100403 1.511719 ..
|<- 1. 0x1438ae9a0 (0x285d83fc0:0) [1x256x256] 5.089844 4.433594 2.892578 ..
CCV_NNC_SOFTMAX_FORWARD [825]: [1] -> [1] (0)
|-> 1. 0x1438efda0 (0x285d83fc0:0) [256x256] 5.089844 4.433594 2.892578 ..
|<- 1. 0x1438efda0 (0x285d83fc0:0) [256x256] 0.005680 0.002947 0.000631 ..
CCV_NNC_GEMM_FORWARD [826]: [2] -> [1] (0)
|-> 1. 0x1438efec0 (0x285d83fc0:0) [1x256x256] 0.005680 0.002947 0.000631 ..
|-> 2. 0x1438efe10 (0x285da70c0:0) [1x256x160] 0.164673 -0.422852 0.826172 ..
|<- 1. 0x1438f0dc0 (0x285da6dc0:0) [1x256x160] 0.187012 -0.315674 0.334961 ..
CCV_NNC_GEMM_FORWARD [827]: [2] -> [1] (0)
|-> 1. 0x1438effe0 (0x285da7500:0) [1x256x160] -0.060486 0.004742 -0.054596 ..
|-> 2. 0x1438eff30 (0x285da6e00:0) [1x256x160] -1.120117 0.085571 -1.927734 ..
|<- 1. 0x1438aea10 (0x285d83fc0:0) [1x256x256] 3.791016 3.039062 3.162109 ..
CCV_NNC_SOFTMAX_FORWARD [828]: [1] -> [1] (0)
|-> 1. 0x1438f0090 (0x285d83fc0:0) [256x256] 3.791016 3.039062 3.162109 ..
|<- 1. 0x1438f0090 (0x285d83fc0:0) [256x256] 0.026489 0.012489 0.014130 ..
CCV_NNC_GEMM_FORWARD [829]: [2] -> [1] (0)
|-> 1. 0x1438f01b0 (0x285d83fc0:0) [1x256x256] 0.026489 0.012489 0.014130 ..
|-> 2. 0x1438f0100 (0x285da70c0:0) [1x256x160] 0.499268 1.361328 -0.416748 ..
|<- 1. 0x1438f0e70 (0x285da6dc0:0) [1x256x160] -0.390869 0.373779 -0.276367 ..
CCV_NNC_GEMM_FORWARD [830]: [2] -> [1] (0)
|-> 1. 0x1438f02d0 (0x285da7500:0) [1x256x160] -0.018173 -0.080750 0.021454 ..
|-> 2. 0x1438f0220 (0x285da6e00:0) [1x256x160] -0.611328 0.277100 -0.175903 ..
|<- 1. 0x1438aea80 (0x285d83fc0:0) [1x256x256] 1.108398 0.464600 0.718262 ..
CCV_NNC_SOFTMAX_FORWARD [831]: [1] -> [1] (0)
|-> 1. 0x1438f0380 (0x285d83fc0:0) [256x256] 1.108398 0.464600 0.718262 ..
|<- 1. 0x1438f0380 (0x285d83fc0:0) [256x256] 0.009308 0.004890 0.006302 ..
CCV_NNC_GEMM_FORWARD [832]: [2] -> [1] (0)
|-> 1. 0x1438f04a0 (0x285d83fc0:0) [1x256x256] 0.009308 0.004890 0.006302 ..
|-> 2. 0x1438f03f0 (0x285da70c0:0) [1x256x160] -0.258789 0.306641 0.349854 ..
|<- 1. 0x1438f0f20 (0x285da6dc0:0) [1x256x160] 0.326904 -0.288818 0.585938 ..
CCV_NNC_TRANSPOSE_FORWARD [833]: [1] -> [1] (0)
|-> 1. 0x1438f0fd0 (0x285da6dc0:0) [2x8x256x160] 0.364746 -0.385986 0.216309 ..
|<- 1. 0x1438aeb60 (0x285da70c0:0) [2x256x8x160] 0.364746 -0.385986 0.216309 ..
CCV_NNC_GEMM_FORWARD [834]: [3] -> [1] (0)
|-> 1. 0x1438f1040 (0x285da70c0:0) [2x256x1280] 0.364746 -0.385986 0.216309 ..
|-> 2. 0x1438c77c0 (0x285d98d00:0) [1280x1280] 0.016434 -0.077148 0.020355 ..
|-> 3. 0x1438c7830 (0x285d98d40:0) [1280] 0.002987 0.038025 -0.099487 ..
|<- 1. 0x1438aebd0 (0x285da6dc0:0) [2x256x1280] -0.197876 -0.065247 0.722656 ..
CCV_NNC_ADD_FORWARD [835]: [2] -> [1] (0)
|-> 1. 0x1438aebd0 (0x285da6dc0:0) [2x256x1280] -0.197876 -0.065247 0.722656 ..
|-> 2. 0x1438ed510 (0x285da6fc0:0) [2x256x1280] 0.678711 2.390625 -1.073242 ..
|<- 1. 0x1438aebd0 (0x285da6dc0:0) [2x256x1280] 0.480957 2.326172 -0.350586 ..
CCV_NNC_LAYER_NORM_FORWARD [836]: [3] -> [3] (0)
|-> 1. 0x1438aebd0 (0x285da6dc0:0) [2x256x1280] 0.480957 2.326172 -0.350586 ..
|-> 2. 0x1438c78a0 (0x285d98d80:0) [1x1x1280] 0.500977 0.479004 0.469727 ..
|-> 3. 0x1438c7910 (0x285d98dc0:0) [1x1x1280] 0.012978 0.008415 0.208862 ..
|<- 1. 0x1438aec40 (0x285da6fc0:0) [2x256x1280] 0.179199 0.820312 0.076111 ..
|<- 2. 0x1438aecb0 (0x285d83940:0) [2x256x1] 0.031891 ..
|<- 3. 0x1438aed20 (0x285d80b00:0) [2x256x1] 0.738770 ..
CCV_NNC_GEMM_FORWARD [837]: [2] -> [1] (0)
|-> 1. 0x1438aec40 (0x285da6fc0:0) [2x256x1280] 0.179199 0.820312 0.076111 ..
|-> 2. 0x1438c7980 (0x285d98e00:0) [1280x1280] -0.025284 0.010193 -0.075134 ..
|<- 1. 0x1438aed90 (0x285da70c0:0) [2x256x1280] -0.555664 0.656738 0.446777 ..
CCV_NNC_SCALAR_MUL_FORWARD [838]: [1] -> [1] (0)
|-> 1. 0x1438aed90 (0x285da70c0:0) [2x256x1280] -0.555664 0.656738 0.446777 ..
|<- 1. 0x1438aed90 (0x285da70c0:0) [2x256x1280] -0.043915 0.051910 0.035309 ..
CCV_NNC_TRANSPOSE_FORWARD [839]: [1] -> [1] (0)
|-> 1. 0x1438f1120 (0x285da70c0:0) [2x256x8x160] -0.043915 0.051910 0.035309 ..
|<- 1. 0x1438aeee0 (0x285da6fc0:0) [2x8x256x160] -0.043915 0.051910 0.035309 ..
CCV_NNC_GEMM_FORWARD [840]: [2] -> [1] (0)
Wait: (0, 80)
|-> 1. 0x1438aeee0 (0x285da6fc0:0) [2x8x256x160] -0.043915 0.051910 0.035309 ..
|-> 2. 0x1438aee70 (0x285d83e40:0) [2x8x133x160] -0.494141 0.059296 0.135498 ..
|<- 1. 0x1438aef50 (0x285d83540:0) [2x8x256x133] 6.062500 -1.798828 -0.122437 ..
CCV_NNC_SOFTMAX_FORWARD [841]: [1] -> [1] (0)
|-> 1. 0x1438f1190 (0x285d83540:0) [4096x133] 6.062500 -1.798828 -0.122437 ..
|<- 1. 0x1438f1190 (0x285d83540:0) [4096x133] 0.677246 0.000261 0.001395 ..
CCV_NNC_GEMM_FORWARD [842]: [2] -> [1] (0)
Wait: (0, 81)
|-> 1. 0x1438f1270 (0x285d83540:0) [2x8x256x133] 0.677246 0.000261 0.001395 ..
|-> 2. 0x1438af030 (0x285d83ec0:0) [2x8x133x160] 0.102844 -0.059814 -0.027191 ..
|<- 1. 0x1438af0a0 (0x285da6fc0:0) [2x8x256x160] -0.012550 -0.268311 0.122009 ..
CCV_NNC_TRANSPOSE_FORWARD [843]: [1] -> [1] (0)
|-> 1. 0x1438f12e0 (0x285da6fc0:0) [2x8x256x160] -0.012550 -0.268311 0.122009 ..
|<- 1. 0x1438af110 (0x285da70c0:0) [2x256x8x160] -0.012550 -0.268311 0.122009 ..
CCV_NNC_GEMM_FORWARD [844]: [3] -> [1] (0)
|-> 1. 0x1438f1350 (0x285da70c0:0) [2x256x1280] -0.012550 -0.268311 0.122009 ..
|-> 2. 0x1438c7ad0 (0x285d98ec0:0) [1280x1280] -0.001011 -0.007881 -0.016693 ..
|-> 3. 0x1438c7b40 (0x285d98f00:0) [1280] 0.006691 0.031921 -0.131836 ..
|<- 1. 0x1438af180 (0x285da7780:0) [2x256x1280] -0.590332 0.661133 0.108337 ..
CCV_NNC_ADD_FORWARD [845]: [2] -> [1] (0)
|-> 1. 0x1438af180 (0x285da7780:0) [2x256x1280] -0.590332 0.661133 0.108337 ..
|-> 2. 0x1438aebd0 (0x285da6dc0:0) [2x256x1280] 0.480957 2.326172 -0.350586 ..
|<- 1. 0x1438af180 (0x285da7780:0) [2x256x1280] -0.109375 2.988281 -0.242188 ..
CCV_NNC_LAYER_NORM_FORWARD [846]: [3] -> [3] (0)
|-> 1. 0x1438af180 (0x285da7780:0) [2x256x1280] -0.109375 2.988281 -0.242188 ..
|-> 2. 0x1438c7bb0 (0x285d98f40:0) [1x1x1280] 0.354492 0.348877 0.344238 ..
|-> 3. 0x1438c7c20 (0x285d98f80:0) [1x1x1280] -0.005108 0.008896 0.161865 ..
|<- 1. 0x1438af1f0 (0x285da77c0:0) [2x256x1280] -0.038788 0.726074 0.097412 ..
|<- 2. 0x1438af260 (0x285da7840:0) [2x256x1] 0.027420 ..
|<- 3. 0x1438af2d0 (0x285da7800:0) [2x256x1] 0.694336 ..
Emit: (0, 82)
CCV_NNC_GEMM_FORWARD [847]: [3] -> [1] (0)
|-> 1. 0x1438af1f0 (0x285da77c0:0) [2x256x1280] -0.038788 0.726074 0.097412 ..
|-> 2. 0x1438c7c90 (0x285d98fc0:0) [5120x1280] -0.039062 -0.002144 0.062469 ..
|-> 3. 0x1438c7d00 (0x285d99000:0) [5120] -0.186279 -0.025879 -0.049347 ..
|<- 1. 0x1438af340 (0x285da7380:0) [2x256x5120] -1.599609 -1.189453 0.044434 ..
CCV_NNC_GELU_FORWARD [848]: [1] -> [1] (0)
|-> 1. 0x1438af340 (0x285da7380:0) [2x256x5120] -1.599609 -1.189453 0.044434 ..
|<- 1. 0x1438af340 (0x285da7380:0) [2x256x5120] -0.087769 -0.139404 0.023010 ..
CCV_NNC_GEMM_FORWARD [849]: [3] -> [1] (1)
Wait: (1, 82)
|-> 1. 0x1438af1f0 (0x285da77c0:0) [2x256x1280] -0.038788 0.726074 0.097412 ..
|-> 2. 0x1438c7d70 (0x285d99040:0) [5120x1280] 0.044525 -0.087646 0.074829 ..
|-> 3. 0x1438c7de0 (0x285d99080:0) [5120] 0.006046 0.012978 0.036591 ..
|<- 1. 0x1438af3b0 (0x285da5ac0:0) [2x256x5120] 0.524414 -0.193848 0.732910 ..
Emit: (1, 83)
CCV_NNC_MUL_FORWARD [850]: [2] -> [1] (0)
Wait: (0, 83)
|-> 1. 0x1438af3b0 (0x285da5ac0:0) [2x256x5120] 0.524414 -0.193848 0.732910 ..
|-> 2. 0x1438af340 (0x285da7380:0) [2x256x5120] -0.087769 -0.139404 0.023010 ..
|<- 1. 0x1438af3b0 (0x285da5ac0:0) [2x256x5120] -0.046021 0.027023 0.016861 ..
CCV_NNC_GEMM_FORWARD [851]: [3] -> [1] (0)
|-> 1. 0x1438af3b0 (0x285da5ac0:0) [2x256x5120] -0.046021 0.027023 0.016861 ..
|-> 2. 0x1438c7e50 (0x285d990c0:0) [1280x5120] -0.086914 0.069763 0.017136 ..
|-> 3. 0x1438c7ec0 (0x285d99100:0) [1280] 0.010849 0.039734 -0.011353 ..
|<- 1. 0x1438af420 (0x285da6dc0:0) [2x256x1280] -2.494141 -1.386719 0.458008 ..
CCV_NNC_ADD_FORWARD [852]: [2] -> [1] (0)
|-> 1. 0x1438af420 (0x285da6dc0:0) [2x256x1280] -2.494141 -1.386719 0.458008 ..
|-> 2. 0x1438af180 (0x285da7780:0) [2x256x1280] -0.109375 2.988281 -0.242188 ..
|<- 1. 0x1438af420 (0x285da6dc0:0) [2x256x1280] -2.603516 1.601562 0.215820 ..
CCV_NNC_CONVOLUTION_FORWARD [853]: [3] -> [1] (0)
|-> 1. 0x1438f13c0 (0x285da6dc0:0) [2x16x16x1280] -2.603516 1.601562 0.215820 ..
|-> 2. 0x1438c7f30 (0x285d99140:0) [1280x1280x1x1] -0.070496 ..
|-> 3. 0x1438c7fa0 (0x285d99180:0) [1280] -0.001201 0.070862 -0.042175 ..
|<- 1. 0x1438af490 (0x285da6e00:0) [2x16x16x1280] 1.289062 -0.592773 5.378906 ..
CCV_NNC_ADD_FORWARD [854]: [2] -> [1] (0)
|-> 1. 0x1438af490 (0x285da6e00:0) [2x16x16x1280] 1.289062 -0.592773 5.378906 ..
|-> 2. 0x1438addd0 (0x285da6f00:0) [2x16x16x1280] -0.212891 -2.810547 3.398438 ..
|<- 1. 0x1438f1430 (0x285da64c0:0) [2x16x16x1280] 1.076172 -3.402344 8.781250 ..
Emit: (0, 85)
CCV_NNC_GROUP_NORM_FORWARD [855]: [3] -> [3] (0)
|-> 1. 0x1438af500 (0x285da64c0:0) [2x16x16x2560] 1.076172 -3.402344 8.781250 ..
|-> 2. 0x1438c8010 (0x285d991c0:0) [1x1x1x2560] 0.357666 0.439209 0.366455 ..
|-> 3. 0x1438c8080 (0x285d99200:0) [1x1x1x2560] -0.041962 -0.113037 -0.022552 ..
|<- 1. 0x1438af570 (0x285da61c0:0) [2x16x16x2560] 0.055145 -0.793457 1.224609 ..
|<- 2. 0x1438af5e0 (0x285da67c0:0) [2x1x1x32] 0.408203 0.363525 0.025787 ..
|<- 3. 0x1438af650 (0x285da6800:0) [2x1x1x32] 0.406494 0.436768 0.381592 ..
CCV_NNC_SWISH_FORWARD [856]: [1] -> [1] (0)
|-> 1. 0x1438af570 (0x285da61c0:0) [2x16x16x2560] 0.055145 -0.793457 1.224609 ..
|<- 1. 0x1438af570 (0x285da61c0:0) [2x16x16x2560] 0.028336 -0.247070 0.946289 ..
CCV_NNC_CONVOLUTION_FORWARD [857]: [3] -> [1] (0)
|-> 1. 0x1438af570 (0x285da61c0:0) [2x16x16x2560] 0.028336 -0.247070 0.946289 ..
|-> 2. 0x1438c81d0 (0x285d992c0:0) [1280x2560x3x3] -0.032288 -0.022507 0.039398 ..
|-> 3. 0x1438c8240 (0x285d99300:0) [1280] 0.070435 0.076294 -0.011490 ..
|<- 1. 0x1438af730 (0x285da6dc0:0) [2x16x16x1280] 3.599609 4.054688 -1.112305 ..
CCV_NNC_ADD_FORWARD [858]: [2] -> [1] (0)
Wait: (0, 84)
|-> 1. 0x1438af730 (0x285da6dc0:0) [2x16x16x1280] 3.599609 4.054688 -1.112305 ..
|-> 2. 0x1438f1590 (0x285d83f40:0) [2x1x1x1280] -0.230713 0.213135 -0.136353 ..
|<- 1. 0x1438af730 (0x285da6dc0:0) [2x16x16x1280] 3.369141 4.269531 -1.249023 ..
CCV_NNC_GROUP_NORM_FORWARD [859]: [3] -> [3] (0)
|-> 1. 0x1438af730 (0x285da6dc0:0) [2x16x16x1280] 3.369141 4.269531 -1.249023 ..
|-> 2. 0x1438c82b0 (0x285d99340:0) [1x1x1x1280] 0.518066 0.552246 0.994141 ..
|-> 3. 0x1438c8320 (0x285d99380:0) [1x1x1x1280] -0.338623 -0.303955 -0.566895 ..
|<- 1. 0x1438af7a0 (0x285da6e00:0) [2x16x16x1280] 0.299316 0.628906 -1.678711 ..
|<- 2. 0x1438af810 (0x285d83f00:0) [2x1x1x32] 0.949219 0.635742 1.174805 ..
|<- 3. 0x1438af880 (0x285d83c80:0) [2x1x1x32] 0.508789 0.510254 0.586914 ..
CCV_NNC_SWISH_FORWARD [860]: [1] -> [1] (0)
|-> 1. 0x1438af7a0 (0x285da6e00:0) [2x16x16x1280] 0.299316 0.628906 -1.678711 ..
|<- 1. 0x1438af7a0 (0x285da6e00:0) [2x16x16x1280] 0.171875 0.410156 -0.263916 ..
CCV_NNC_CONVOLUTION_FORWARD [861]: [3] -> [1] (0)
|-> 1. 0x1438af7a0 (0x285da6e00:0) [2x16x16x1280] 0.171875 0.410156 -0.263916 ..
|-> 2. 0x1438c8390 (0x285d993c0:0) [1280x1280x3x3] 0.041443 0.061768 0.032532 ..
|-> 3. 0x1438c8400 (0x285d99400:0) [1280] 0.032562 0.042175 0.009171 ..
|<- 1. 0x1438af8f0 (0x285da6dc0:0) [2x16x16x1280] -3.492188 0.046509 -0.402344 ..
CCV_NNC_CONVOLUTION_FORWARD [862]: [3] -> [1] (1)
Wait: (1, 85)
|-> 1. 0x1438af500 (0x285da64c0:0) [2x16x16x2560] 1.076172 -3.402344 8.781250 ..
|-> 2. 0x1438c8470 (0x285d99440:0) [1280x2560x1x1] -0.024002 ..
|-> 3. 0x1438c84e0 (0x285d99480:0) [1280] 0.035889 0.044037 0.012260 ..
|<- 1. 0x1438af960 (0x285da6f00:0) [2x16x16x1280] -1.852539 6.878906 -4.097656 ..
Emit: (1, 86)
CCV_NNC_ADD_FORWARD [863]: [2] -> [1] (0)
Wait: (0, 86)
|-> 1. 0x1438af960 (0x285da6f00:0) [2x16x16x1280] -1.852539 6.878906 -4.097656 ..
|-> 2. 0x1438af8f0 (0x285da6dc0:0) [2x16x16x1280] -3.492188 0.046509 -0.402344 ..
|<- 1. 0x1438af960 (0x285da6f00:0) [2x16x16x1280] -5.343750 6.925781 -4.500000 ..
CCV_NNC_GROUP_NORM_FORWARD [864]: [3] -> [3] (0)
|-> 1. 0x1438af960 (0x285da6f00:0) [2x16x16x1280] -5.343750 6.925781 -4.500000 ..
|-> 2. 0x1438c8550 (0x285d994c0:0) [1x1x1x1280] 0.398926 0.397217 0.397949 ..
|-> 3. 0x1438c85c0 (0x285d99500:0) [1x1x1x1280] 0.099426 0.062744 -0.002895 ..
|<- 1. 0x1438af9d0 (0x285da6dc0:0) [2x16x16x1280] -0.752441 1.158203 -0.718750 ..
|<- 2. 0x1438afa40 (0x285da6140:0) [2x1x1x32] 0.010361 0.348389 -0.304199 ..
|<- 3. 0x1438afab0 (0x285da6100:0) [2x1x1x32] 0.398926 0.368164 0.340332 ..
CCV_NNC_CONVOLUTION_FORWARD [865]: [3] -> [1] (0)
|-> 1. 0x1438af9d0 (0x285da6dc0:0) [2x16x16x1280] -0.752441 1.158203 -0.718750 ..
|-> 2. 0x1438c8630 (0x285d99540:0) [1280x1280x1x1] 0.045197 ..
|-> 3. 0x1438c86a0 (0x285d99580:0) [1280] -0.030960 0.120422 -0.045044 ..
|<- 1. 0x1438afb20 (0x285da6e00:0) [2x16x16x1280] -0.554199 -2.144531 -2.298828 ..
CCV_NNC_LAYER_NORM_FORWARD [866]: [3] -> [3] (0)
|-> 1. 0x1438f1600 (0x285da6e00:0) [2x256x1280] -0.554199 -2.144531 -2.298828 ..
|-> 2. 0x1438c8710 (0x285d995c0:0) [1x1x1280] 0.323975 0.366943 0.323242 ..
|-> 3. 0x1438c8780 (0x285d99600:0) [1x1x1280] -0.026993 0.017227 0.040405 ..
|<- 1. 0x1438afb90 (0x285da6dc0:0) [2x256x1280] -0.112793 -0.431396 -0.384766 ..
|<- 2. 0x1438afc00 (0x285d83940:0) [2x256x1] -0.114319 ..
|<- 3. 0x1438afc70 (0x285d80b00:0) [2x256x1] 0.602051 ..
Emit: (0, 87)
CCV_NNC_GEMM_FORWARD [867]: [2] -> [1] (0)
|-> 1. 0x1438afb90 (0x285da6dc0:0) [2x256x1280] -0.112793 -0.431396 -0.384766 ..
|-> 2. 0x1438c87f0 (0x285d99640:0) [1280x1280] -0.079041 0.136353 -0.024612 ..
|<- 1. 0x1438afce0 (0x285da7080:0) [2x256x1280] 0.639160 1.525391 0.189331 ..
CCV_NNC_SCALAR_MUL_FORWARD [868]: [1] -> [1] (0)
|-> 1. 0x1438afce0 (0x285da7080:0) [2x256x1280] 0.639160 1.525391 0.189331 ..
|<- 1. 0x1438afce0 (0x285da7080:0) [2x256x1280] 0.050507 0.120544 0.014961 ..
CCV_NNC_TRANSPOSE_FORWARD [869]: [1] -> [1] (0)
|-> 1. 0x1438f16e0 (0x285da7080:0) [2x256x8x160] 0.050507 0.120544 0.014961 ..
|<- 1. 0x1438afe30 (0x285da6fc0:0) [2x8x256x160] 0.050507 0.120544 0.014961 ..
CCV_NNC_GEMM_FORWARD [870]: [2] -> [1] (1)
Wait: (1, 87)
|-> 1. 0x1438afb90 (0x285da6dc0:0) [2x256x1280] -0.112793 -0.431396 -0.384766 ..
|-> 2. 0x1438c8860 (0x285d99680:0) [1280x1280] -0.004429 0.031113 0.028229 ..
|<- 1. 0x1438afd50 (0x285da7000:0) [2x256x1280] 1.949219 2.984375 1.569336 ..
CCV_NNC_TRANSPOSE_FORWARD [871]: [1] -> [1] (1)
|-> 1. 0x1438f1670 (0x285da7000:0) [2x256x8x160] 1.949219 2.984375 1.569336 ..
|<- 1. 0x1438afdc0 (0x285da7500:0) [2x8x256x160] 1.949219 2.984375 1.569336 ..
Emit: (1, 88)
CCV_NNC_GEMM_FORWARD [872]: [2] -> [1] (2)
Wait: (2, 87)
|-> 1. 0x1438afb90 (0x285da6dc0:0) [2x256x1280] -0.112793 -0.431396 -0.384766 ..
|-> 2. 0x1438c88d0 (0x285d996c0:0) [1280x1280] 0.040771 0.018997 0.008034 ..
|<- 1. 0x1438afea0 (0x285da7140:0) [2x256x1280] 0.170532 -0.477051 -0.034088 ..
CCV_NNC_TRANSPOSE_FORWARD [873]: [1] -> [1] (2)
|-> 1. 0x1438f1830 (0x285da7140:0) [2x256x8x160] 0.170532 -0.477051 -0.034088 ..
|<- 1. 0x1438aff80 (0x285da70c0:0) [2x8x256x160] 0.170532 -0.477051 -0.034088 ..
Emit: (2, 89)
CCV_NNC_GEMM_FORWARD [874]: [2] -> [1] (0)
Wait: (0, 88)
|-> 1. 0x1438f17c0 (0x285da6fc0:0) [1x256x160] 0.050507 0.120544 0.014961 ..
|-> 2. 0x1438f1750 (0x285da7500:0) [1x256x160] 1.949219 2.984375 1.569336 ..
|<- 1. 0x1438aff10 (0x285da7100:0) [1x256x256] 10.070312 6.820312 6.746094 ..
CCV_NNC_SOFTMAX_FORWARD [875]: [1] -> [1] (0)
|-> 1. 0x1438f18a0 (0x285da7100:0) [256x256] 10.070312 6.820312 6.746094 ..
|<- 1. 0x1438f18a0 (0x285da7100:0) [256x256] 0.620117 0.024048 0.022324 ..
CCV_NNC_GEMM_FORWARD [876]: [2] -> [1] (0)
Wait: (0, 89)
|-> 1. 0x1438f1980 (0x285da7100:0) [1x256x256] 0.620117 0.024048 0.022324 ..
|-> 2. 0x1438f1910 (0x285da70c0:0) [1x256x160] 0.170532 -0.477051 -0.034088 ..
|<- 1. 0x1438f4600 (0x285da6dc0:0) [1x256x160] 0.072632 -0.516113 -0.109436 ..
CCV_NNC_GEMM_FORWARD [877]: [2] -> [1] (0)
|-> 1. 0x1438f1aa0 (0x285da6fc0:0) [1x256x160] 0.043060 -0.016678 -0.030396 ..
|-> 2. 0x1438f19f0 (0x285da7500:0) [1x256x160] -0.232300 0.495605 1.078125 ..
|<- 1. 0x1438afff0 (0x285da7100:0) [1x256x256] 7.539062 3.177734 2.347656 ..
CCV_NNC_SOFTMAX_FORWARD [878]: [1] -> [1] (0)
|-> 1. 0x1438f1b50 (0x285da7100:0) [256x256] 7.539062 3.177734 2.347656 ..
|<- 1. 0x1438f1b50 (0x285da7100:0) [256x256] 0.112183 0.001431 0.000624 ..
CCV_NNC_GEMM_FORWARD [879]: [2] -> [1] (0)
|-> 1. 0x1438f1c70 (0x285da7100:0) [1x256x256] 0.112183 0.001431 0.000624 ..
|-> 2. 0x1438f1bc0 (0x285da70c0:0) [1x256x160] -1.738281 -1.147461 0.335693 ..
|<- 1. 0x1438f4670 (0x285da6dc0:0) [1x256x160] -1.063477 -0.694336 -0.510742 ..
CCV_NNC_GEMM_FORWARD [880]: [2] -> [1] (0)
|-> 1. 0x1438f1d90 (0x285da6fc0:0) [1x256x160] 0.025681 0.109680 -0.089539 ..
|-> 2. 0x1438f1ce0 (0x285da7500:0) [1x256x160] 1.176758 0.610840 0.282715 ..
|<- 1. 0x1438b0060 (0x285da7100:0) [1x256x256] 6.980469 4.449219 5.238281 ..
CCV_NNC_SOFTMAX_FORWARD [881]: [1] -> [1] (0)
|-> 1. 0x1438f1e40 (0x285da7100:0) [256x256] 6.980469 4.449219 5.238281 ..
|<- 1. 0x1438f1e40 (0x285da7100:0) [256x256] 0.162964 0.012962 0.028549 ..
CCV_NNC_GEMM_FORWARD [882]: [2] -> [1] (0)
|-> 1. 0x1438f1f60 (0x285da7100:0) [1x256x256] 0.162964 0.012962 0.028549 ..
|-> 2. 0x1438f1eb0 (0x285da70c0:0) [1x256x160] -0.705566 -0.148560 -0.640625 ..
|<- 1. 0x1438f4720 (0x285da6dc0:0) [1x256x160] -0.708496 -0.226196 -0.329346 ..
CCV_NNC_GEMM_FORWARD [883]: [2] -> [1] (0)
|-> 1. 0x1438f2080 (0x285da6fc0:0) [1x256x160] -0.024124 -0.029022 0.114563 ..
|-> 2. 0x1438f1fd0 (0x285da7500:0) [1x256x160] -1.910156 0.655762 -0.496338 ..
|<- 1. 0x1438b00d0 (0x285da7100:0) [1x256x256] 7.082031 3.769531 4.468750 ..
CCV_NNC_SOFTMAX_FORWARD [884]: [1] -> [1] (0)
|-> 1. 0x1438f2130 (0x285da7100:0) [256x256] 7.082031 3.769531 4.468750 ..
|<- 1. 0x1438f2130 (0x285da7100:0) [256x256] 0.233276 0.008499 0.017090 ..
CCV_NNC_GEMM_FORWARD [885]: [2] -> [1] (0)
|-> 1. 0x1438f2250 (0x285da7100:0) [1x256x256] 0.233276 0.008499 0.017090 ..
|-> 2. 0x1438f21a0 (0x285da70c0:0) [1x256x160] 1.168945 0.696777 -1.337891 ..
|<- 1. 0x1438f47d0 (0x285da6dc0:0) [1x256x160] 0.337158 0.245117 -0.674805 ..
CCV_NNC_GEMM_FORWARD [886]: [2] -> [1] (0)
|-> 1. 0x1438f2370 (0x285da6fc0:0) [1x256x160] -0.007347 0.029007 0.041748 ..
|-> 2. 0x1438f22c0 (0x285da7500:0) [1x256x160] -0.294189 -0.900391 -0.202148 ..
|<- 1. 0x1438b0140 (0x285da7100:0) [1x256x256] 7.851562 -1.454102 1.911133 ..
CCV_NNC_SOFTMAX_FORWARD [887]: [1] -> [1] (0)
|-> 1. 0x1438f2420 (0x285da7100:0) [256x256] 7.851562 -1.454102 1.911133 ..
|<- 1. 0x1438f2420 (0x285da7100:0) [256x256] 0.206055 0.000019 0.000542 ..
CCV_NNC_GEMM_FORWARD [888]: [2] -> [1] (0)
|-> 1. 0x1438f2540 (0x285da7100:0) [1x256x256] 0.206055 0.000019 0.000542 ..
|-> 2. 0x1438f2490 (0x285da70c0:0) [1x256x160] 0.247681 0.911133 0.065979 ..
|<- 1. 0x1438f4880 (0x285da6dc0:0) [1x256x160] 0.647949 0.694824 -0.026855 ..
CCV_NNC_GEMM_FORWARD [889]: [2] -> [1] (0)
|-> 1. 0x1438f2660 (0x285da6fc0:0) [1x256x160] -0.223511 0.076233 0.043945 ..
|-> 2. 0x1438f25b0 (0x285da7500:0) [1x256x160] 1.372070 0.509766 -1.004883 ..
|<- 1. 0x1438b01b0 (0x285da7100:0) [1x256x256] 8.132812 4.582031 5.632812 ..
CCV_NNC_SOFTMAX_FORWARD [890]: [1] -> [1] (0)
|-> 1. 0x1438f2710 (0x285da7100:0) [256x256] 8.132812 4.582031 5.632812 ..
|<- 1. 0x1438f2710 (0x285da7100:0) [256x256] 0.136353 0.003914 0.011192 ..
CCV_NNC_GEMM_FORWARD [891]: [2] -> [1] (0)
|-> 1. 0x1438f2830 (0x285da7100:0) [1x256x256] 0.136353 0.003914 0.011192 ..
|-> 2. 0x1438f2780 (0x285da70c0:0) [1x256x160] 0.764160 -0.154053 0.611328 ..
|<- 1. 0x1438f4930 (0x285da6dc0:0) [1x256x160] 0.591797 0.015686 0.218506 ..
CCV_NNC_GEMM_FORWARD [892]: [2] -> [1] (0)
|-> 1. 0x1438f2950 (0x285da6fc0:0) [1x256x160] 0.146606 0.026474 -0.005627 ..
|-> 2. 0x1438f28a0 (0x285da7500:0) [1x256x160] 0.768555 -0.469482 -1.038086 ..
|<- 1. 0x1438b0220 (0x285da7100:0) [1x256x256] 2.623047 1.068359 1.483398 ..
CCV_NNC_SOFTMAX_FORWARD [893]: [1] -> [1] (0)
|-> 1. 0x1438f2a00 (0x285da7100:0) [256x256] 2.623047 1.068359 1.483398 ..
|<- 1. 0x1438f2a00 (0x285da7100:0) [256x256] 0.048828 0.010315 0.015625 ..
CCV_NNC_GEMM_FORWARD [894]: [2] -> [1] (0)
|-> 1. 0x1438f2b20 (0x285da7100:0) [1x256x256] 0.048828 0.010315 0.015625 ..
|-> 2. 0x1438f2a70 (0x285da70c0:0) [1x256x160] -0.182983 -0.253662 1.363281 ..
|<- 1. 0x1438f49e0 (0x285da6dc0:0) [1x256x160] 0.237427 -0.470215 0.799316 ..
CCV_NNC_GEMM_FORWARD [895]: [2] -> [1] (0)
|-> 1. 0x1438f2c40 (0x285da6fc0:0) [1x256x160] 0.054230 0.058594 0.033875 ..
|-> 2. 0x1438f2b90 (0x285da7500:0) [1x256x160] 0.423584 -0.734863 -0.531738 ..
|<- 1. 0x1438b0290 (0x285da7100:0) [1x256x256] 5.960938 4.382812 4.917969 ..
CCV_NNC_SOFTMAX_FORWARD [896]: [1] -> [1] (0)
|-> 1. 0x1438f2cf0 (0x285da7100:0) [256x256] 5.960938 4.382812 4.917969 ..
|<- 1. 0x1438f2cf0 (0x285da7100:0) [256x256] 0.030304 0.006252 0.010681 ..
CCV_NNC_GEMM_FORWARD [897]: [2] -> [1] (0)
|-> 1. 0x1438f2e10 (0x285da7100:0) [1x256x256] 0.030304 0.006252 0.010681 ..
|-> 2. 0x1438f2d60 (0x285da70c0:0) [1x256x160] -0.123840 0.445068 -0.837891 ..
|<- 1. 0x1438f4a90 (0x285da6dc0:0) [1x256x160] 0.384033 0.083862 -0.193115 ..
CCV_NNC_GEMM_FORWARD [898]: [2] -> [1] (0)
|-> 1. 0x1438f2f30 (0x285da6fc0:0) [1x256x160] 0.019333 0.087524 0.053802 ..
|-> 2. 0x1438f2e80 (0x285da7500:0) [1x256x160] 2.158203 1.722656 1.718750 ..
|<- 1. 0x1438b0300 (0x285da7100:0) [1x256x256] 10.085938 8.164062 8.406250 ..
CCV_NNC_SOFTMAX_FORWARD [899]: [1] -> [1] (0)
|-> 1. 0x1438f2fe0 (0x285da7100:0) [256x256] 10.085938 8.164062 8.406250 ..
|<- 1. 0x1438f2fe0 (0x285da7100:0) [256x256] 0.452393 0.066162 0.084290 ..
CCV_NNC_GEMM_FORWARD [900]: [2] -> [1] (0)
|-> 1. 0x1438f3100 (0x285da7100:0) [1x256x256] 0.452393 0.066162 0.084290 ..
|-> 2. 0x1438f3050 (0x285da70c0:0) [1x256x160] -0.031036 -1.166016 0.129272 ..
|<- 1. 0x1438f4b40 (0x285da6dc0:0) [1x256x160] -0.035217 -0.971191 0.135132 ..
CCV_NNC_GEMM_FORWARD [901]: [2] -> [1] (0)
|-> 1. 0x1438f3220 (0x285da6fc0:0) [1x256x160] 0.083801 -0.166748 -0.042175 ..
|-> 2. 0x1438f3170 (0x285da7500:0) [1x256x160] -0.334717 -0.952637 0.387939 ..
|<- 1. 0x1438b0370 (0x285da7100:0) [1x256x256] 5.230469 3.679688 2.566406 ..
CCV_NNC_SOFTMAX_FORWARD [902]: [1] -> [1] (0)
|-> 1. 0x1438f32d0 (0x285da7100:0) [256x256] 5.230469 3.679688 2.566406 ..
|<- 1. 0x1438f32d0 (0x285da7100:0) [256x256] 0.104858 0.022232 0.007305 ..
CCV_NNC_GEMM_FORWARD [903]: [2] -> [1] (0)
|-> 1. 0x1438f33f0 (0x285da7100:0) [1x256x256] 0.104858 0.022232 0.007305 ..
|-> 2. 0x1438f3340 (0x285da70c0:0) [1x256x160] -0.562500 -0.381104 -0.351074 ..
|<- 1. 0x1438f4bf0 (0x285da6dc0:0) [1x256x160] -0.185303 0.016830 -0.185059 ..
CCV_NNC_GEMM_FORWARD [904]: [2] -> [1] (0)
|-> 1. 0x1438f3510 (0x285da6fc0:0) [1x256x160] 0.006348 0.105774 0.003361 ..
|-> 2. 0x1438f3460 (0x285da7500:0) [1x256x160] 0.595215 0.463379 1.402344 ..
|<- 1. 0x1438b03e0 (0x285da7100:0) [1x256x256] 7.652344 6.476562 6.976562 ..
CCV_NNC_SOFTMAX_FORWARD [905]: [1] -> [1] (0)
|-> 1. 0x1438f35c0 (0x285da7100:0) [256x256] 7.652344 6.476562 6.976562 ..
|<- 1. 0x1438f35c0 (0x285da7100:0) [256x256] 0.156982 0.048462 0.079895 ..
CCV_NNC_GEMM_FORWARD [906]: [2] -> [1] (0)
|-> 1. 0x1438f36e0 (0x285da7100:0) [1x256x256] 0.156982 0.048462 0.079895 ..
|-> 2. 0x1438f3630 (0x285da70c0:0) [1x256x160] -0.701172 -0.053009 0.064392 ..
|<- 1. 0x1438f4ca0 (0x285da6dc0:0) [1x256x160] -0.487061 -0.076782 0.087891 ..
CCV_NNC_GEMM_FORWARD [907]: [2] -> [1] (0)
|-> 1. 0x1438f3800 (0x285da6fc0:0) [1x256x160] -0.012260 0.044281 0.068420 ..
|-> 2. 0x1438f3750 (0x285da7500:0) [1x256x160] -1.064453 1.369141 0.449951 ..
|<- 1. 0x1438b0450 (0x285da7100:0) [1x256x256] 6.019531 4.535156 4.652344 ..
CCV_NNC_SOFTMAX_FORWARD [908]: [1] -> [1] (0)
|-> 1. 0x1438f38b0 (0x285da7100:0) [256x256] 6.019531 4.535156 4.652344 ..
|<- 1. 0x1438f38b0 (0x285da7100:0) [256x256] 0.161011 0.036469 0.041016 ..
CCV_NNC_GEMM_FORWARD [909]: [2] -> [1] (0)
|-> 1. 0x1438f39d0 (0x285da7100:0) [1x256x256] 0.161011 0.036469 0.041016 ..
|-> 2. 0x1438f3920 (0x285da70c0:0) [1x256x160] 0.281006 0.725098 -1.186523 ..
|<- 1. 0x1438f4d50 (0x285da6dc0:0) [1x256x160] 0.262451 0.128418 -0.516602 ..
CCV_NNC_GEMM_FORWARD [910]: [2] -> [1] (0)
|-> 1. 0x1438f3af0 (0x285da6fc0:0) [1x256x160] 0.027863 -0.004871 0.034241 ..
|-> 2. 0x1438f3a40 (0x285da7500:0) [1x256x160] -0.218262 -1.789062 -0.616211 ..
|<- 1. 0x1438b04c0 (0x285da7100:0) [1x256x256] 7.648438 2.396484 4.136719 ..
CCV_NNC_SOFTMAX_FORWARD [911]: [1] -> [1] (0)
|-> 1. 0x1438f3ba0 (0x285da7100:0) [256x256] 7.648438 2.396484 4.136719 ..
|<- 1. 0x1438f3ba0 (0x285da7100:0) [256x256] 0.182739 0.000957 0.005455 ..
CCV_NNC_GEMM_FORWARD [912]: [2] -> [1] (0)
|-> 1. 0x1438f3cc0 (0x285da7100:0) [1x256x256] 0.182739 0.000957 0.005455 ..
|-> 2. 0x1438f3c10 (0x285da70c0:0) [1x256x160] 0.893555 0.750488 0.679688 ..
|<- 1. 0x1438f4e00 (0x285da6dc0:0) [1x256x160] 1.060547 0.522949 0.245361 ..
CCV_NNC_GEMM_FORWARD [913]: [2] -> [1] (0)
|-> 1. 0x1438f3de0 (0x285da6fc0:0) [1x256x160] -0.252930 0.169067 0.006447 ..
|-> 2. 0x1438f3d30 (0x285da7500:0) [1x256x160] 1.604492 0.692871 -1.746094 ..
|<- 1. 0x1438b0530 (0x285da7100:0) [1x256x256] 6.566406 5.593750 5.199219 ..
CCV_NNC_SOFTMAX_FORWARD [914]: [1] -> [1] (0)
|-> 1. 0x1438f3e90 (0x285da7100:0) [256x256] 6.566406 5.593750 5.199219 ..
|<- 1. 0x1438f3e90 (0x285da7100:0) [256x256] 0.068604 0.025925 0.017471 ..
CCV_NNC_GEMM_FORWARD [915]: [2] -> [1] (0)
|-> 1. 0x1438f3fb0 (0x285da7100:0) [1x256x256] 0.068604 0.025925 0.017471 ..
|-> 2. 0x1438f3f00 (0x285da70c0:0) [1x256x160] 0.778809 0.391602 0.486816 ..
|<- 1. 0x1438f4eb0 (0x285da6dc0:0) [1x256x160] 0.820312 0.552246 0.275146 ..
CCV_NNC_GEMM_FORWARD [916]: [2] -> [1] (0)
|-> 1. 0x1438f40d0 (0x285da6fc0:0) [1x256x160] 0.055969 0.038879 -0.041809 ..
|-> 2. 0x1438f4020 (0x285da7500:0) [1x256x160] -0.500000 0.502441 -0.301025 ..
|<- 1. 0x1438b05a0 (0x285da7100:0) [1x256x256] 2.681641 0.804199 1.614258 ..
CCV_NNC_SOFTMAX_FORWARD [917]: [1] -> [1] (0)
|-> 1. 0x1438f4180 (0x285da7100:0) [256x256] 2.681641 0.804199 1.614258 ..
|<- 1. 0x1438f4180 (0x285da7100:0) [256x256] 0.042542 0.006508 0.014633 ..
CCV_NNC_GEMM_FORWARD [918]: [2] -> [1] (0)
|-> 1. 0x1438f42a0 (0x285da7100:0) [1x256x256] 0.042542 0.006508 0.014633 ..
|-> 2. 0x1438f41f0 (0x285da70c0:0) [1x256x160] 0.806641 -1.046875 0.018753 ..
|<- 1. 0x1438f4f60 (0x285da6dc0:0) [1x256x160] 0.142578 -0.398926 -0.196777 ..
CCV_NNC_GEMM_FORWARD [919]: [2] -> [1] (0)
|-> 1. 0x1438f43c0 (0x285da6fc0:0) [1x256x160] 0.039764 -0.060974 -0.042236 ..
|-> 2. 0x1438f4310 (0x285da7500:0) [1x256x160] 0.840332 -0.751953 -0.403320 ..
|<- 1. 0x1438b0610 (0x285da7100:0) [1x256x256] 6.425781 5.226562 5.136719 ..
CCV_NNC_SOFTMAX_FORWARD [920]: [1] -> [1] (0)
|-> 1. 0x1438f4470 (0x285da7100:0) [256x256] 6.425781 5.226562 5.136719 ..
|<- 1. 0x1438f4470 (0x285da7100:0) [256x256] 0.080750 0.024353 0.022263 ..
CCV_NNC_GEMM_FORWARD [921]: [2] -> [1] (0)
|-> 1. 0x1438f4590 (0x285da7100:0) [1x256x256] 0.080750 0.024353 0.022263 ..
|-> 2. 0x1438f44e0 (0x285da70c0:0) [1x256x160] 0.654785 0.263916 -0.434082 ..
|<- 1. 0x1438f5010 (0x285da6dc0:0) [1x256x160] 0.616211 0.246704 0.032349 ..
CCV_NNC_TRANSPOSE_FORWARD [922]: [1] -> [1] (0)
|-> 1. 0x1438f50c0 (0x285da6dc0:0) [2x8x256x160] 0.072632 -0.516113 -0.109436 ..
|<- 1. 0x1438b06f0 (0x285da70c0:0) [2x256x8x160] 0.072632 -0.516113 -0.109436 ..
CCV_NNC_GEMM_FORWARD [923]: [3] -> [1] (0)
|-> 1. 0x1438f5130 (0x285da70c0:0) [2x256x1280] 0.072632 -0.516113 -0.109436 ..
|-> 2. 0x1438c8940 (0x285d99700:0) [1280x1280] -0.013046 -0.022934 0.066040 ..
|-> 3. 0x1438c89b0 (0x285d99740:0) [1280] -0.035095 0.051544 -0.071899 ..
|<- 1. 0x1438b0760 (0x285da6dc0:0) [2x256x1280] -0.622559 0.609375 0.079468 ..
CCV_NNC_ADD_FORWARD [924]: [2] -> [1] (0)
|-> 1. 0x1438b0760 (0x285da6dc0:0) [2x256x1280] -0.622559 0.609375 0.079468 ..
|-> 2. 0x1438f1600 (0x285da6e00:0) [2x256x1280] -0.554199 -2.144531 -2.298828 ..
|<- 1. 0x1438b0760 (0x285da6dc0:0) [2x256x1280] -1.176758 -1.535156 -2.218750 ..
CCV_NNC_LAYER_NORM_FORWARD [925]: [3] -> [3] (0)
|-> 1. 0x1438b0760 (0x285da6dc0:0) [2x256x1280] -1.176758 -1.535156 -2.218750 ..
|-> 2. 0x1438c8a20 (0x285d99780:0) [1x1x1280] 0.533203 0.528809 0.527832 ..
|-> 3. 0x1438c8a90 (0x285d997c0:0) [1x1x1280] -0.068298 0.169189 -0.048798 ..
|<- 1. 0x1438b07d0 (0x285da6e00:0) [2x256x1280] -0.428467 -0.307373 -0.751953 ..
|<- 2. 0x1438b0840 (0x285d83940:0) [2x256x1] -0.104065 ..
|<- 3. 0x1438b08b0 (0x285d80b00:0) [2x256x1] 0.629883 ..
CCV_NNC_GEMM_FORWARD [926]: [2] -> [1] (0)
|-> 1. 0x1438b07d0 (0x285da6e00:0) [2x256x1280] -0.428467 -0.307373 -0.751953 ..
|-> 2. 0x1438c8b00 (0x285d99800:0) [1280x1280] -0.022980 -0.034637 0.010147 ..
|<- 1. 0x1438b0920 (0x285da70c0:0) [2x256x1280] -0.089539 0.138916 1.353516 ..
CCV_NNC_SCALAR_MUL_FORWARD [927]: [1] -> [1] (0)
|-> 1. 0x1438b0920 (0x285da70c0:0) [2x256x1280] -0.089539 0.138916 1.353516 ..
|<- 1. 0x1438b0920 (0x285da70c0:0) [2x256x1280] -0.007076 0.010979 0.106995 ..
CCV_NNC_TRANSPOSE_FORWARD [928]: [1] -> [1] (0)
|-> 1. 0x1438f5210 (0x285da70c0:0) [2x256x8x160] -0.007076 0.010979 0.106995 ..
|<- 1. 0x1438b0a70 (0x285da6e00:0) [2x8x256x160] -0.007076 0.010979 0.106995 ..
CCV_NNC_GEMM_FORWARD [929]: [2] -> [1] (0)
Wait: (0, 90)
|-> 1. 0x1438b0a70 (0x285da6e00:0) [2x8x256x160] -0.007076 0.010979 0.106995 ..
|-> 2. 0x1438b0a00 (0x285d82b80:0) [2x8x133x160] 0.121155 0.245972 -0.240967 ..
|<- 1. 0x1438b0ae0 (0x285d83540:0) [2x8x256x133] 9.742188 -1.166016 -2.281250 ..
CCV_NNC_SOFTMAX_FORWARD [930]: [1] -> [1] (0)
|-> 1. 0x1438f5280 (0x285d83540:0) [4096x133] 9.742188 -1.166016 -2.281250 ..
|<- 1. 0x1438f5280 (0x285d83540:0) [4096x133] 0.979492 0.000018 0.000006 ..
CCV_NNC_GEMM_FORWARD [931]: [2] -> [1] (0)
Wait: (0, 91)
|-> 1. 0x1438f5360 (0x285d83540:0) [2x8x256x133] 0.979492 0.000018 0.000006 ..
|-> 2. 0x1438b0bc0 (0x285d8f740:0) [2x8x133x160] 0.004066 -0.018509 -0.005821 ..
|<- 1. 0x1438b0c30 (0x285da6e00:0) [2x8x256x160] 0.004787 -0.015945 -0.017044 ..
CCV_NNC_TRANSPOSE_FORWARD [932]: [1] -> [1] (0)
|-> 1. 0x1438f53d0 (0x285da6e00:0) [2x8x256x160] 0.004787 -0.015945 -0.017044 ..
|<- 1. 0x1438b0ca0 (0x285da70c0:0) [2x256x8x160] 0.004787 -0.015945 -0.017044 ..
CCV_NNC_GEMM_FORWARD [933]: [3] -> [1] (0)
|-> 1. 0x1438f5440 (0x285da70c0:0) [2x256x1280] 0.004787 -0.015945 -0.017044 ..
|-> 2. 0x1438c8c50 (0x285d998c0:0) [1280x1280] -0.035217 -0.020599 -0.032043 ..
|-> 3. 0x1438c8cc0 (0x285d99900:0) [1280] -0.004532 0.020935 -0.034210 ..
|<- 1. 0x1438b0d10 (0x285da7000:0) [2x256x1280] 0.211914 -0.218506 -0.389648 ..
CCV_NNC_ADD_FORWARD [934]: [2] -> [1] (0)
|-> 1. 0x1438b0d10 (0x285da7000:0) [2x256x1280] 0.211914 -0.218506 -0.389648 ..
|-> 2. 0x1438b0760 (0x285da6dc0:0) [2x256x1280] -1.176758 -1.535156 -2.218750 ..
|<- 1. 0x1438b0d10 (0x285da7000:0) [2x256x1280] -0.964844 -1.753906 -2.609375 ..
CCV_NNC_LAYER_NORM_FORWARD [935]: [3] -> [3] (0)
|-> 1. 0x1438b0d10 (0x285da7000:0) [2x256x1280] -0.964844 -1.753906 -2.609375 ..
|-> 2. 0x1438c8d30 (0x285d99940:0) [1x1x1280] 0.380127 0.390869 0.374268 ..
|-> 3. 0x1438c8da0 (0x285d99980:0) [1x1x1280] -0.022308 0.036255 0.046906 ..
|<- 1. 0x1438b0d80 (0x285da72c0:0) [2x256x1280] -0.220947 -0.351807 -0.515137 ..
|<- 2. 0x1438b0df0 (0x285da7800:0) [2x256x1] -0.087402 ..
|<- 3. 0x1438b0e60 (0x285da7840:0) [2x256x1] 0.595703 ..
Emit: (0, 92)
CCV_NNC_GEMM_FORWARD [936]: [3] -> [1] (0)
|-> 1. 0x1438b0d80 (0x285da72c0:0) [2x256x1280] -0.220947 -0.351807 -0.515137 ..
|-> 2. 0x1438c8e10 (0x285d999c0:0) [5120x1280] 0.057953 -0.109924 0.071899 ..
|-> 3. 0x1438c8e80 (0x285d99a00:0) [5120] -0.213013 -0.045563 -0.019592 ..
|<- 1. 0x1438b0ed0 (0x285da7380:0) [2x256x5120] -1.300781 -0.664551 0.034515 ..
CCV_NNC_GELU_FORWARD [937]: [1] -> [1] (0)
|-> 1. 0x1438b0ed0 (0x285da7380:0) [2x256x5120] -1.300781 -0.664551 0.034515 ..
|<- 1. 0x1438b0ed0 (0x285da7380:0) [2x256x5120] -0.125732 -0.168213 0.017731 ..
CCV_NNC_GEMM_FORWARD [938]: [3] -> [1] (1)
Wait: (1, 92)
|-> 1. 0x1438b0d80 (0x285da72c0:0) [2x256x1280] -0.220947 -0.351807 -0.515137 ..
|-> 2. 0x1438c8ef0 (0x285d99a40:0) [5120x1280] 0.000521 0.080933 -0.085510 ..
|-> 3. 0x1438c8f60 (0x285d99a80:0) [5120] -0.024734 0.008774 0.006813 ..
|<- 1. 0x1438b0f40 (0x285da5ac0:0) [2x256x5120] -0.028610 -1.030273 -0.769531 ..
Emit: (1, 93)
CCV_NNC_MUL_FORWARD [939]: [2] -> [1] (0)
Wait: (0, 93)
|-> 1. 0x1438b0f40 (0x285da5ac0:0) [2x256x5120] -0.028610 -1.030273 -0.769531 ..
|-> 2. 0x1438b0ed0 (0x285da7380:0) [2x256x5120] -0.125732 -0.168213 0.017731 ..
|<- 1. 0x1438b0f40 (0x285da5ac0:0) [2x256x5120] 0.003597 0.173340 -0.013641 ..
CCV_NNC_GEMM_FORWARD [940]: [3] -> [1] (0)
|-> 1. 0x1438b0f40 (0x285da5ac0:0) [2x256x5120] 0.003597 0.173340 -0.013641 ..
|-> 2. 0x1438c8fd0 (0x285d99ac0:0) [1280x5120] -0.065979 -0.060883 0.041168 ..
|-> 3. 0x1438c9040 (0x285d99b00:0) [1280] -0.026901 -0.001597 0.080750 ..
|<- 1. 0x1438b0fb0 (0x285da7140:0) [2x256x1280] 0.187744 0.619141 1.061523 ..
CCV_NNC_ADD_FORWARD [941]: [2] -> [1] (0)
|-> 1. 0x1438b0fb0 (0x285da7140:0) [2x256x1280] 0.187744 0.619141 1.061523 ..
|-> 2. 0x1438b0d10 (0x285da7000:0) [2x256x1280] -0.964844 -1.753906 -2.609375 ..
|<- 1. 0x1438b0fb0 (0x285da7140:0) [2x256x1280] -0.777344 -1.134766 -1.547852 ..
CCV_NNC_CONVOLUTION_FORWARD [942]: [3] -> [1] (0)
|-> 1. 0x1438f54b0 (0x285da7140:0) [2x16x16x1280] -0.777344 -1.134766 -1.547852 ..
|-> 2. 0x1438c90b0 (0x285d99b40:0) [1280x1280x1x1] -0.040009 ..
|-> 3. 0x1438c9120 (0x285d99b80:0) [1280] -0.010376 0.030624 -0.020950 ..
|<- 1. 0x1438b1020 (0x285da6e00:0) [2x16x16x1280] -1.301758 -3.751953 5.585938 ..
CCV_NNC_ADD_FORWARD [943]: [2] -> [1] (0)
|-> 1. 0x1438b1020 (0x285da6e00:0) [2x16x16x1280] -1.301758 -3.751953 5.585938 ..
|-> 2. 0x1438af960 (0x285da6f00:0) [2x16x16x1280] -5.343750 6.925781 -4.500000 ..
|<- 1. 0x1438f5520 (0x285d8f6c0:0) [2x16x16x1280] -6.644531 3.173828 1.085938 ..
Emit: (0, 95)
CCV_NNC_GROUP_NORM_FORWARD [944]: [3] -> [3] (0)
|-> 1. 0x1438b1090 (0x285d8f6c0:0) [2x16x16x1920] -6.644531 3.173828 1.085938 ..
|-> 2. 0x1438c9190 (0x285d99bc0:0) [1x1x1x1920] 0.369873 0.423828 0.469727 ..
|-> 3. 0x1438c9200 (0x285d99c00:0) [1x1x1x1920] -0.063354 -0.070618 -0.123596 ..
|<- 1. 0x1438b1100 (0x285d8ce40:0) [2x16x16x1920] -1.292969 0.491699 0.035065 ..
|<- 2. 0x1438b1170 (0x285da6e80:0) [2x1x1x32] 0.372803 0.045929 0.686523 ..
|<- 3. 0x1438b11e0 (0x285da6e40:0) [2x1x1x32] 0.473633 0.417725 0.443115 ..
CCV_NNC_SWISH_FORWARD [945]: [1] -> [1] (0)
|-> 1. 0x1438b1100 (0x285d8ce40:0) [2x16x16x1920] -1.292969 0.491699 0.035065 ..
|<- 1. 0x1438b1100 (0x285d8ce40:0) [2x16x16x1920] -0.278320 0.305176 0.017838 ..
CCV_NNC_CONVOLUTION_FORWARD [946]: [3] -> [1] (0)
|-> 1. 0x1438b1100 (0x285d8ce40:0) [2x16x16x1920] -0.278320 0.305176 0.017838 ..
|-> 2. 0x1438c9350 (0x285d99cc0:0) [1280x1920x3x3] -0.071899 -0.020355 -0.076477 ..
|-> 3. 0x1438c93c0 (0x285d99d00:0) [1280] 0.046570 0.005695 0.048706 ..
|<- 1. 0x1438b12c0 (0x285da7140:0) [2x16x16x1280] 1.129883 0.439209 6.167969 ..
CCV_NNC_ADD_FORWARD [947]: [2] -> [1] (0)
Wait: (0, 94)
|-> 1. 0x1438b12c0 (0x285da7140:0) [2x16x16x1280] 1.129883 0.439209 6.167969 ..
|-> 2. 0x1438f5680 (0x285d8c440:0) [2x1x1x1280] 1.041992 0.774902 1.260742 ..
|<- 1. 0x1438b12c0 (0x285da7140:0) [2x16x16x1280] 2.171875 1.213867 7.429688 ..
CCV_NNC_GROUP_NORM_FORWARD [948]: [3] -> [3] (0)
|-> 1. 0x1438b12c0 (0x285da7140:0) [2x16x16x1280] 2.171875 1.213867 7.429688 ..
|-> 2. 0x1438c9430 (0x285d99d40:0) [1x1x1x1280] 0.454590 0.866211 0.541504 ..
|-> 3. 0x1438c94a0 (0x285d99d80:0) [1x1x1x1280] -0.253418 -0.310547 -0.239624 ..
|<- 1. 0x1438b1330 (0x285da6e00:0) [2x16x16x1280] 0.076843 -0.088440 1.550781 ..
|<- 2. 0x1438b13a0 (0x285d8c680:0) [2x1x1x32] 0.691406 0.110413 0.063354 ..
|<- 3. 0x1438b1410 (0x285d8c240:0) [2x1x1x32] 0.490723 0.457764 0.548828 ..
CCV_NNC_SWISH_FORWARD [949]: [1] -> [1] (0)
|-> 1. 0x1438b1330 (0x285da6e00:0) [2x16x16x1280] 0.076843 -0.088440 1.550781 ..
|<- 1. 0x1438b1330 (0x285da6e00:0) [2x16x16x1280] 0.039886 -0.042267 1.279297 ..
CCV_NNC_CONVOLUTION_FORWARD [950]: [3] -> [1] (0)
|-> 1. 0x1438b1330 (0x285da6e00:0) [2x16x16x1280] 0.039886 -0.042267 1.279297 ..
|-> 2. 0x1438c9510 (0x285d99dc0:0) [1280x1280x3x3] -0.100159 -0.106445 0.042694 ..
|-> 3. 0x1438c9580 (0x285d99e00:0) [1280] 0.001283 -0.011497 -0.087036 ..
|<- 1. 0x1438b1480 (0x285da7140:0) [2x16x16x1280] 0.440674 -2.119141 -1.319336 ..
CCV_NNC_CONVOLUTION_FORWARD [951]: [3] -> [1] (1)
Wait: (1, 95)
|-> 1. 0x1438b1090 (0x285d8f6c0:0) [2x16x16x1920] -6.644531 3.173828 1.085938 ..
|-> 2. 0x1438c95f0 (0x285d99e40:0) [1280x1920x1x1] -0.015823 ..
|-> 3. 0x1438c9660 (0x285d99e80:0) [1280] -0.005310 -0.018036 -0.093018 ..
|<- 1. 0x1438b14f0 (0x285da6f00:0) [2x16x16x1280] -1.634766 -0.795410 -1.690430 ..
Emit: (1, 96)
CCV_NNC_ADD_FORWARD [952]: [2] -> [1] (0)
Wait: (0, 96)
|-> 1. 0x1438b14f0 (0x285da6f00:0) [2x16x16x1280] -1.634766 -0.795410 -1.690430 ..
|-> 2. 0x1438b1480 (0x285da7140:0) [2x16x16x1280] 0.440674 -2.119141 -1.319336 ..
|<- 1. 0x1438b14f0 (0x285da6f00:0) [2x16x16x1280] -1.194336 -2.914062 -3.009766 ..
CCV_NNC_GROUP_NORM_FORWARD [953]: [3] -> [3] (0)
|-> 1. 0x1438b14f0 (0x285da6f00:0) [2x16x16x1280] -1.194336 -2.914062 -3.009766 ..
|-> 2. 0x1438c96d0 (0x285d99ec0:0) [1x1x1x1280] 0.356445 0.367920 0.364014 ..
|-> 3. 0x1438c9740 (0x285d99f00:0) [1x1x1x1280] -0.016251 -0.021881 0.052979 ..
|<- 1. 0x1438b1560 (0x285da7140:0) [2x16x16x1280] -0.244263 -0.613770 -0.552246 ..
|<- 2. 0x1438b15d0 (0x285da6140:0) [2x1x1x32] -0.059113 -0.151611 0.005707 ..
|<- 3. 0x1438b1640 (0x285da6100:0) [2x1x1x32] 0.563477 0.433838 0.554199 ..
CCV_NNC_CONVOLUTION_FORWARD [954]: [3] -> [1] (0)
|-> 1. 0x1438b1560 (0x285da7140:0) [2x16x16x1280] -0.244263 -0.613770 -0.552246 ..
|-> 2. 0x1438c97b0 (0x285d99f40:0) [1280x1280x1x1] -0.044098 ..
|-> 3. 0x1438c9820 (0x285d99f80:0) [1280] 0.058502 0.041290 0.052246 ..
|<- 1. 0x1438b16b0 (0x285da6e00:0) [2x16x16x1280] -0.857910 0.154419 -0.089844 ..
CCV_NNC_LAYER_NORM_FORWARD [955]: [3] -> [3] (0)
|-> 1. 0x1438f56f0 (0x285da6e00:0) [2x256x1280] -0.857910 0.154419 -0.089844 ..
|-> 2. 0x1438c9890 (0x285d99fc0:0) [1x1x1280] 0.292236 0.305664 0.298828 ..
|-> 3. 0x1438c9900 (0x285d9a000:0) [1x1x1280] -0.016541 0.005215 0.019699 ..
|<- 1. 0x1438b1720 (0x285da7140:0) [2x256x1280] -0.187256 0.025818 -0.007133 ..
|<- 2. 0x1438b1790 (0x285d8cc00:0) [2x256x1] 0.049683 ..
|<- 3. 0x1438b1800 (0x285d8d040:0) [2x256x1] 0.643555 ..
Emit: (0, 97)
CCV_NNC_GEMM_FORWARD [956]: [2] -> [1] (0)
|-> 1. 0x1438b1720 (0x285da7140:0) [2x256x1280] -0.187256 0.025818 -0.007133 ..
|-> 2. 0x1438c9970 (0x285d9a040:0) [1280x1280] -0.121460 -0.055603 -0.006561 ..
|<- 1. 0x1438b1870 (0x285da7000:0) [2x256x1280] -0.865723 -0.432129 -0.188477 ..
CCV_NNC_SCALAR_MUL_FORWARD [957]: [1] -> [1] (0)
|-> 1. 0x1438b1870 (0x285da7000:0) [2x256x1280] -0.865723 -0.432129 -0.188477 ..
|<- 1. 0x1438b1870 (0x285da7000:0) [2x256x1280] -0.068420 -0.034149 -0.014900 ..
CCV_NNC_TRANSPOSE_FORWARD [958]: [1] -> [1] (0)
|-> 1. 0x1438f57d0 (0x285da7000:0) [2x256x8x160] -0.068420 -0.034149 -0.014900 ..
|<- 1. 0x1438b19c0 (0x285da6dc0:0) [2x8x256x160] -0.068420 -0.034149 -0.014900 ..
CCV_NNC_GEMM_FORWARD [959]: [2] -> [1] (1)
Wait: (1, 97)
|-> 1. 0x1438b1720 (0x285da7140:0) [2x256x1280] -0.187256 0.025818 -0.007133 ..
|-> 2. 0x1438c99e0 (0x285d9a080:0) [1280x1280] -0.066650 0.023560 0.073730 ..
|<- 1. 0x1438b18e0 (0x285da7040:0) [2x256x1280] -1.296875 1.006836 -1.194336 ..
CCV_NNC_TRANSPOSE_FORWARD [960]: [1] -> [1] (1)
|-> 1. 0x1438f5760 (0x285da7040:0) [2x256x8x160] -1.296875 1.006836 -1.194336 ..
|<- 1. 0x1438b1950 (0x285d8c980:0) [2x8x256x160] -1.296875 1.006836 -1.194336 ..
Emit: (1, 98)
CCV_NNC_GEMM_FORWARD [961]: [2] -> [1] (2)
Wait: (2, 97)
|-> 1. 0x1438b1720 (0x285da7140:0) [2x256x1280] -0.187256 0.025818 -0.007133 ..
|-> 2. 0x1438c9a50 (0x285d9a0c0:0) [1280x1280] 0.030045 0.071716 -0.026672 ..
|<- 1. 0x1438b1a30 (0x285da7080:0) [2x256x1280] -0.123413 -1.111328 0.277588 ..
CCV_NNC_TRANSPOSE_FORWARD [962]: [1] -> [1] (2)
|-> 1. 0x1438f5920 (0x285da7080:0) [2x256x8x160] -0.123413 -1.111328 0.277588 ..
|<- 1. 0x1438b1b10 (0x285d8c780:0) [2x8x256x160] -0.123413 -1.111328 0.277588 ..
Emit: (2, 99)
CCV_NNC_GEMM_FORWARD [963]: [2] -> [1] (0)
Wait: (0, 98)
|-> 1. 0x1438f58b0 (0x285da6dc0:0) [1x256x160] -0.068420 -0.034149 -0.014900 ..
|-> 2. 0x1438f5840 (0x285d8c980:0) [1x256x160] -1.296875 1.006836 -1.194336 ..
|<- 1. 0x1438b1aa0 (0x285da7100:0) [1x256x256] 2.474609 0.318604 0.121704 ..
CCV_NNC_SOFTMAX_FORWARD [964]: [1] -> [1] (0)
|-> 1. 0x1438f5990 (0x285da7100:0) [256x256] 2.474609 0.318604 0.121704 ..
|<- 1. 0x1438f5990 (0x285da7100:0) [256x256] 0.039551 0.004578 0.003759 ..
CCV_NNC_GEMM_FORWARD [965]: [2] -> [1] (0)
Wait: (0, 99)
|-> 1. 0x1438f5a70 (0x285da7100:0) [1x256x256] 0.039551 0.004578 0.003759 ..
|-> 2. 0x1438f5a00 (0x285d8c780:0) [1x256x160] -0.123413 -1.111328 0.277588 ..
|<- 1. 0x1438f86f0 (0x285da7140:0) [1x256x160] -0.029663 -0.238525 0.205688 ..
CCV_NNC_GEMM_FORWARD [966]: [2] -> [1] (0)
|-> 1. 0x1438f5b90 (0x285da6dc0:0) [1x256x160] 0.025436 0.048096 -0.006474 ..
|-> 2. 0x1438f5ae0 (0x285d8c980:0) [1x256x160] -0.026215 0.209106 0.471191 ..
|<- 1. 0x1438b1b80 (0x285da7100:0) [1x256x256] 5.050781 1.940430 2.738281 ..
CCV_NNC_SOFTMAX_FORWARD [967]: [1] -> [1] (0)
|-> 1. 0x1438f5c40 (0x285da7100:0) [256x256] 5.050781 1.940430 2.738281 ..
|<- 1. 0x1438f5c40 (0x285da7100:0) [256x256] 0.134399 0.005993 0.013313 ..
CCV_NNC_GEMM_FORWARD [968]: [2] -> [1] (0)
|-> 1. 0x1438f5d60 (0x285da7100:0) [1x256x256] 0.134399 0.005993 0.013313 ..
|-> 2. 0x1438f5cb0 (0x285d8c780:0) [1x256x160] -0.559082 0.386230 -0.292969 ..
|<- 1. 0x1438f8760 (0x285da7140:0) [1x256x160] -0.003584 0.193726 -0.424072 ..
CCV_NNC_GEMM_FORWARD [969]: [2] -> [1] (0)
|-> 1. 0x1438f5e80 (0x285da6dc0:0) [1x256x160] -0.042480 0.061066 0.055664 ..
|-> 2. 0x1438f5dd0 (0x285d8c980:0) [1x256x160] -3.333984 0.008812 0.408936 ..
|<- 1. 0x1438b1bf0 (0x285da7100:0) [1x256x256] 3.126953 -0.156616 0.113159 ..
CCV_NNC_SOFTMAX_FORWARD [970]: [1] -> [1] (0)
|-> 1. 0x1438f5f30 (0x285da7100:0) [256x256] 3.126953 -0.156616 0.113159 ..
|<- 1. 0x1438f5f30 (0x285da7100:0) [256x256] 0.115295 0.004322 0.005661 ..
CCV_NNC_GEMM_FORWARD [971]: [2] -> [1] (0)
|-> 1. 0x1438f6050 (0x285da7100:0) [1x256x256] 0.115295 0.004322 0.005661 ..
|-> 2. 0x1438f5fa0 (0x285d8c780:0) [1x256x160] -0.766113 0.706543 -1.374023 ..
|<- 1. 0x1438f8810 (0x285da7140:0) [1x256x160] -0.169189 0.109985 -0.546875 ..
CCV_NNC_GEMM_FORWARD [972]: [2] -> [1] (0)
|-> 1. 0x1438f6170 (0x285da6dc0:0) [1x256x160] 0.056244 0.001263 0.041534 ..
|-> 2. 0x1438f60c0 (0x285d8c980:0) [1x256x160] -1.695312 -0.590332 -0.623047 ..
|<- 1. 0x1438b1c60 (0x285da7100:0) [1x256x256] 5.187500 0.637207 1.765625 ..
CCV_NNC_SOFTMAX_FORWARD [973]: [1] -> [1] (0)
|-> 1. 0x1438f6220 (0x285da7100:0) [256x256] 5.187500 0.637207 1.765625 ..
|<- 1. 0x1438f6220 (0x285da7100:0) [256x256] 0.269287 0.002844 0.008789 ..
CCV_NNC_GEMM_FORWARD [974]: [2] -> [1] (0)
|-> 1. 0x1438f6340 (0x285da7100:0) [1x256x256] 0.269287 0.002844 0.008789 ..
|-> 2. 0x1438f6290 (0x285d8c780:0) [1x256x160] 0.040863 -0.086243 0.060791 ..
|<- 1. 0x1438f88c0 (0x285da7140:0) [1x256x160] -0.068237 -0.361328 0.153931 ..
CCV_NNC_GEMM_FORWARD [975]: [2] -> [1] (0)
|-> 1. 0x1438f6460 (0x285da6dc0:0) [1x256x160] 0.106262 -0.136841 -0.024200 ..
|-> 2. 0x1438f63b0 (0x285d8c980:0) [1x256x160] -0.123840 -1.485352 -0.448975 ..
|<- 1. 0x1438b1cd0 (0x285da7100:0) [1x256x256] 5.027344 0.989746 1.094727 ..
CCV_NNC_SOFTMAX_FORWARD [976]: [1] -> [1] (0)
|-> 1. 0x1438f6510 (0x285da7100:0) [256x256] 5.027344 0.989746 1.094727 ..
|<- 1. 0x1438f6510 (0x285da7100:0) [256x256] 0.422119 0.007446 0.008270 ..
CCV_NNC_GEMM_FORWARD [977]: [2] -> [1] (0)
|-> 1. 0x1438f6630 (0x285da7100:0) [1x256x256] 0.422119 0.007446 0.008270 ..
|-> 2. 0x1438f6580 (0x285d8c780:0) [1x256x160] -0.202881 -1.025391 -0.043030 ..
|<- 1. 0x1438f8970 (0x285da7140:0) [1x256x160] -0.031525 -0.352295 -0.065369 ..
CCV_NNC_GEMM_FORWARD [978]: [2] -> [1] (0)
|-> 1. 0x1438f6750 (0x285da6dc0:0) [1x256x160] -0.025620 -0.084595 0.006088 ..
|-> 2. 0x1438f66a0 (0x285d8c980:0) [1x256x160] -0.844727 -0.199829 0.766113 ..
|<- 1. 0x1438b1d40 (0x285da7100:0) [1x256x256] 4.238281 2.683594 3.179688 ..
CCV_NNC_SOFTMAX_FORWARD [979]: [1] -> [1] (0)
|-> 1. 0x1438f6800 (0x285da7100:0) [256x256] 4.238281 2.683594 3.179688 ..
|<- 1. 0x1438f6800 (0x285da7100:0) [256x256] 0.069763 0.014732 0.024200 ..
CCV_NNC_GEMM_FORWARD [980]: [2] -> [1] (0)
|-> 1. 0x1438f6920 (0x285da7100:0) [1x256x256] 0.069763 0.014732 0.024200 ..
|-> 2. 0x1438f6870 (0x285d8c780:0) [1x256x160] 0.288086 -0.375488 0.562500 ..
|<- 1. 0x1438f8a20 (0x285da7140:0) [1x256x160] 0.076599 -0.465576 0.074158 ..
CCV_NNC_GEMM_FORWARD [981]: [2] -> [1] (0)
|-> 1. 0x1438f6a40 (0x285da6dc0:0) [1x256x160] -0.066284 -0.072693 -0.047546 ..
|-> 2. 0x1438f6990 (0x285d8c980:0) [1x256x160] -1.922852 -1.832031 0.287109 ..
|<- 1. 0x1438b1db0 (0x285da7100:0) [1x256x256] 4.167969 0.547363 1.880859 ..
CCV_NNC_SOFTMAX_FORWARD [982]: [1] -> [1] (0)
|-> 1. 0x1438f6af0 (0x285da7100:0) [256x256] 4.167969 0.547363 1.880859 ..
|<- 1. 0x1438f6af0 (0x285da7100:0) [256x256] 0.159424 0.004269 0.016190 ..
CCV_NNC_GEMM_FORWARD [983]: [2] -> [1] (0)
|-> 1. 0x1438f6c10 (0x285da7100:0) [1x256x256] 0.159424 0.004269 0.016190 ..
|-> 2. 0x1438f6b60 (0x285d8c780:0) [1x256x160] 1.224609 0.110657 1.205078 ..
|<- 1. 0x1438f8ad0 (0x285da7140:0) [1x256x160] 0.603027 0.037598 0.402344 ..
CCV_NNC_GEMM_FORWARD [984]: [2] -> [1] (0)
|-> 1. 0x1438f6d30 (0x285da6dc0:0) [1x256x160] -0.030258 -0.005009 -0.014069 ..
|-> 2. 0x1438f6c80 (0x285d8c980:0) [1x256x160] -0.125732 0.028305 0.761230 ..
|<- 1. 0x1438b1e20 (0x285da7100:0) [1x256x256] 2.710938 1.256836 1.192383 ..
CCV_NNC_SOFTMAX_FORWARD [985]: [1] -> [1] (0)
|-> 1. 0x1438f6de0 (0x285da7100:0) [256x256] 2.710938 1.256836 1.192383 ..
|<- 1. 0x1438f6de0 (0x285da7100:0) [256x256] 0.058228 0.013603 0.012756 ..
CCV_NNC_GEMM_FORWARD [986]: [2] -> [1] (0)
|-> 1. 0x1438f6f00 (0x285da7100:0) [1x256x256] 0.058228 0.013603 0.012756 ..
|-> 2. 0x1438f6e50 (0x285d8c780:0) [1x256x160] -0.057709 -0.303711 -0.490234 ..
|<- 1. 0x1438f8b80 (0x285da7140:0) [1x256x160] -0.202637 -0.004353 -0.188843 ..
CCV_NNC_GEMM_FORWARD [987]: [2] -> [1] (0)
|-> 1. 0x1438f7020 (0x285da6dc0:0) [1x256x160] -0.096252 -0.071045 -0.034515 ..
|-> 2. 0x1438f6f70 (0x285d8c980:0) [1x256x160] -0.761230 1.026367 -1.627930 ..
|<- 1. 0x1438b1e90 (0x285da7100:0) [1x256x256] -0.142334 -1.962891 -1.364258 ..
CCV_NNC_SOFTMAX_FORWARD [988]: [1] -> [1] (0)
|-> 1. 0x1438f70d0 (0x285da7100:0) [256x256] -0.142334 -1.962891 -1.364258 ..
|<- 1. 0x1438f70d0 (0x285da7100:0) [256x256] 0.003401 0.000551 0.001002 ..
CCV_NNC_GEMM_FORWARD [989]: [2] -> [1] (0)
|-> 1. 0x1438f71f0 (0x285da7100:0) [1x256x256] 0.003401 0.000551 0.001002 ..
|-> 2. 0x1438f7140 (0x285d8c780:0) [1x256x160] -0.634766 -1.153320 -0.300049 ..
|<- 1. 0x1438f8c30 (0x285da7140:0) [1x256x160] 0.282471 0.024155 0.024918 ..
CCV_NNC_GEMM_FORWARD [990]: [2] -> [1] (0)
|-> 1. 0x1438f7310 (0x285da6dc0:0) [1x256x160] -0.013100 0.013702 0.059387 ..
|-> 2. 0x1438f7260 (0x285d8c980:0) [1x256x160] -0.775879 1.148438 1.910156 ..
|<- 1. 0x1438b1f00 (0x285da7100:0) [1x256x256] 3.984375 3.125000 3.052734 ..
CCV_NNC_SOFTMAX_FORWARD [991]: [1] -> [1] (0)
|-> 1. 0x1438f73c0 (0x285da7100:0) [256x256] 3.984375 3.125000 3.052734 ..
|<- 1. 0x1438f73c0 (0x285da7100:0) [256x256] 0.072021 0.030502 0.028381 ..
CCV_NNC_GEMM_FORWARD [992]: [2] -> [1] (0)
|-> 1. 0x1438f74e0 (0x285da7100:0) [1x256x256] 0.072021 0.030502 0.028381 ..
|-> 2. 0x1438f7430 (0x285d8c780:0) [1x256x160] 0.066711 0.679199 -0.135254 ..
|<- 1. 0x1438f8ce0 (0x285da7140:0) [1x256x160] 0.047180 0.719727 -0.400635 ..
CCV_NNC_GEMM_FORWARD [993]: [2] -> [1] (0)
|-> 1. 0x1438f7600 (0x285da6dc0:0) [1x256x160] -0.026962 0.184692 0.025650 ..
|-> 2. 0x1438f7550 (0x285d8c980:0) [1x256x160] -2.107422 -0.120667 0.050323 ..
|<- 1. 0x1438b1f70 (0x285da7100:0) [1x256x256] 2.644531 0.411621 0.771484 ..
CCV_NNC_SOFTMAX_FORWARD [994]: [1] -> [1] (0)
|-> 1. 0x1438f76b0 (0x285da7100:0) [256x256] 2.644531 0.411621 0.771484 ..
|<- 1. 0x1438f76b0 (0x285da7100:0) [256x256] 0.063965 0.006855 0.009827 ..
CCV_NNC_GEMM_FORWARD [995]: [2] -> [1] (0)
|-> 1. 0x1438f77d0 (0x285da7100:0) [1x256x256] 0.063965 0.006855 0.009827 ..
|-> 2. 0x1438f7720 (0x285d8c780:0) [1x256x160] -0.258789 -0.493896 -0.442383 ..
|<- 1. 0x1438f8d90 (0x285da7140:0) [1x256x160] 0.053894 -0.741699 -0.207642 ..
CCV_NNC_GEMM_FORWARD [996]: [2] -> [1] (0)
|-> 1. 0x1438f78f0 (0x285da6dc0:0) [1x256x160] -0.015503 0.042389 -0.000524 ..
|-> 2. 0x1438f7840 (0x285d8c980:0) [1x256x160] -2.117188 -0.396484 -1.464844 ..
|<- 1. 0x1438b1fe0 (0x285da7100:0) [1x256x256] 4.343750 1.093750 2.136719 ..
CCV_NNC_SOFTMAX_FORWARD [997]: [1] -> [1] (0)
|-> 1. 0x1438f79a0 (0x285da7100:0) [256x256] 4.343750 1.093750 2.136719 ..
|<- 1. 0x1438f79a0 (0x285da7100:0) [256x256] 0.280273 0.010864 0.030823 ..
CCV_NNC_GEMM_FORWARD [998]: [2] -> [1] (0)
|-> 1. 0x1438f7ac0 (0x285da7100:0) [1x256x256] 0.280273 0.010864 0.030823 ..
|-> 2. 0x1438f7a10 (0x285d8c780:0) [1x256x160] -0.196411 -0.195312 -0.061340 ..
|<- 1. 0x1438f8e40 (0x285da7140:0) [1x256x160] -0.235474 -0.348389 -0.164551 ..
CCV_NNC_GEMM_FORWARD [999]: [2] -> [1] (0)
|-> 1. 0x1438f7be0 (0x285da6dc0:0) [1x256x160] 0.166138 -0.070251 -0.092407 ..
|-> 2. 0x1438f7b30 (0x285d8c980:0) [1x256x160] -1.057617 -2.427734 -0.274414 ..
|<- 1. 0x1438b2050 (0x285da7100:0) [1x256x256] 4.710938 1.409180 2.310547 ..
CCV_NNC_SOFTMAX_FORWARD [1000]: [1] -> [1] (0)
|-> 1. 0x1438f7c90 (0x285da7100:0) [256x256] 4.710938 1.409180 2.310547 ..
|<- 1. 0x1438f7c90 (0x285da7100:0) [256x256] 0.256348 0.009438 0.023239 ..
CCV_NNC_GEMM_FORWARD [1001]: [2] -> [1] (0)
|-> 1. 0x1438f7db0 (0x285da7100:0) [1x256x256] 0.256348 0.009438 0.023239 ..
|-> 2. 0x1438f7d00 (0x285d8c780:0) [1x256x160] -0.330322 -0.535156 -0.308594 ..
|<- 1. 0x1438f8ef0 (0x285da7140:0) [1x256x160] -0.343750 -0.173340 -0.205078 ..
CCV_NNC_GEMM_FORWARD [1002]: [2] -> [1] (0)
|-> 1. 0x1438f7ed0 (0x285da6dc0:0) [1x256x160] 0.034546 -0.083740 -0.047852 ..
|-> 2. 0x1438f7e20 (0x285d8c980:0) [1x256x160] -0.906738 0.093384 1.075195 ..
|<- 1. 0x1438b20c0 (0x285da7100:0) [1x256x256] 2.625000 1.369141 1.050781 ..
CCV_NNC_SOFTMAX_FORWARD [1003]: [1] -> [1] (0)
|-> 1. 0x1438f7f80 (0x285da7100:0) [256x256] 2.625000 1.369141 1.050781 ..
|<- 1. 0x1438f7f80 (0x285da7100:0) [256x256] 0.045929 0.013084 0.009514 ..
CCV_NNC_GEMM_FORWARD [1004]: [2] -> [1] (0)
|-> 1. 0x1438f80a0 (0x285da7100:0) [1x256x256] 0.045929 0.013084 0.009514 ..
|-> 2. 0x1438f7ff0 (0x285d8c780:0) [1x256x160] 0.256592 -0.325684 0.286133 ..
|<- 1. 0x1438f8fa0 (0x285da7140:0) [1x256x160] 0.290771 -0.006809 0.150879 ..
CCV_NNC_GEMM_FORWARD [1005]: [2] -> [1] (0)
|-> 1. 0x1438f81c0 (0x285da6dc0:0) [1x256x160] -0.085571 -0.097107 -0.003794 ..
|-> 2. 0x1438f8110 (0x285d8c980:0) [1x256x160] -2.148438 -1.299805 0.352783 ..
|<- 1. 0x1438b2130 (0x285da7100:0) [1x256x256] 4.015625 1.193359 1.611328 ..
CCV_NNC_SOFTMAX_FORWARD [1006]: [1] -> [1] (0)
|-> 1. 0x1438f8270 (0x285da7100:0) [256x256] 4.015625 1.193359 1.611328 ..
|<- 1. 0x1438f8270 (0x285da7100:0) [256x256] 0.218506 0.012993 0.019745 ..
CCV_NNC_GEMM_FORWARD [1007]: [2] -> [1] (0)
|-> 1. 0x1438f8390 (0x285da7100:0) [1x256x256] 0.218506 0.012993 0.019745 ..
|-> 2. 0x1438f82e0 (0x285d8c780:0) [1x256x160] 0.908203 -0.232300 0.604980 ..
|<- 1. 0x1438f9050 (0x285da7140:0) [1x256x160] 0.309326 -0.281006 0.420654 ..
CCV_NNC_GEMM_FORWARD [1008]: [2] -> [1] (0)
|-> 1. 0x1438f84b0 (0x285da6dc0:0) [1x256x160] -0.102417 0.009850 0.057648 ..
|-> 2. 0x1438f8400 (0x285d8c980:0) [1x256x160] -0.301758 0.466553 1.138672 ..
|<- 1. 0x1438b21a0 (0x285da7100:0) [1x256x256] 2.775391 2.132812 2.513672 ..
CCV_NNC_SOFTMAX_FORWARD [1009]: [1] -> [1] (0)
|-> 1. 0x1438f8560 (0x285da7100:0) [256x256] 2.775391 2.132812 2.513672 ..
|<- 1. 0x1438f8560 (0x285da7100:0) [256x256] 0.036469 0.019180 0.028076 ..
CCV_NNC_GEMM_FORWARD [1010]: [2] -> [1] (0)
|-> 1. 0x1438f8680 (0x285da7100:0) [1x256x256] 0.036469 0.019180 0.028076 ..
|-> 2. 0x1438f85d0 (0x285d8c780:0) [1x256x160] -0.153931 -0.440430 -0.136719 ..
|<- 1. 0x1438f9100 (0x285da7140:0) [1x256x160] -0.478027 -0.097473 -0.007957 ..
CCV_NNC_TRANSPOSE_FORWARD [1011]: [1] -> [1] (0)
|-> 1. 0x1438f91b0 (0x285da7140:0) [2x8x256x160] -0.029663 -0.238525 0.205688 ..
|<- 1. 0x1438b2280 (0x285d8c780:0) [2x256x8x160] -0.029663 -0.238525 0.205688 ..
CCV_NNC_GEMM_FORWARD [1012]: [3] -> [1] (0)
|-> 1. 0x1438f9220 (0x285d8c780:0) [2x256x1280] -0.029663 -0.238525 0.205688 ..
|-> 2. 0x1438c9ac0 (0x285d9a100:0) [1280x1280] 0.016495 0.047668 0.106934 ..
|-> 3. 0x1438c9b30 (0x285d9a140:0) [1280] -0.011230 0.035309 0.040924 ..
|<- 1. 0x1438b22f0 (0x285da7140:0) [2x256x1280] 0.725586 0.106384 -0.291504 ..
CCV_NNC_ADD_FORWARD [1013]: [2] -> [1] (0)
|-> 1. 0x1438b22f0 (0x285da7140:0) [2x256x1280] 0.725586 0.106384 -0.291504 ..
|-> 2. 0x1438f56f0 (0x285da6e00:0) [2x256x1280] -0.857910 0.154419 -0.089844 ..
|<- 1. 0x1438b22f0 (0x285da7140:0) [2x256x1280] -0.132324 0.260742 -0.381348 ..
CCV_NNC_LAYER_NORM_FORWARD [1014]: [3] -> [3] (0)
|-> 1. 0x1438b22f0 (0x285da7140:0) [2x256x1280] -0.132324 0.260742 -0.381348 ..
|-> 2. 0x1438c9ba0 (0x285d9a180:0) [1x1x1280] 0.531250 0.606934 0.561523 ..
|-> 3. 0x1438c9c10 (0x285d9a1c0:0) [1x1x1280] -0.029846 0.085083 -0.074341 ..
|<- 1. 0x1438b2360 (0x285da6e00:0) [2x256x1280] -0.096313 0.173706 -0.241089 ..
|<- 2. 0x1438b23d0 (0x285d89780:0) [2x256x1] 0.048981 ..
|<- 3. 0x1438b2440 (0x285d8b980:0) [2x256x1] 0.689941 ..
CCV_NNC_GEMM_FORWARD [1015]: [2] -> [1] (0)
|-> 1. 0x1438b2360 (0x285da6e00:0) [2x256x1280] -0.096313 0.173706 -0.241089 ..
|-> 2. 0x1438c9c80 (0x285d9a200:0) [1280x1280] 0.044159 -0.077209 0.041718 ..
|<- 1. 0x1438b24b0 (0x285d8c780:0) [2x256x1280] -1.210938 -1.211914 -0.032318 ..
CCV_NNC_SCALAR_MUL_FORWARD [1016]: [1] -> [1] (0)
|-> 1. 0x1438b24b0 (0x285d8c780:0) [2x256x1280] -1.210938 -1.211914 -0.032318 ..
|<- 1. 0x1438b24b0 (0x285d8c780:0) [2x256x1280] -0.095703 -0.095764 -0.002554 ..
CCV_NNC_TRANSPOSE_FORWARD [1017]: [1] -> [1] (0)
|-> 1. 0x1438f9300 (0x285d8c780:0) [2x256x8x160] -0.095703 -0.095764 -0.002554 ..
|<- 1. 0x1438b2600 (0x285da6e00:0) [2x8x256x160] -0.095703 -0.095764 -0.002554 ..
CCV_NNC_GEMM_FORWARD [1018]: [2] -> [1] (0)
Wait: (0, 100)
|-> 1. 0x1438b2600 (0x285da6e00:0) [2x8x256x160] -0.095703 -0.095764 -0.002554 ..
|-> 2. 0x1438b2590 (0x285d89340:0) [2x8x133x160] 0.334717 -0.014442 -0.148804 ..
|<- 1. 0x1438b2670 (0x285d892c0:0) [2x8x256x133] 10.531250 0.444580 2.359375 ..
CCV_NNC_SOFTMAX_FORWARD [1019]: [1] -> [1] (0)
|-> 1. 0x1438f9370 (0x285d892c0:0) [4096x133] 10.531250 0.444580 2.359375 ..
|<- 1. 0x1438f9370 (0x285d892c0:0) [4096x133] 0.937988 0.000039 0.000265 ..
CCV_NNC_GEMM_FORWARD [1020]: [2] -> [1] (0)
Wait: (0, 101)
|-> 1. 0x1438f9450 (0x285d892c0:0) [2x8x256x133] 0.937988 0.000039 0.000265 ..
|-> 2. 0x1438b2750 (0x285d89c80:0) [2x8x133x160] 0.031281 0.007065 -0.043945 ..
|<- 1. 0x1438b27c0 (0x285da6e00:0) [2x8x256x160] 0.076538 -0.065552 -0.033875 ..
CCV_NNC_TRANSPOSE_FORWARD [1021]: [1] -> [1] (0)
|-> 1. 0x1438f94c0 (0x285da6e00:0) [2x8x256x160] 0.076538 -0.065552 -0.033875 ..
|<- 1. 0x1438b2830 (0x285d8c780:0) [2x256x8x160] 0.076538 -0.065552 -0.033875 ..
CCV_NNC_GEMM_FORWARD [1022]: [3] -> [1] (0)
|-> 1. 0x1438f9530 (0x285d8c780:0) [2x256x1280] 0.076538 -0.065552 -0.033875 ..
|-> 2. 0x1438c9dd0 (0x285d9a2c0:0) [1280x1280] 0.003952 -0.029709 0.045410 ..
|-> 3. 0x1438c9e40 (0x285d9a300:0) [1280] -0.005177 0.035767 0.049866 ..
|<- 1. 0x1438b28a0 (0x285da7000:0) [2x256x1280] -0.213623 0.076111 0.495361 ..
CCV_NNC_ADD_FORWARD [1023]: [2] -> [1] (0)
|-> 1. 0x1438b28a0 (0x285da7000:0) [2x256x1280] -0.213623 0.076111 0.495361 ..
|-> 2. 0x1438b22f0 (0x285da7140:0) [2x256x1280] -0.132324 0.260742 -0.381348 ..
|<- 1. 0x1438b28a0 (0x285da7000:0) [2x256x1280] -0.345947 0.336914 0.114014 ..
CCV_NNC_LAYER_NORM_FORWARD [1024]: [3] -> [3] (0)
|-> 1. 0x1438b28a0 (0x285da7000:0) [2x256x1280] -0.345947 0.336914 0.114014 ..
|-> 2. 0x1438c9eb0 (0x285d9a340:0) [1x1x1280] 0.341553 0.357910 0.346191 ..
|-> 3. 0x1438c9f20 (0x285d9a380:0) [1x1x1280] 0.046143 -0.032074 -0.076843 ..
|<- 1. 0x1438b2910 (0x285da72c0:0) [2x256x1280] -0.044464 0.035034 -0.063110 ..
|<- 2. 0x1438b2980 (0x285da6f40:0) [2x256x1] 0.054169 ..
|<- 3. 0x1438b29f0 (0x285da6f80:0) [2x256x1] 0.663086 ..
Emit: (0, 102)
CCV_NNC_GEMM_FORWARD [1025]: [3] -> [1] (0)
|-> 1. 0x1438b2910 (0x285da72c0:0) [2x256x1280] -0.044464 0.035034 -0.063110 ..
|-> 2. 0x1438c9f90 (0x285d9a3c0:0) [5120x1280] -0.029694 -0.015450 -0.071960 ..
|-> 3. 0x1438ca000 (0x285d9a400:0) [5120] -0.007454 -0.018753 -0.000805 ..
|<- 1. 0x1438b2a60 (0x285da7380:0) [2x256x5120] -0.097412 -0.713867 0.692383 ..
CCV_NNC_GELU_FORWARD [1026]: [1] -> [1] (0)
|-> 1. 0x1438b2a60 (0x285da7380:0) [2x256x5120] -0.097412 -0.713867 0.692383 ..
|<- 1. 0x1438b2a60 (0x285da7380:0) [2x256x5120] -0.044922 -0.169678 0.522949 ..
CCV_NNC_GEMM_FORWARD [1027]: [3] -> [1] (1)
Wait: (1, 102)
|-> 1. 0x1438b2910 (0x285da72c0:0) [2x256x1280] -0.044464 0.035034 -0.063110 ..
|-> 2. 0x1438ca070 (0x285d9a440:0) [5120x1280] 0.053772 -0.025650 -0.059418 ..
|-> 3. 0x1438ca0e0 (0x285d9a480:0) [5120] 0.016739 -0.004398 0.012329 ..
|<- 1. 0x1438b2ad0 (0x285da5ac0:0) [2x256x5120] 0.131592 -0.269287 0.271240 ..
Emit: (1, 103)
CCV_NNC_MUL_FORWARD [1028]: [2] -> [1] (0)
Wait: (0, 103)
|-> 1. 0x1438b2ad0 (0x285da5ac0:0) [2x256x5120] 0.131592 -0.269287 0.271240 ..
|-> 2. 0x1438b2a60 (0x285da7380:0) [2x256x5120] -0.044922 -0.169678 0.522949 ..
|<- 1. 0x1438b2ad0 (0x285da5ac0:0) [2x256x5120] -0.005913 0.045685 0.141846 ..
CCV_NNC_GEMM_FORWARD [1029]: [3] -> [1] (0)
|-> 1. 0x1438b2ad0 (0x285da5ac0:0) [2x256x5120] -0.005913 0.045685 0.141846 ..
|-> 2. 0x1438ca150 (0x285d9a4c0:0) [1280x5120] -0.010429 -0.089233 -0.003870 ..
|-> 3. 0x1438ca1c0 (0x285d9a500:0) [1280] -0.001016 -0.026932 -0.011261 ..
|<- 1. 0x1438b2b40 (0x285da6dc0:0) [2x256x1280] -0.128418 -1.971680 -0.229614 ..
CCV_NNC_ADD_FORWARD [1030]: [2] -> [1] (0)
|-> 1. 0x1438b2b40 (0x285da6dc0:0) [2x256x1280] -0.128418 -1.971680 -0.229614 ..
|-> 2. 0x1438b28a0 (0x285da7000:0) [2x256x1280] -0.345947 0.336914 0.114014 ..
|<- 1. 0x1438b2b40 (0x285da6dc0:0) [2x256x1280] -0.474365 -1.634766 -0.115601 ..
CCV_NNC_CONVOLUTION_FORWARD [1031]: [3] -> [1] (0)
|-> 1. 0x1438f95a0 (0x285da6dc0:0) [2x16x16x1280] -0.474365 -1.634766 -0.115601 ..
|-> 2. 0x1438ca230 (0x285d9a540:0) [1280x1280x1x1] 0.035187 ..
|-> 3. 0x1438ca2a0 (0x285d9a580:0) [1280] 0.014740 -0.048126 0.051697 ..
|<- 1. 0x1438b2bb0 (0x285da7000:0) [2x16x16x1280] 0.229736 -0.174683 4.160156 ..
CCV_NNC_ADD_FORWARD [1032]: [2] -> [1] (0)
|-> 1. 0x1438b2bb0 (0x285da7000:0) [2x16x16x1280] 0.229736 -0.174683 4.160156 ..
|-> 2. 0x1438b14f0 (0x285da6f00:0) [2x16x16x1280] -1.194336 -2.914062 -3.009766 ..
|<- 1. 0x1438b2bb0 (0x285da7000:0) [2x16x16x1280] -0.964844 -3.087891 1.150391 ..
CCV_NNC_UPSAMPLE_FORWARD [1033]: [1] -> [1] (0)
|-> 1. 0x1438b2bb0 (0x285da7000:0) [2x16x16x1280] -0.964844 -3.087891 1.150391 ..
|<- 1. 0x1438b2c20 (0x285da5ac0:0) [2x32x32x1280] -0.964844 -3.087891 1.150391 ..
CCV_NNC_CONVOLUTION_FORWARD [1034]: [3] -> [1] (0)
|-> 1. 0x1438b2c20 (0x285da5ac0:0) [2x32x32x1280] -0.964844 -3.087891 1.150391 ..
|-> 2. 0x1438ca310 (0x285d9a5c0:0) [1280x1280x3x3] -0.024902 -0.039246 -0.029648 ..
|-> 3. 0x1438ca380 (0x285d9a600:0) [1280] 0.068298 0.009995 0.088501 ..
|<- 1. 0x1438f9610 (0x285d8a540:0) [2x32x32x1280] -2.570312 -0.451904 8.929688 ..
Emit: (0, 105)
CCV_NNC_GROUP_NORM_FORWARD [1035]: [3] -> [3] (0)
|-> 1. 0x1438b2c90 (0x285d8a540:0) [2x32x32x1920] -2.570312 -0.451904 8.929688 ..
|-> 2. 0x1438ca3f0 (0x285d9a640:0) [1x1x1x1920] 0.323486 0.736816 0.702637 ..
|-> 3. 0x1438ca460 (0x285d9a680:0) [1x1x1x1920] -0.043121 -0.490723 -0.364502 ..
|<- 1. 0x1438b2d00 (0x285d89300:0) [2x32x32x1920] -0.186035 -0.504395 0.939453 ..
|<- 2. 0x1438b2d70 (0x285d89600:0) [2x1x1x32] -0.358643 0.008682 -0.120728 ..
|<- 3. 0x1438b2de0 (0x285d8a680:0) [2x1x1x32] 0.199829 0.170654 0.202393 ..
CCV_NNC_SWISH_FORWARD [1036]: [1] -> [1] (0)
|-> 1. 0x1438b2d00 (0x285d89300:0) [2x32x32x1920] -0.186035 -0.504395 0.939453 ..
|<- 1. 0x1438b2d00 (0x285d89300:0) [2x32x32x1920] -0.084412 -0.189941 0.675293 ..
CCV_NNC_CONVOLUTION_FORWARD [1037]: [3] -> [1] (0)
|-> 1. 0x1438b2d00 (0x285d89300:0) [2x32x32x1920] -0.084412 -0.189941 0.675293 ..
|-> 2. 0x1438ca5b0 (0x285d9a740:0) [640x1920x3x3] -0.028946 0.073425 0.018143 ..
|-> 3. 0x1438ca620 (0x285d9a780:0) [640] 0.090149 0.105103 0.058411 ..
|<- 1. 0x1438b2ec0 (0x285da69c0:0) [2x32x32x640] 3.695312 9.406250 5.417969 ..
CCV_NNC_ADD_FORWARD [1038]: [2] -> [1] (0)
Wait: (0, 104)
|-> 1. 0x1438b2ec0 (0x285da69c0:0) [2x32x32x640] 3.695312 9.406250 5.417969 ..
|-> 2. 0x1438f9770 (0x285df5b80:0) [2x1x1x640] 0.082214 1.164062 0.841797 ..
|<- 1. 0x1438b2ec0 (0x285da69c0:0) [2x32x32x640] 3.777344 10.570312 6.257812 ..
CCV_NNC_GROUP_NORM_FORWARD [1039]: [3] -> [3] (0)
|-> 1. 0x1438b2ec0 (0x285da69c0:0) [2x32x32x640] 3.777344 10.570312 6.257812 ..
|-> 2. 0x1438ca690 (0x285d9a7c0:0) [1x1x1x640] 0.891113 0.568848 1.095703 ..
|-> 3. 0x1438ca700 (0x285d9a800:0) [1x1x1x640] -0.676270 -0.693359 -0.376221 ..
|<- 1. 0x1438b2f30 (0x285da61c0:0) [2x32x32x640] 0.359375 1.776367 2.169922 ..
|<- 2. 0x1438b2fa0 (0x285df67c0:0) [2x1x1x32] 1.293945 1.502930 0.658691 ..
|<- 3. 0x1438b3010 (0x285df5600:0) [2x1x1x32] 0.468018 0.478516 0.463135 ..
CCV_NNC_SWISH_FORWARD [1040]: [1] -> [1] (0)
|-> 1. 0x1438b2f30 (0x285da61c0:0) [2x32x32x640] 0.359375 1.776367 2.169922 ..
|<- 1. 0x1438b2f30 (0x285da61c0:0) [2x32x32x640] 0.211670 1.519531 1.947266 ..
CCV_NNC_CONVOLUTION_FORWARD [1041]: [3] -> [1] (0)
|-> 1. 0x1438b2f30 (0x285da61c0:0) [2x32x32x640] 0.211670 1.519531 1.947266 ..
|-> 2. 0x1438ca770 (0x285d9a840:0) [640x640x3x3] 0.003094 0.050446 -0.045868 ..
|-> 3. 0x1438ca7e0 (0x285d9a880:0) [640] -0.037384 0.043182 -0.021820 ..
|<- 1. 0x1438b3080 (0x285da69c0:0) [2x32x32x640] -2.900391 3.585938 3.650391 ..
CCV_NNC_CONVOLUTION_FORWARD [1042]: [3] -> [1] (1)
Wait: (1, 105)
|-> 1. 0x1438b2c90 (0x285d8a540:0) [2x32x32x1920] -2.570312 -0.451904 8.929688 ..
|-> 2. 0x1438ca850 (0x285d9a8c0:0) [640x1920x1x1] -0.019440 ..
|-> 3. 0x1438ca8c0 (0x285d9a900:0) [640] -0.040924 0.046875 -0.026077 ..
|<- 1. 0x1438b30f0 (0x285da62c0:0) [2x32x32x640] 5.339844 -4.343750 4.878906 ..
Emit: (1, 106)
CCV_NNC_ADD_FORWARD [1043]: [2] -> [1] (0)
Wait: (0, 106)
|-> 1. 0x1438b30f0 (0x285da62c0:0) [2x32x32x640] 5.339844 -4.343750 4.878906 ..
|-> 2. 0x1438b3080 (0x285da69c0:0) [2x32x32x640] -2.900391 3.585938 3.650391 ..
|<- 1. 0x1438b30f0 (0x285da62c0:0) [2x32x32x640] 2.439453 -0.757812 8.531250 ..
CCV_NNC_GROUP_NORM_FORWARD [1044]: [3] -> [3] (0)
|-> 1. 0x1438b30f0 (0x285da62c0:0) [2x32x32x640] 2.439453 -0.757812 8.531250 ..
|-> 2. 0x1438ca930 (0x285d9a940:0) [1x1x1x640] 0.708496 0.607422 0.636230 ..
|-> 3. 0x1438ca9a0 (0x285d9a980:0) [1x1x1x640] 0.052734 0.027512 -0.014030 ..
|<- 1. 0x1438b3160 (0x285da69c0:0) [2x32x32x640] 0.437744 -0.245605 1.535156 ..
|<- 2. 0x1438b31d0 (0x285da6140:0) [2x1x1x32] 0.689941 -0.210083 0.612305 ..
|<- 3. 0x1438b3240 (0x285da6100:0) [2x1x1x32] 0.310547 0.299316 0.241455 ..
CCV_NNC_CONVOLUTION_FORWARD [1045]: [3] -> [1] (0)
|-> 1. 0x1438b3160 (0x285da69c0:0) [2x32x32x640] 0.437744 -0.245605 1.535156 ..
|-> 2. 0x1438caa10 (0x285d9a9c0:0) [640x640x1x1] 0.047913 ..
|-> 3. 0x1438caa80 (0x285d9aa00:0) [640] -0.080200 -0.173218 -0.108032 ..
|<- 1. 0x1438b32b0 (0x285da61c0:0) [2x32x32x640] -4.050781 0.651367 -1.082031 ..
CCV_NNC_LAYER_NORM_FORWARD [1046]: [3] -> [3] (0)
|-> 1. 0x1438f97e0 (0x285da61c0:0) [2x1024x640] -4.050781 0.651367 -1.082031 ..
|-> 2. 0x1438caaf0 (0x285d9aa40:0) [1x1x640] 0.691895 0.783691 0.561523 ..
|-> 3. 0x1438cab60 (0x285d9aa80:0) [1x1x640] 0.066345 -0.014656 0.093201 ..
|<- 1. 0x1438b3320 (0x285da6440:0) [2x1024x640] -1.447266 0.228882 -0.249390 ..
|<- 2. 0x1438b3390 (0x285df6a80:0) [2x1024x1] 0.066528 ..
|<- 3. 0x1438b3400 (0x285df5a80:0) [2x1024x1] 0.531250 ..
Emit: (0, 107)
CCV_NNC_GEMM_FORWARD [1047]: [2] -> [1] (0)
|-> 1. 0x1438b3320 (0x285da6440:0) [2x1024x640] -1.447266 0.228882 -0.249390 ..
|-> 2. 0x1438cabd0 (0x285d9aac0:0) [640x640] -0.039215 0.078186 0.038971 ..
|<- 1. 0x1438b3470 (0x285da63c0:0) [2x1024x640] -0.948242 0.126587 -1.590820 ..
CCV_NNC_SCALAR_MUL_FORWARD [1048]: [1] -> [1] (0)
|-> 1. 0x1438b3470 (0x285da63c0:0) [2x1024x640] -0.948242 0.126587 -1.590820 ..
|<- 1. 0x1438b3470 (0x285da63c0:0) [2x1024x640] -0.106018 0.014153 -0.177856 ..
CCV_NNC_TRANSPOSE_FORWARD [1049]: [1] -> [1] (0)
|-> 1. 0x1438f98c0 (0x285da63c0:0) [2x1024x8x80] -0.106018 0.014153 -0.177856 ..
|<- 1. 0x1438b35c0 (0x285df77c0:0) [2x8x1024x80] -0.106018 0.014153 -0.177856 ..
CCV_NNC_GEMM_FORWARD [1050]: [2] -> [1] (1)
Wait: (1, 107)
|-> 1. 0x1438b3320 (0x285da6440:0) [2x1024x640] -1.447266 0.228882 -0.249390 ..
|-> 2. 0x1438cac40 (0x285d9ab00:0) [640x640] 0.020844 0.064453 -0.010071 ..
|<- 1. 0x1438b34e0 (0x285da6300:0) [2x1024x640] -1.957031 0.275635 -2.267578 ..
CCV_NNC_TRANSPOSE_FORWARD [1051]: [1] -> [1] (1)
|-> 1. 0x1438f9850 (0x285da6300:0) [2x1024x8x80] -1.957031 0.275635 -2.267578 ..
|<- 1. 0x1438b3550 (0x285da6480:0) [2x8x1024x80] -1.957031 0.275635 -2.267578 ..
Emit: (1, 108)
CCV_NNC_GEMM_FORWARD [1052]: [2] -> [1] (2)
Wait: (2, 107)
|-> 1. 0x1438b3320 (0x285da6440:0) [2x1024x640] -1.447266 0.228882 -0.249390 ..
|-> 2. 0x1438cacb0 (0x285d9ab40:0) [640x640] 0.021179 -0.102051 -0.008934 ..
|<- 1. 0x1438b3630 (0x285da69c0:0) [2x1024x640] -0.310547 -0.400146 -0.831543 ..
CCV_NNC_TRANSPOSE_FORWARD [1053]: [1] -> [1] (2)
|-> 1. 0x1438f9a10 (0x285da69c0:0) [2x1024x8x80] -0.310547 -0.400146 -0.831543 ..
|<- 1. 0x1438b3710 (0x285da6200:0) [2x8x1024x80] -0.310547 -0.400146 -0.831543 ..
Emit: (2, 109)
CCV_NNC_GEMM_FORWARD [1054]: [2] -> [1] (0)
Wait: (0, 108)
|-> 1. 0x1438f99a0 (0x285df77c0:0) [1x1024x80] -0.106018 0.014153 -0.177856 ..
|-> 2. 0x1438f9930 (0x285da6480:0) [1x1024x80] -1.957031 0.275635 -2.267578 ..
|<- 1. 0x1438b36a0 (0x285df5900:0) [1x1024x1024] 7.847656 2.396484 1.670898 ..
CCV_NNC_SOFTMAX_FORWARD [1055]: [1] -> [1] (0)
|-> 1. 0x1438f9a80 (0x285df5900:0) [1024x1024] 7.847656 2.396484 1.670898 ..
|<- 1. 0x1438f9a80 (0x285df5900:0) [1024x1024] 0.055725 0.000239 0.000116 ..
CCV_NNC_GEMM_FORWARD [1056]: [2] -> [1] (0)
Wait: (0, 109)
|-> 1. 0x1438f9b60 (0x285df5900:0) [1x1024x1024] 0.055725 0.000239 0.000116 ..
|-> 2. 0x1438f9af0 (0x285da6200:0) [1x1024x80] -0.310547 -0.400146 -0.831543 ..
|<- 1. 0x1438fc7e0 (0x285da6440:0) [1x1024x80] -0.406494 -0.149292 -0.776855 ..
CCV_NNC_GEMM_FORWARD [1057]: [2] -> [1] (0)
|-> 1. 0x1438f9c80 (0x285df77c0:0) [1x1024x80] 0.005150 0.263916 0.042297 ..
|-> 2. 0x1438f9bd0 (0x285da6480:0) [1x1024x80] 1.383789 2.326172 -1.015625 ..
|<- 1. 0x1438b3780 (0x285da6a40:0) [1x1024x1024] 5.320312 3.998047 3.390625 ..
CCV_NNC_SOFTMAX_FORWARD [1058]: [1] -> [1] (0)
|-> 1. 0x1438f9d30 (0x285da6a40:0) [1024x1024] 5.320312 3.998047 3.390625 ..
|<- 1. 0x1438f9d30 (0x285da6a40:0) [1024x1024] 0.060638 0.016159 0.008804 ..
CCV_NNC_GEMM_FORWARD [1059]: [2] -> [1] (0)
|-> 1. 0x1438f9e50 (0x285da6a40:0) [1x1024x1024] 0.060638 0.016159 0.008804 ..
|-> 2. 0x1438f9da0 (0x285da6200:0) [1x1024x80] 1.101562 -1.238281 0.707520 ..
|<- 1. 0x1438fc850 (0x285da6440:0) [1x1024x80] 1.252930 -0.494873 0.638672 ..
CCV_NNC_GEMM_FORWARD [1060]: [2] -> [1] (0)
|-> 1. 0x1438f9f70 (0x285df77c0:0) [1x1024x80] -0.064880 -0.058472 0.057098 ..
|-> 2. 0x1438f9ec0 (0x285da6480:0) [1x1024x80] 1.626953 -0.387451 -1.530273 ..
|<- 1. 0x1438b37f0 (0x285da6a40:0) [1x1024x1024] 11.531250 8.398438 7.800781 ..
CCV_NNC_SOFTMAX_FORWARD [1061]: [1] -> [1] (0)
|-> 1. 0x1438fa020 (0x285da6a40:0) [1024x1024] 11.531250 8.398438 7.800781 ..
|<- 1. 0x1438fa020 (0x285da6a40:0) [1024x1024] 0.166016 0.007240 0.003983 ..
CCV_NNC_GEMM_FORWARD [1062]: [2] -> [1] (0)
|-> 1. 0x1438fa140 (0x285da6a40:0) [1x1024x1024] 0.166016 0.007240 0.003983 ..
|-> 2. 0x1438fa090 (0x285da6200:0) [1x1024x80] 1.445312 0.543945 1.396484 ..
|<- 1. 0x1438fc900 (0x285da6440:0) [1x1024x80] 0.942871 0.017838 1.226562 ..
CCV_NNC_GEMM_FORWARD [1063]: [2] -> [1] (0)
|-> 1. 0x1438fa260 (0x285df77c0:0) [1x1024x80] 0.104553 -0.311768 0.097900 ..
|-> 2. 0x1438fa1b0 (0x285da6480:0) [1x1024x80] -2.537109 -1.655273 -0.967773 ..
|<- 1. 0x1438b3860 (0x285da6a40:0) [1x1024x1024] 9.218750 4.425781 4.574219 ..
CCV_NNC_SOFTMAX_FORWARD [1064]: [1] -> [1] (0)
|-> 1. 0x1438fa310 (0x285da6a40:0) [1024x1024] 9.218750 4.425781 4.574219 ..
|<- 1. 0x1438fa310 (0x285da6a40:0) [1024x1024] 0.005772 0.000048 0.000055 ..
CCV_NNC_GEMM_FORWARD [1065]: [2] -> [1] (0)
|-> 1. 0x1438fa430 (0x285da6a40:0) [1x1024x1024] 0.005772 0.000048 0.000055 ..
|-> 2. 0x1438fa380 (0x285da6200:0) [1x1024x80] -0.574707 1.099609 0.077087 ..
|<- 1. 0x1438fc9b0 (0x285da6440:0) [1x1024x80] -0.349609 0.652344 -0.100403 ..
CCV_NNC_GEMM_FORWARD [1066]: [2] -> [1] (0)
|-> 1. 0x1438fa550 (0x285df77c0:0) [1x1024x80] 0.395996 0.095947 0.136597 ..
|-> 2. 0x1438fa4a0 (0x285da6480:0) [1x1024x80] 1.074219 1.585938 -0.672363 ..
|<- 1. 0x1438b38d0 (0x285da6a40:0) [1x1024x1024] 12.000000 8.179688 7.320312 ..
CCV_NNC_SOFTMAX_FORWARD [1067]: [1] -> [1] (0)
|-> 1. 0x1438fa600 (0x285da6a40:0) [1024x1024] 12.000000 8.179688 7.320312 ..
|<- 1. 0x1438fa600 (0x285da6a40:0) [1024x1024] 0.145142 0.003183 0.001348 ..
CCV_NNC_GEMM_FORWARD [1068]: [2] -> [1] (0)
|-> 1. 0x1438fa720 (0x285da6a40:0) [1x1024x1024] 0.145142 0.003183 0.001348 ..
|-> 2. 0x1438fa670 (0x285da6200:0) [1x1024x80] 0.641602 1.889648 -2.398438 ..
|<- 1. 0x1438fca60 (0x285da6440:0) [1x1024x80] 0.862793 0.747070 -1.107422 ..
CCV_NNC_GEMM_FORWARD [1069]: [2] -> [1] (0)
|-> 1. 0x1438fa840 (0x285df77c0:0) [1x1024x80] -0.019272 -0.103821 0.011749 ..
|-> 2. 0x1438fa790 (0x285da6480:0) [1x1024x80] -0.899414 1.210938 -3.439453 ..
|<- 1. 0x1438b3940 (0x285da6a40:0) [1x1024x1024] 9.718750 6.210938 6.535156 ..
CCV_NNC_SOFTMAX_FORWARD [1070]: [1] -> [1] (0)
|-> 1. 0x1438fa8f0 (0x285da6a40:0) [1024x1024] 9.718750 6.210938 6.535156 ..
|<- 1. 0x1438fa8f0 (0x285da6a40:0) [1024x1024] 0.050140 0.001502 0.002077 ..
CCV_NNC_GEMM_FORWARD [1071]: [2] -> [1] (0)
|-> 1. 0x1438faa10 (0x285da6a40:0) [1x1024x1024] 0.050140 0.001502 0.002077 ..
|-> 2. 0x1438fa960 (0x285da6200:0) [1x1024x80] 0.067627 -0.346191 1.285156 ..
|<- 1. 0x1438fcb10 (0x285da6440:0) [1x1024x80] 0.209839 0.197266 0.341309 ..
CCV_NNC_GEMM_FORWARD [1072]: [2] -> [1] (0)
|-> 1. 0x1438fab30 (0x285df77c0:0) [1x1024x80] 0.162109 -0.019989 0.143188 ..
|-> 2. 0x1438faa80 (0x285da6480:0) [1x1024x80] 0.217285 0.928223 0.564941 ..
|<- 1. 0x1438b39b0 (0x285da6a40:0) [1x1024x1024] 6.863281 5.515625 4.871094 ..
CCV_NNC_SOFTMAX_FORWARD [1073]: [1] -> [1] (0)
|-> 1. 0x1438fabe0 (0x285da6a40:0) [1024x1024] 6.863281 5.515625 4.871094 ..
|<- 1. 0x1438fabe0 (0x285da6a40:0) [1024x1024] 0.038879 0.010101 0.005302 ..
CCV_NNC_GEMM_FORWARD [1074]: [2] -> [1] (0)
|-> 1. 0x1438fad00 (0x285da6a40:0) [1x1024x1024] 0.038879 0.010101 0.005302 ..
|-> 2. 0x1438fac50 (0x285da6200:0) [1x1024x80] -2.605469 -0.640137 -2.230469 ..
|<- 1. 0x1438fcbc0 (0x285da6440:0) [1x1024x80] -1.278320 -0.217407 -0.659180 ..
CCV_NNC_GEMM_FORWARD [1075]: [2] -> [1] (0)
|-> 1. 0x1438fae20 (0x285df77c0:0) [1x1024x80] -0.098450 0.082520 -0.078369 ..
|-> 2. 0x1438fad70 (0x285da6480:0) [1x1024x80] 1.118164 0.899414 -1.043945 ..
|<- 1. 0x1438b3a20 (0x285da6a40:0) [1x1024x1024] 8.867188 6.843750 6.515625 ..
CCV_NNC_SOFTMAX_FORWARD [1076]: [1] -> [1] (0)
|-> 1. 0x1438faed0 (0x285da6a40:0) [1024x1024] 8.867188 6.843750 6.515625 ..
|<- 1. 0x1438faed0 (0x285da6a40:0) [1024x1024] 0.062744 0.008293 0.005974 ..
CCV_NNC_GEMM_FORWARD [1077]: [2] -> [1] (0)
|-> 1. 0x1438faff0 (0x285da6a40:0) [1x1024x1024] 0.062744 0.008293 0.005974 ..
|-> 2. 0x1438faf40 (0x285da6200:0) [1x1024x80] -0.328857 -0.922363 0.826660 ..
|<- 1. 0x1438fcc70 (0x285da6440:0) [1x1024x80] -0.347412 0.001214 0.536133 ..
CCV_NNC_GEMM_FORWARD [1078]: [2] -> [1] (0)
|-> 1. 0x1438fb110 (0x285df77c0:0) [1x1024x80] -0.021927 0.053253 -0.091064 ..
|-> 2. 0x1438fb060 (0x285da6480:0) [1x1024x80] -1.745117 0.699707 -2.273438 ..
|<- 1. 0x1438b3a90 (0x285da6a40:0) [1x1024x1024] 7.902344 4.640625 3.664062 ..
CCV_NNC_SOFTMAX_FORWARD [1079]: [1] -> [1] (0)
|-> 1. 0x1438fb1c0 (0x285da6a40:0) [1024x1024] 7.902344 4.640625 3.664062 ..
|<- 1. 0x1438fb1c0 (0x285da6a40:0) [1024x1024] 0.207275 0.007942 0.002991 ..
CCV_NNC_GEMM_FORWARD [1080]: [2] -> [1] (0)
|-> 1. 0x1438fb2e0 (0x285da6a40:0) [1x1024x1024] 0.207275 0.007942 0.002991 ..
|-> 2. 0x1438fb230 (0x285da6200:0) [1x1024x80] -1.315430 -0.680176 -1.226562 ..
|<- 1. 0x1438fcd20 (0x285da6440:0) [1x1024x80] -0.783691 -0.452637 -0.495117 ..
CCV_NNC_GEMM_FORWARD [1081]: [2] -> [1] (0)
|-> 1. 0x1438fb400 (0x285df77c0:0) [1x1024x80] -0.011406 0.242432 0.042206 ..
|-> 2. 0x1438fb350 (0x285da6480:0) [1x1024x80] 0.708008 2.251953 -0.971191 ..
|<- 1. 0x1438b3b00 (0x285da6a40:0) [1x1024x1024] 4.933594 4.113281 3.576172 ..
CCV_NNC_SOFTMAX_FORWARD [1082]: [1] -> [1] (0)
|-> 1. 0x1438fb4b0 (0x285da6a40:0) [1024x1024] 4.933594 4.113281 3.576172 ..
|<- 1. 0x1438fb4b0 (0x285da6a40:0) [1024x1024] 0.048645 0.021423 0.012520 ..
CCV_NNC_GEMM_FORWARD [1083]: [2] -> [1] (0)
|-> 1. 0x1438fb5d0 (0x285da6a40:0) [1x1024x1024] 0.048645 0.021423 0.012520 ..
|-> 2. 0x1438fb520 (0x285da6200:0) [1x1024x80] 1.591797 -0.169434 -0.897461 ..
|<- 1. 0x1438fcdd0 (0x285da6440:0) [1x1024x80] 1.650391 -0.547363 -0.398193 ..
CCV_NNC_GEMM_FORWARD [1084]: [2] -> [1] (0)
|-> 1. 0x1438fb6f0 (0x285df77c0:0) [1x1024x80] -0.036224 0.046967 0.144653 ..
|-> 2. 0x1438fb640 (0x285da6480:0) [1x1024x80] 1.212891 -0.765625 -0.355225 ..
|<- 1. 0x1438b3b70 (0x285da6a40:0) [1x1024x1024] 10.734375 8.875000 8.320312 ..
CCV_NNC_SOFTMAX_FORWARD [1085]: [1] -> [1] (0)
|-> 1. 0x1438fb7a0 (0x285da6a40:0) [1024x1024] 10.734375 8.875000 8.320312 ..
|<- 1. 0x1438fb7a0 (0x285da6a40:0) [1024x1024] 0.166260 0.025894 0.014870 ..
CCV_NNC_GEMM_FORWARD [1086]: [2] -> [1] (0)
|-> 1. 0x1438fb8c0 (0x285da6a40:0) [1x1024x1024] 0.166260 0.025894 0.014870 ..
|-> 2. 0x1438fb810 (0x285da6200:0) [1x1024x80] 1.184570 0.406494 1.345703 ..
|<- 1. 0x1438fce80 (0x285da6440:0) [1x1024x80] 0.907715 -0.385986 0.723633 ..
CCV_NNC_GEMM_FORWARD [1087]: [2] -> [1] (0)
|-> 1. 0x1438fb9e0 (0x285df77c0:0) [1x1024x80] 0.025208 -0.258301 -0.009644 ..
|-> 2. 0x1438fb930 (0x285da6480:0) [1x1024x80] -2.501953 -1.279297 -1.924805 ..
|<- 1. 0x1438b3be0 (0x285da6a40:0) [1x1024x1024] 8.218750 4.582031 3.949219 ..
CCV_NNC_SOFTMAX_FORWARD [1088]: [1] -> [1] (0)
|-> 1. 0x1438fba90 (0x285da6a40:0) [1024x1024] 8.218750 4.582031 3.949219 ..
|<- 1. 0x1438fba90 (0x285da6a40:0) [1024x1024] 0.029465 0.000776 0.000412 ..
CCV_NNC_GEMM_FORWARD [1089]: [2] -> [1] (0)
|-> 1. 0x1438fbbb0 (0x285da6a40:0) [1x1024x1024] 0.029465 0.000776 0.000412 ..
|-> 2. 0x1438fbb00 (0x285da6200:0) [1x1024x80] -0.411621 -0.152832 -0.058990 ..
|<- 1. 0x1438fcf30 (0x285da6440:0) [1x1024x80] -0.340576 0.598145 0.068726 ..
CCV_NNC_GEMM_FORWARD [1090]: [2] -> [1] (0)
|-> 1. 0x1438fbcd0 (0x285df77c0:0) [1x1024x80] 0.190918 0.075012 0.030991 ..
|-> 2. 0x1438fbc20 (0x285da6480:0) [1x1024x80] 0.249023 1.406250 -0.586914 ..
|<- 1. 0x1438b3c50 (0x285da6a40:0) [1x1024x1024] 10.195312 7.882812 7.691406 ..
CCV_NNC_SOFTMAX_FORWARD [1091]: [1] -> [1] (0)
|-> 1. 0x1438fbd80 (0x285da6a40:0) [1024x1024] 10.195312 7.882812 7.691406 ..
|<- 1. 0x1438fbd80 (0x285da6a40:0) [1024x1024] 0.129517 0.012825 0.010590 ..
CCV_NNC_GEMM_FORWARD [1092]: [2] -> [1] (0)
|-> 1. 0x1438fbea0 (0x285da6a40:0) [1x1024x1024] 0.129517 0.012825 0.010590 ..
|-> 2. 0x1438fbdf0 (0x285da6200:0) [1x1024x80] -0.445557 0.682129 -1.758789 ..
|<- 1. 0x1438fcfe0 (0x285da6440:0) [1x1024x80] 0.112549 0.340088 -1.012695 ..
CCV_NNC_GEMM_FORWARD [1093]: [2] -> [1] (0)
|-> 1. 0x1438fbfc0 (0x285df77c0:0) [1x1024x80] 0.015450 -0.055664 0.019714 ..
|-> 2. 0x1438fbf10 (0x285da6480:0) [1x1024x80] -1.585938 1.376953 -3.314453 ..
|<- 1. 0x1438b3cc0 (0x285da6a40:0) [1x1024x1024] 8.085938 5.375000 4.058594 ..
CCV_NNC_SOFTMAX_FORWARD [1094]: [1] -> [1] (0)
|-> 1. 0x1438fc070 (0x285da6a40:0) [1024x1024] 8.085938 5.375000 4.058594 ..
|<- 1. 0x1438fc070 (0x285da6a40:0) [1024x1024] 0.090454 0.006016 0.001613 ..
CCV_NNC_GEMM_FORWARD [1095]: [2] -> [1] (0)
|-> 1. 0x1438fc190 (0x285da6a40:0) [1x1024x1024] 0.090454 0.006016 0.001613 ..
|-> 2. 0x1438fc0e0 (0x285da6200:0) [1x1024x80] -0.291504 -0.235474 0.512695 ..
|<- 1. 0x1438fd090 (0x285da6440:0) [1x1024x80] 0.010147 0.340820 0.092346 ..
CCV_NNC_GEMM_FORWARD [1096]: [2] -> [1] (0)
|-> 1. 0x1438fc2b0 (0x285df77c0:0) [1x1024x80] 0.202515 -0.060425 0.113770 ..
|-> 2. 0x1438fc200 (0x285da6480:0) [1x1024x80] 0.569824 0.371094 0.895996 ..
|<- 1. 0x1438b3d30 (0x285da6a40:0) [1x1024x1024] 6.632812 5.851562 4.843750 ..
CCV_NNC_SOFTMAX_FORWARD [1097]: [1] -> [1] (0)
|-> 1. 0x1438fc360 (0x285da6a40:0) [1024x1024] 6.632812 5.851562 4.843750 ..
|<- 1. 0x1438fc360 (0x285da6a40:0) [1024x1024] 0.079590 0.036438 0.013298 ..
CCV_NNC_GEMM_FORWARD [1098]: [2] -> [1] (0)
|-> 1. 0x1438fc480 (0x285da6a40:0) [1x1024x1024] 0.079590 0.036438 0.013298 ..
|-> 2. 0x1438fc3d0 (0x285da6200:0) [1x1024x80] -2.998047 -0.884277 -1.756836 ..
|<- 1. 0x1438fd140 (0x285da6440:0) [1x1024x80] -1.086914 -0.827637 -1.216797 ..
CCV_NNC_GEMM_FORWARD [1099]: [2] -> [1] (0)
|-> 1. 0x1438fc5a0 (0x285df77c0:0) [1x1024x80] 0.015121 0.020782 0.007282 ..
|-> 2. 0x1438fc4f0 (0x285da6480:0) [1x1024x80] 1.905273 0.151123 -1.991211 ..
|<- 1. 0x1438b3da0 (0x285da6a40:0) [1x1024x1024] 7.542969 6.515625 5.761719 ..
CCV_NNC_SOFTMAX_FORWARD [1100]: [1] -> [1] (0)
|-> 1. 0x1438fc650 (0x285da6a40:0) [1024x1024] 7.542969 6.515625 5.761719 ..
|<- 1. 0x1438fc650 (0x285da6a40:0) [1024x1024] 0.067749 0.024246 0.011414 ..
CCV_NNC_GEMM_FORWARD [1101]: [2] -> [1] (0)
|-> 1. 0x1438fc770 (0x285da6a40:0) [1x1024x1024] 0.067749 0.024246 0.011414 ..
|-> 2. 0x1438fc6c0 (0x285da6200:0) [1x1024x80] -0.400879 0.031891 0.479736 ..
|<- 1. 0x1438fd1f0 (0x285da6440:0) [1x1024x80] -0.313232 0.100342 -0.046082 ..
CCV_NNC_TRANSPOSE_FORWARD [1102]: [1] -> [1] (0)
|-> 1. 0x1438fd2a0 (0x285da6440:0) [2x8x1024x80] -0.406494 -0.149292 -0.776855 ..
|<- 1. 0x1438b3e80 (0x285da6480:0) [2x1024x8x80] -0.406494 -0.149292 -0.776855 ..
CCV_NNC_GEMM_FORWARD [1103]: [3] -> [1] (0)
|-> 1. 0x1438fd310 (0x285da6480:0) [2x1024x640] -0.406494 -0.149292 -0.776855 ..
|-> 2. 0x1438cad20 (0x285d9ab80:0) [640x640] -0.012177 0.042786 -0.010574 ..
|-> 3. 0x1438cad90 (0x285d9abc0:0) [640] 0.045715 -0.017365 -0.002123 ..
|<- 1. 0x1438b3ef0 (0x285da6440:0) [2x1024x640] -1.027344 0.172485 -0.229126 ..
CCV_NNC_ADD_FORWARD [1104]: [2] -> [1] (0)
|-> 1. 0x1438b3ef0 (0x285da6440:0) [2x1024x640] -1.027344 0.172485 -0.229126 ..
|-> 2. 0x1438f97e0 (0x285da61c0:0) [2x1024x640] -4.050781 0.651367 -1.082031 ..
|<- 1. 0x1438b3ef0 (0x285da6440:0) [2x1024x640] -5.078125 0.823730 -1.311523 ..
CCV_NNC_LAYER_NORM_FORWARD [1105]: [3] -> [3] (0)
|-> 1. 0x1438b3ef0 (0x285da6440:0) [2x1024x640] -5.078125 0.823730 -1.311523 ..
|-> 2. 0x1438cae00 (0x285d9ac00:0) [1x1x640] 0.628418 0.670410 0.625000 ..
|-> 3. 0x1438cae70 (0x285d9ac40:0) [1x1x640] -0.086426 0.027649 -0.236450 ..
|<- 1. 0x1438b3f60 (0x285da61c0:0) [2x1024x640] -2.027344 0.314941 -0.763672 ..
|<- 2. 0x1438b3fd0 (0x285df6340:0) [2x1024x1] 0.104065 ..
|<- 3. 0x1438b4040 (0x285df6640:0) [2x1024x1] 0.595703 ..
CCV_NNC_GEMM_FORWARD [1106]: [2] -> [1] (0)
|-> 1. 0x1438b3f60 (0x285da61c0:0) [2x1024x640] -2.027344 0.314941 -0.763672 ..
|-> 2. 0x1438caee0 (0x285d9ac80:0) [640x640] -0.005630 -0.052368 -0.010986 ..
|<- 1. 0x1438b40b0 (0x285da6480:0) [2x1024x640] -0.700195 -0.820312 0.155029 ..
CCV_NNC_SCALAR_MUL_FORWARD [1107]: [1] -> [1] (0)
|-> 1. 0x1438b40b0 (0x285da6480:0) [2x1024x640] -0.700195 -0.820312 0.155029 ..
|<- 1. 0x1438b40b0 (0x285da6480:0) [2x1024x640] -0.078308 -0.091736 0.017334 ..
CCV_NNC_TRANSPOSE_FORWARD [1108]: [1] -> [1] (0)
|-> 1. 0x1438fd3f0 (0x285da6480:0) [2x1024x8x80] -0.078308 -0.091736 0.017334 ..
|<- 1. 0x1438b4200 (0x285da6200:0) [2x8x1024x80] -0.078308 -0.091736 0.017334 ..
CCV_NNC_GEMM_FORWARD [1109]: [2] -> [1] (0)
Wait: (0, 110)
|-> 1. 0x1438b4200 (0x285da6200:0) [2x8x1024x80] -0.078308 -0.091736 0.017334 ..
|-> 2. 0x1438b4190 (0x285df3a00:0) [2x8x133x80] -0.624512 0.743164 -0.471924 ..
|<- 1. 0x1438b4270 (0x285da65c0:0) [2x8x1024x133] 11.007812 0.559082 2.984375 ..
CCV_NNC_SOFTMAX_FORWARD [1110]: [1] -> [1] (0)
|-> 1. 0x1438fd460 (0x285da65c0:0) [16384x133] 11.007812 0.559082 2.984375 ..
|<- 1. 0x1438fd460 (0x285da65c0:0) [16384x133] 0.997559 0.000029 0.000327 ..
CCV_NNC_GEMM_FORWARD [1111]: [2] -> [1] (0)
Wait: (0, 111)
|-> 1. 0x1438fd540 (0x285da65c0:0) [2x8x1024x133] 0.997559 0.000029 0.000327 ..
|-> 2. 0x1438b4350 (0x285df34c0:0) [2x8x133x80] -0.003769 -0.020844 -0.024673 ..
|<- 1. 0x1438b43c0 (0x285da6200:0) [2x8x1024x80] -0.002960 -0.020828 -0.025955 ..
CCV_NNC_TRANSPOSE_FORWARD [1112]: [1] -> [1] (0)
|-> 1. 0x1438fd5b0 (0x285da6200:0) [2x8x1024x80] -0.002960 -0.020828 -0.025955 ..
|<- 1. 0x1438b4430 (0x285da61c0:0) [2x1024x8x80] -0.002960 -0.020828 -0.025955 ..
CCV_NNC_GEMM_FORWARD [1113]: [3] -> [1] (0)
|-> 1. 0x1438fd620 (0x285da61c0:0) [2x1024x640] -0.002960 -0.020828 -0.025955 ..
|-> 2. 0x1438cb030 (0x285d9ad40:0) [640x640] -0.022522 -0.016708 -0.080933 ..
|-> 3. 0x1438cb0a0 (0x285d9ad80:0) [640] 0.058624 -0.042572 0.005444 ..
|<- 1. 0x1438b44a0 (0x285da69c0:0) [2x1024x640] 0.314697 -0.147217 0.098511 ..
CCV_NNC_ADD_FORWARD [1114]: [2] -> [1] (0)
|-> 1. 0x1438b44a0 (0x285da69c0:0) [2x1024x640] 0.314697 -0.147217 0.098511 ..
|-> 2. 0x1438b3ef0 (0x285da6440:0) [2x1024x640] -5.078125 0.823730 -1.311523 ..
|<- 1. 0x1438b44a0 (0x285da69c0:0) [2x1024x640] -4.761719 0.676758 -1.212891 ..
CCV_NNC_LAYER_NORM_FORWARD [1115]: [3] -> [3] (0)
|-> 1. 0x1438b44a0 (0x285da69c0:0) [2x1024x640] -4.761719 0.676758 -1.212891 ..
|-> 2. 0x1438cb110 (0x285d9adc0:0) [1x1x640] 0.554199 0.599609 0.568848 ..
|-> 3. 0x1438cb180 (0x285d9ae00:0) [1x1x640] -0.168335 0.053772 0.048218 ..
|<- 1. 0x1438b4510 (0x285da6c80:0) [2x1024x640] -1.705078 0.246582 -0.380371 ..
|<- 2. 0x1438b4580 (0x285df3440:0) [2x1024x1] 0.111511 ..
|<- 3. 0x1438b45f0 (0x285df04c0:0) [2x1024x1] 0.568848 ..
Emit: (0, 112)
CCV_NNC_GEMM_FORWARD [1116]: [3] -> [1] (0)
|-> 1. 0x1438b4510 (0x285da6c80:0) [2x1024x640] -1.705078 0.246582 -0.380371 ..
|-> 2. 0x1438cb1f0 (0x285d9ae40:0) [2560x640] -0.012077 -0.010094 -0.071472 ..
|-> 3. 0x1438cb260 (0x285d9ae80:0) [2560] 0.060455 0.003229 0.109253 ..
|<- 1. 0x1438b4660 (0x285da6740:0) [2x1024x2560] 0.008530 -0.821777 0.839355 ..
CCV_NNC_GELU_FORWARD [1117]: [1] -> [1] (0)
|-> 1. 0x1438b4660 (0x285da6740:0) [2x1024x2560] 0.008530 -0.821777 0.839355 ..
|<- 1. 0x1438b4660 (0x285da6740:0) [2x1024x2560] 0.004295 -0.168945 0.670898 ..
CCV_NNC_GEMM_FORWARD [1118]: [3] -> [1] (1)
Wait: (1, 112)
|-> 1. 0x1438b4510 (0x285da6c80:0) [2x1024x640] -1.705078 0.246582 -0.380371 ..
|-> 2. 0x1438cb2d0 (0x285d9aec0:0) [2560x640] 0.037872 -0.020813 0.006653 ..
|-> 3. 0x1438cb340 (0x285d9af00:0) [2560] 0.006737 -0.069885 0.003771 ..
|<- 1. 0x1438b46d0 (0x285da6780:0) [2x1024x2560] 0.019150 -0.985352 0.680176 ..
Emit: (1, 113)
CCV_NNC_MUL_FORWARD [1119]: [2] -> [1] (0)
Wait: (0, 113)
|-> 1. 0x1438b46d0 (0x285da6780:0) [2x1024x2560] 0.019150 -0.985352 0.680176 ..
|-> 2. 0x1438b4660 (0x285da6740:0) [2x1024x2560] 0.004295 -0.168945 0.670898 ..
|<- 1. 0x1438b46d0 (0x285da6780:0) [2x1024x2560] 0.000082 0.166504 0.456299 ..
CCV_NNC_GEMM_FORWARD [1120]: [3] -> [1] (0)
|-> 1. 0x1438b46d0 (0x285da6780:0) [2x1024x2560] 0.000082 0.166504 0.456299 ..
|-> 2. 0x1438cb3b0 (0x285d9af40:0) [640x2560] 0.078125 -0.080627 0.054596 ..
|-> 3. 0x1438cb420 (0x285d9af80:0) [640] 0.032166 0.039581 0.050507 ..
|<- 1. 0x1438b4740 (0x285da6900:0) [2x1024x640] 1.244141 -1.011719 0.771484 ..
CCV_NNC_ADD_FORWARD [1121]: [2] -> [1] (0)
|-> 1. 0x1438b4740 (0x285da6900:0) [2x1024x640] 1.244141 -1.011719 0.771484 ..
|-> 2. 0x1438b44a0 (0x285da69c0:0) [2x1024x640] -4.761719 0.676758 -1.212891 ..
|<- 1. 0x1438b4740 (0x285da6900:0) [2x1024x640] -3.517578 -0.334961 -0.441406 ..
CCV_NNC_CONVOLUTION_FORWARD [1122]: [3] -> [1] (0)
|-> 1. 0x1438fd690 (0x285da6900:0) [2x32x32x640] -3.517578 -0.334961 -0.441406 ..
|-> 2. 0x1438cb490 (0x285d9afc0:0) [640x640x1x1] -0.019455 ..
|-> 3. 0x1438cb500 (0x285d9b000:0) [640] 0.020035 -0.083984 -0.027573 ..
|<- 1. 0x1438b47b0 (0x285da6480:0) [2x32x32x640] -0.189453 -1.632812 1.898438 ..
CCV_NNC_ADD_FORWARD [1123]: [2] -> [1] (0)
|-> 1. 0x1438b47b0 (0x285da6480:0) [2x32x32x640] -0.189453 -1.632812 1.898438 ..
|-> 2. 0x1438b30f0 (0x285da62c0:0) [2x32x32x640] 2.439453 -0.757812 8.531250 ..
|<- 1. 0x1438fd700 (0x285da5980:0) [2x32x32x640] 2.250000 -2.390625 10.429688 ..
Emit: (0, 115)
CCV_NNC_GROUP_NORM_FORWARD [1124]: [3] -> [3] (0)
|-> 1. 0x1438b4820 (0x285da5980:0) [2x32x32x1280] 2.250000 -2.390625 10.429688 ..
|-> 2. 0x1438cb570 (0x285d9b040:0) [1x1x1x1280] 0.348877 0.208130 0.154419 ..
|-> 3. 0x1438cb5e0 (0x285d9b080:0) [1x1x1x1280] -0.095276 -0.012260 0.000666 ..
|<- 1. 0x1438b4890 (0x285da56c0:0) [2x32x32x1280] 0.168701 -0.221924 0.597656 ..
|<- 2. 0x1438b4900 (0x285da6880:0) [2x1x1x32] 0.259277 0.320557 -0.147705 ..
|<- 3. 0x1438b4970 (0x285da68c0:0) [2x1x1x32] 0.380127 0.296631 0.354492 ..
CCV_NNC_SWISH_FORWARD [1125]: [1] -> [1] (0)
|-> 1. 0x1438b4890 (0x285da56c0:0) [2x32x32x1280] 0.168701 -0.221924 0.597656 ..
|<- 1. 0x1438b4890 (0x285da56c0:0) [2x32x32x1280] 0.091431 -0.098694 0.385498 ..
CCV_NNC_CONVOLUTION_FORWARD [1126]: [3] -> [1] (0)
|-> 1. 0x1438b4890 (0x285da56c0:0) [2x32x32x1280] 0.091431 -0.098694 0.385498 ..
|-> 2. 0x1438cb730 (0x285d9b140:0) [640x1280x3x3] 0.023132 -0.018478 -0.010208 ..
|-> 3. 0x1438cb7a0 (0x285d9b180:0) [640] 0.049561 -0.049164 -0.064270 ..
|<- 1. 0x1438b4a50 (0x285da6900:0) [2x32x32x640] 0.536621 0.736328 -0.935547 ..
CCV_NNC_ADD_FORWARD [1127]: [2] -> [1] (0)
Wait: (0, 114)
|-> 1. 0x1438b4a50 (0x285da6900:0) [2x32x32x640] 0.536621 0.736328 -0.935547 ..
|-> 2. 0x1438fd860 (0x285df3880:0) [2x1x1x640] 0.327637 -0.112061 0.204590 ..
|<- 1. 0x1438b4a50 (0x285da6900:0) [2x32x32x640] 0.864258 0.624023 -0.730957 ..
CCV_NNC_GROUP_NORM_FORWARD [1128]: [3] -> [3] (0)
|-> 1. 0x1438b4a50 (0x285da6900:0) [2x32x32x640] 0.864258 0.624023 -0.730957 ..
|-> 2. 0x1438cb810 (0x285d9b1c0:0) [1x1x1x640] 0.701172 1.098633 0.985352 ..
|-> 3. 0x1438cb880 (0x285d9b200:0) [1x1x1x640] -0.384766 -0.416992 -0.247803 ..
|<- 1. 0x1438b4ac0 (0x285da6480:0) [2x32x32x640] -0.078613 -0.220825 -1.505859 ..
|<- 2. 0x1438b4b30 (0x285da73c0:0) [2x1x1x32] 0.457764 0.240845 0.434570 ..
|<- 3. 0x1438b4ba0 (0x285da7400:0) [2x1x1x32] 1.074219 1.084961 1.072266 ..
CCV_NNC_SWISH_FORWARD [1129]: [1] -> [1] (0)
|-> 1. 0x1438b4ac0 (0x285da6480:0) [2x32x32x640] -0.078613 -0.220825 -1.505859 ..
|<- 1. 0x1438b4ac0 (0x285da6480:0) [2x32x32x640] -0.037750 -0.098267 -0.273438 ..
CCV_NNC_CONVOLUTION_FORWARD [1130]: [3] -> [1] (0)
|-> 1. 0x1438b4ac0 (0x285da6480:0) [2x32x32x640] -0.037750 -0.098267 -0.273438 ..
|-> 2. 0x1438cb8f0 (0x285d9b240:0) [640x640x3x3] -0.011276 -0.066528 -0.028992 ..
|-> 3. 0x1438cb960 (0x285d9b280:0) [640] -0.036926 0.037872 -0.057709 ..
|<- 1. 0x1438b4c10 (0x285da6900:0) [2x32x32x640] 2.128906 0.881836 -3.003906 ..
CCV_NNC_CONVOLUTION_FORWARD [1131]: [3] -> [1] (1)
Wait: (1, 115)
|-> 1. 0x1438b4820 (0x285da5980:0) [2x32x32x1280] 2.250000 -2.390625 10.429688 ..
|-> 2. 0x1438cb9d0 (0x285d9b2c0:0) [640x1280x1x1] -0.016281 ..
|-> 3. 0x1438cba40 (0x285d9b300:0) [640] -0.030899 0.043091 -0.066040 ..
|<- 1. 0x1438b4c80 (0x285da62c0:0) [2x32x32x640] 4.031250 2.068359 1.596680 ..
Emit: (1, 116)
CCV_NNC_ADD_FORWARD [1132]: [2] -> [1] (0)
Wait: (0, 116)
|-> 1. 0x1438b4c80 (0x285da62c0:0) [2x32x32x640] 4.031250 2.068359 1.596680 ..
|-> 2. 0x1438b4c10 (0x285da6900:0) [2x32x32x640] 2.128906 0.881836 -3.003906 ..
|<- 1. 0x1438b4c80 (0x285da62c0:0) [2x32x32x640] 6.160156 2.949219 -1.407227 ..
CCV_NNC_GROUP_NORM_FORWARD [1133]: [3] -> [3] (0)
|-> 1. 0x1438b4c80 (0x285da62c0:0) [2x32x32x640] 6.160156 2.949219 -1.407227 ..
|-> 2. 0x1438cbab0 (0x285d9b340:0) [1x1x1x640] 0.534180 0.542480 0.524902 ..
|-> 3. 0x1438cbb20 (0x285d9b380:0) [1x1x1x640] -0.119385 0.006519 0.113098 ..
|<- 1. 0x1438b4cf0 (0x285da6900:0) [2x32x32x640] 1.582031 0.863281 -0.201294 ..
|<- 2. 0x1438b4d60 (0x285da5740:0) [2x1x1x32] -0.209229 0.553223 -0.221924 ..
|<- 3. 0x1438b4dd0 (0x285da5700:0) [2x1x1x32] 0.500000 0.471680 0.536133 ..
CCV_NNC_CONVOLUTION_FORWARD [1134]: [3] -> [1] (0)
|-> 1. 0x1438b4cf0 (0x285da6900:0) [2x32x32x640] 1.582031 0.863281 -0.201294 ..
|-> 2. 0x1438cbb90 (0x285d9b3c0:0) [640x640x1x1] -0.045441 ..
|-> 3. 0x1438cbc00 (0x285d9b400:0) [640] 0.070984 0.085327 0.044617 ..
|<- 1. 0x1438b4e40 (0x285da6480:0) [2x32x32x640] 0.435059 1.207031 -0.772461 ..
CCV_NNC_LAYER_NORM_FORWARD [1135]: [3] -> [3] (0)
|-> 1. 0x1438fd8d0 (0x285da6480:0) [2x1024x640] 0.435059 1.207031 -0.772461 ..
|-> 2. 0x1438cbc70 (0x285d9b440:0) [1x1x640] 0.688477 0.641602 0.764648 ..
|-> 3. 0x1438cbce0 (0x285d9b480:0) [1x1x640] -0.024811 0.018936 0.091858 ..
|<- 1. 0x1438b4eb0 (0x285da6900:0) [2x1024x640] 0.196655 0.561523 -0.289307 ..
|<- 2. 0x1438b4f20 (0x285da6980:0) [2x1024x1] -0.038513 ..
|<- 3. 0x1438b4f90 (0x285df3a80:0) [2x1024x1] 0.679199 ..
Emit: (0, 117)
CCV_NNC_GEMM_FORWARD [1136]: [2] -> [1] (0)
|-> 1. 0x1438b4eb0 (0x285da6900:0) [2x1024x640] 0.196655 0.561523 -0.289307 ..
|-> 2. 0x1438cbd50 (0x285d9b4c0:0) [640x640] -0.081299 -0.182983 -0.128784 ..
|<- 1. 0x1438b5000 (0x285da63c0:0) [2x1024x640] -0.748535 -1.299805 1.466797 ..
CCV_NNC_SCALAR_MUL_FORWARD [1137]: [1] -> [1] (0)
|-> 1. 0x1438b5000 (0x285da63c0:0) [2x1024x640] -0.748535 -1.299805 1.466797 ..
|<- 1. 0x1438b5000 (0x285da63c0:0) [2x1024x640] -0.083679 -0.145386 0.164062 ..
CCV_NNC_TRANSPOSE_FORWARD [1138]: [1] -> [1] (0)
|-> 1. 0x1438fd9b0 (0x285da63c0:0) [2x1024x8x80] -0.083679 -0.145386 0.164062 ..
|<- 1. 0x1438b5150 (0x285da61c0:0) [2x8x1024x80] -0.083679 -0.145386 0.164062 ..
CCV_NNC_GEMM_FORWARD [1139]: [2] -> [1] (1)
Wait: (1, 117)
|-> 1. 0x1438b4eb0 (0x285da6900:0) [2x1024x640] 0.196655 0.561523 -0.289307 ..
|-> 2. 0x1438cbdc0 (0x285d9b500:0) [640x640] -0.016510 -0.015404 0.061310 ..
|<- 1. 0x1438b5070 (0x285da6400:0) [2x1024x640] 0.303223 -0.942871 2.898438 ..
CCV_NNC_TRANSPOSE_FORWARD [1140]: [1] -> [1] (1)
|-> 1. 0x1438fd940 (0x285da6400:0) [2x1024x8x80] 0.303223 -0.942871 2.898438 ..
|<- 1. 0x1438b50e0 (0x285da6440:0) [2x8x1024x80] 0.303223 -0.942871 2.898438 ..
Emit: (1, 118)
CCV_NNC_GEMM_FORWARD [1141]: [2] -> [1] (2)
Wait: (2, 117)
|-> 1. 0x1438b4eb0 (0x285da6900:0) [2x1024x640] 0.196655 0.561523 -0.289307 ..
|-> 2. 0x1438cbe30 (0x285d9b540:0) [640x640] 0.048279 0.015762 -0.024597 ..
|<- 1. 0x1438b51c0 (0x285da64c0:0) [2x1024x640] 0.349854 0.400146 -0.986328 ..
CCV_NNC_TRANSPOSE_FORWARD [1142]: [1] -> [1] (2)
|-> 1. 0x1438fdb00 (0x285da64c0:0) [2x1024x8x80] 0.349854 0.400146 -0.986328 ..
|<- 1. 0x1438b52a0 (0x285da6300:0) [2x8x1024x80] 0.349854 0.400146 -0.986328 ..
Emit: (2, 119)
CCV_NNC_GEMM_FORWARD [1143]: [2] -> [1] (0)
Wait: (0, 118)
|-> 1. 0x1438fda90 (0x285da61c0:0) [1x1024x80] -0.083679 -0.145386 0.164062 ..
|-> 2. 0x1438fda20 (0x285da6440:0) [1x1024x80] 0.303223 -0.942871 2.898438 ..
|<- 1. 0x1438b5230 (0x285da6500:0) [1x1024x1024] 9.125000 6.324219 5.953125 ..
CCV_NNC_SOFTMAX_FORWARD [1144]: [1] -> [1] (0)
|-> 1. 0x1438fdb70 (0x285da6500:0) [1024x1024] 9.125000 6.324219 5.953125 ..
|<- 1. 0x1438fdb70 (0x285da6500:0) [1024x1024] 0.088867 0.005402 0.003727 ..
CCV_NNC_GEMM_FORWARD [1145]: [2] -> [1] (0)
Wait: (0, 119)
|-> 1. 0x1438fdc50 (0x285da6500:0) [1x1024x1024] 0.088867 0.005402 0.003727 ..
|-> 2. 0x1438fdbe0 (0x285da6300:0) [1x1024x80] 0.349854 0.400146 -0.986328 ..
|<- 1. 0x1439008d0 (0x285da6900:0) [1x1024x80] 0.251709 0.124329 -0.160522 ..
CCV_NNC_GEMM_FORWARD [1146]: [2] -> [1] (0)
|-> 1. 0x1438fdd70 (0x285da61c0:0) [1x1024x80] 0.039612 -0.106384 0.004818 ..
|-> 2. 0x1438fdcc0 (0x285da6440:0) [1x1024x80] 0.294678 -2.785156 0.544434 ..
|<- 1. 0x1438b5310 (0x285da6500:0) [1x1024x1024] 7.187500 6.179688 6.246094 ..
CCV_NNC_SOFTMAX_FORWARD [1147]: [1] -> [1] (0)
|-> 1. 0x1438fde20 (0x285da6500:0) [1024x1024] 7.187500 6.179688 6.246094 ..
|<- 1. 0x1438fde20 (0x285da6500:0) [1024x1024] 0.015991 0.005836 0.006241 ..
CCV_NNC_GEMM_FORWARD [1148]: [2] -> [1] (0)
|-> 1. 0x1438fdf40 (0x285da6500:0) [1x1024x1024] 0.015991 0.005836 0.006241 ..
|-> 2. 0x1438fde90 (0x285da6300:0) [1x1024x80] 0.707031 0.604492 0.451172 ..
|<- 1. 0x143900940 (0x285da6900:0) [1x1024x80] 0.421387 0.062073 0.249390 ..
CCV_NNC_GEMM_FORWARD [1149]: [2] -> [1] (0)
|-> 1. 0x1438fe060 (0x285da61c0:0) [1x1024x80] 0.068787 -0.033844 -0.122498 ..
|-> 2. 0x1438fdfb0 (0x285da6440:0) [1x1024x80] -2.189453 -0.781250 -2.013672 ..
|<- 1. 0x1438b5380 (0x285da6500:0) [1x1024x1024] 9.671875 8.242188 7.500000 ..
CCV_NNC_SOFTMAX_FORWARD [1150]: [1] -> [1] (0)
|-> 1. 0x1438fe110 (0x285da6500:0) [1024x1024] 9.671875 8.242188 7.500000 ..
|<- 1. 0x1438fe110 (0x285da6500:0) [1024x1024] 0.050629 0.012115 0.005768 ..
CCV_NNC_GEMM_FORWARD [1151]: [2] -> [1] (0)
|-> 1. 0x1438fe230 (0x285da6500:0) [1x1024x1024] 0.050629 0.012115 0.005768 ..
|-> 2. 0x1438fe180 (0x285da6300:0) [1x1024x80] -0.841797 -0.464355 -0.812500 ..
|<- 1. 0x1439009f0 (0x285da6900:0) [1x1024x80] -0.292725 -0.004795 -0.311035 ..
CCV_NNC_GEMM_FORWARD [1152]: [2] -> [1] (0)
|-> 1. 0x1438fe350 (0x285da61c0:0) [1x1024x80] 0.115112 0.301025 0.013199 ..
|-> 2. 0x1438fe2a0 (0x285da6440:0) [1x1024x80] 0.410400 1.400391 0.180786 ..
|<- 1. 0x1438b53f0 (0x285da6500:0) [1x1024x1024] 6.929688 2.871094 2.326172 ..
CCV_NNC_SOFTMAX_FORWARD [1153]: [1] -> [1] (0)
|-> 1. 0x1438fe400 (0x285da6500:0) [1024x1024] 6.929688 2.871094 2.326172 ..
|<- 1. 0x1438fe400 (0x285da6500:0) [1024x1024] 0.008217 0.000142 0.000082 ..
CCV_NNC_GEMM_FORWARD [1154]: [2] -> [1] (0)
|-> 1. 0x1438fe520 (0x285da6500:0) [1x1024x1024] 0.008217 0.000142 0.000082 ..
|-> 2. 0x1438fe470 (0x285da6300:0) [1x1024x80] -0.363281 0.162231 0.040985 ..
|<- 1. 0x143900aa0 (0x285da6900:0) [1x1024x80] 0.601074 0.089111 0.244263 ..
CCV_NNC_GEMM_FORWARD [1155]: [2] -> [1] (0)
|-> 1. 0x1438fe640 (0x285da61c0:0) [1x1024x80] 0.026794 0.202148 -0.193481 ..
|-> 2. 0x1438fe590 (0x285da6440:0) [1x1024x80] 1.017578 2.259766 -1.029297 ..
|<- 1. 0x1438b5460 (0x285da6500:0) [1x1024x1024] 9.695312 7.917969 8.234375 ..
CCV_NNC_SOFTMAX_FORWARD [1156]: [1] -> [1] (0)
|-> 1. 0x1438fe6f0 (0x285da6500:0) [1024x1024] 9.695312 7.917969 8.234375 ..
|<- 1. 0x1438fe6f0 (0x285da6500:0) [1024x1024] 0.035522 0.006008 0.008240 ..
CCV_NNC_GEMM_FORWARD [1157]: [2] -> [1] (0)
|-> 1. 0x1438fe810 (0x285da6500:0) [1x1024x1024] 0.035522 0.006008 0.008240 ..
|-> 2. 0x1438fe760 (0x285da6300:0) [1x1024x80] 0.113770 -2.037109 1.186523 ..
|<- 1. 0x143900b50 (0x285da6900:0) [1x1024x80] -0.186768 -1.440430 0.526855 ..
CCV_NNC_GEMM_FORWARD [1158]: [2] -> [1] (0)
|-> 1. 0x1438fe930 (0x285da61c0:0) [1x1024x80] -0.289307 -0.203003 -0.209961 ..
|-> 2. 0x1438fe880 (0x285da6440:0) [1x1024x80] -3.289062 -1.369141 -0.828125 ..
|<- 1. 0x1438b54d0 (0x285da6500:0) [1x1024x1024] 10.710938 7.425781 7.300781 ..
CCV_NNC_SOFTMAX_FORWARD [1159]: [1] -> [1] (0)
|-> 1. 0x1438fe9e0 (0x285da6500:0) [1024x1024] 10.710938 7.425781 7.300781 ..
|<- 1. 0x1438fe9e0 (0x285da6500:0) [1024x1024] 0.104248 0.003902 0.003445 ..
CCV_NNC_GEMM_FORWARD [1160]: [2] -> [1] (0)
|-> 1. 0x1438feb00 (0x285da6500:0) [1x1024x1024] 0.104248 0.003902 0.003445 ..
|-> 2. 0x1438fea50 (0x285da6300:0) [1x1024x80] 1.570312 0.113892 0.033203 ..
|<- 1. 0x143900c00 (0x285da6900:0) [1x1024x80] 1.144531 0.071045 -0.189697 ..
CCV_NNC_GEMM_FORWARD [1161]: [2] -> [1] (0)
|-> 1. 0x1438fec20 (0x285da61c0:0) [1x1024x80] -0.112488 0.033417 0.124817 ..
|-> 2. 0x1438feb70 (0x285da6440:0) [1x1024x80] -2.361328 0.327148 1.335938 ..
|<- 1. 0x1438b5540 (0x285da6500:0) [1x1024x1024] 9.117188 6.726562 6.761719 ..
CCV_NNC_SOFTMAX_FORWARD [1162]: [1] -> [1] (0)
|-> 1. 0x1438fecd0 (0x285da6500:0) [1024x1024] 9.117188 6.726562 6.761719 ..
|<- 1. 0x1438fecd0 (0x285da6500:0) [1024x1024] 0.062622 0.005733 0.005939 ..
CCV_NNC_GEMM_FORWARD [1163]: [2] -> [1] (0)
|-> 1. 0x1438fedf0 (0x285da6500:0) [1x1024x1024] 0.062622 0.005733 0.005939 ..
|-> 2. 0x1438fed40 (0x285da6300:0) [1x1024x80] -1.561523 0.216675 0.079102 ..
|<- 1. 0x143900cb0 (0x285da6900:0) [1x1024x80] -0.437256 -0.018661 0.170898 ..
CCV_NNC_GEMM_FORWARD [1164]: [2] -> [1] (0)
|-> 1. 0x1438fef10 (0x285da61c0:0) [1x1024x80] 0.211670 0.118469 -0.038544 ..
|-> 2. 0x1438fee60 (0x285da6440:0) [1x1024x80] 2.093750 1.329102 -0.355713 ..
|<- 1. 0x1438b55b0 (0x285da6500:0) [1x1024x1024] 9.312500 6.441406 6.476562 ..
CCV_NNC_SOFTMAX_FORWARD [1165]: [1] -> [1] (0)
|-> 1. 0x1438fefc0 (0x285da6500:0) [1024x1024] 9.312500 6.441406 6.476562 ..
|<- 1. 0x1438fefc0 (0x285da6500:0) [1024x1024] 0.076904 0.004356 0.004509 ..
CCV_NNC_GEMM_FORWARD [1166]: [2] -> [1] (0)
|-> 1. 0x1438ff0e0 (0x285da6500:0) [1x1024x1024] 0.076904 0.004356 0.004509 ..
|-> 2. 0x1438ff030 (0x285da6300:0) [1x1024x80] -0.719238 -0.450439 -0.077271 ..
|<- 1. 0x143900d60 (0x285da6900:0) [1x1024x80] -0.152100 0.037018 -0.095581 ..
CCV_NNC_GEMM_FORWARD [1167]: [2] -> [1] (0)
|-> 1. 0x1438ff200 (0x285da61c0:0) [1x1024x80] -0.051849 -0.109497 0.154785 ..
|-> 2. 0x1438ff150 (0x285da6440:0) [1x1024x80] -0.158203 -0.573242 3.302734 ..
|<- 1. 0x1438b5620 (0x285da6500:0) [1x1024x1024] 9.742188 7.671875 6.585938 ..
CCV_NNC_SOFTMAX_FORWARD [1168]: [1] -> [1] (0)
|-> 1. 0x1438ff2b0 (0x285da6500:0) [1024x1024] 9.742188 7.671875 6.585938 ..
|<- 1. 0x1438ff2b0 (0x285da6500:0) [1024x1024] 0.128906 0.016251 0.005486 ..
CCV_NNC_GEMM_FORWARD [1169]: [2] -> [1] (0)
|-> 1. 0x1438ff3d0 (0x285da6500:0) [1x1024x1024] 0.128906 0.016251 0.005486 ..
|-> 2. 0x1438ff320 (0x285da6300:0) [1x1024x80] 0.228271 0.659180 -0.205078 ..
|<- 1. 0x143900e10 (0x285da6900:0) [1x1024x80] 0.178833 0.197021 0.030228 ..
CCV_NNC_GEMM_FORWARD [1170]: [2] -> [1] (0)
|-> 1. 0x1438ff4f0 (0x285da61c0:0) [1x1024x80] 0.001628 -0.031128 -0.060394 ..
|-> 2. 0x1438ff440 (0x285da6440:0) [1x1024x80] -0.342773 -2.083984 0.778320 ..
|<- 1. 0x1438b5690 (0x285da6500:0) [1x1024x1024] 7.890625 7.039062 6.425781 ..
CCV_NNC_SOFTMAX_FORWARD [1171]: [1] -> [1] (0)
|-> 1. 0x1438ff5a0 (0x285da6500:0) [1024x1024] 7.890625 7.039062 6.425781 ..
|<- 1. 0x1438ff5a0 (0x285da6500:0) [1024x1024] 0.031372 0.013382 0.007248 ..
CCV_NNC_GEMM_FORWARD [1172]: [2] -> [1] (0)
|-> 1. 0x1438ff6c0 (0x285da6500:0) [1x1024x1024] 0.031372 0.013382 0.007248 ..
|-> 2. 0x1438ff610 (0x285da6300:0) [1x1024x80] 0.725586 0.770996 0.296387 ..
|<- 1. 0x143900ec0 (0x285da6900:0) [1x1024x80] 0.150635 0.479980 -0.303711 ..
CCV_NNC_GEMM_FORWARD [1173]: [2] -> [1] (0)
|-> 1. 0x1438ff7e0 (0x285da61c0:0) [1x1024x80] 0.051941 -0.137451 -0.081787 ..
|-> 2. 0x1438ff730 (0x285da6440:0) [1x1024x80] -1.098633 -0.538574 -1.790039 ..
|<- 1. 0x1438b5700 (0x285da6500:0) [1x1024x1024] 7.425781 6.550781 6.003906 ..
CCV_NNC_SOFTMAX_FORWARD [1174]: [1] -> [1] (0)
|-> 1. 0x1438ff890 (0x285da6500:0) [1024x1024] 7.425781 6.550781 6.003906 ..
|<- 1. 0x1438ff890 (0x285da6500:0) [1024x1024] 0.018936 0.007896 0.004570 ..
CCV_NNC_GEMM_FORWARD [1175]: [2] -> [1] (0)
|-> 1. 0x1438ff9b0 (0x285da6500:0) [1x1024x1024] 0.018936 0.007896 0.004570 ..
|-> 2. 0x1438ff900 (0x285da6300:0) [1x1024x80] -0.150391 0.125488 -0.615723 ..
|<- 1. 0x143900f70 (0x285da6900:0) [1x1024x80] -0.163452 0.236572 0.105652 ..
CCV_NNC_GEMM_FORWARD [1176]: [2] -> [1] (0)
|-> 1. 0x1438ffad0 (0x285da61c0:0) [1x1024x80] 0.038025 0.229126 -0.016830 ..
|-> 2. 0x1438ffa20 (0x285da6440:0) [1x1024x80] 0.412842 1.302734 0.852051 ..
|<- 1. 0x1438b5770 (0x285da6500:0) [1x1024x1024] 6.207031 4.675781 3.884766 ..
CCV_NNC_SOFTMAX_FORWARD [1177]: [1] -> [1] (0)
|-> 1. 0x1438ffb80 (0x285da6500:0) [1024x1024] 6.207031 4.675781 3.884766 ..
|<- 1. 0x1438ffb80 (0x285da6500:0) [1024x1024] 0.020233 0.004375 0.001984 ..
CCV_NNC_GEMM_FORWARD [1178]: [2] -> [1] (0)
|-> 1. 0x1438ffca0 (0x285da6500:0) [1x1024x1024] 0.020233 0.004375 0.001984 ..
|-> 2. 0x1438ffbf0 (0x285da6300:0) [1x1024x80] 0.580078 -0.054504 -0.119995 ..
|<- 1. 0x143901020 (0x285da6900:0) [1x1024x80] 0.567383 0.057770 -0.253174 ..
CCV_NNC_GEMM_FORWARD [1179]: [2] -> [1] (0)
|-> 1. 0x1438ffdc0 (0x285da61c0:0) [1x1024x80] 0.073303 0.101929 -0.182007 ..
|-> 2. 0x1438ffd10 (0x285da6440:0) [1x1024x80] 1.126953 1.458984 -1.231445 ..
|<- 1. 0x1438b57e0 (0x285da6500:0) [1x1024x1024] 8.515625 7.183594 7.035156 ..
CCV_NNC_SOFTMAX_FORWARD [1180]: [1] -> [1] (0)
|-> 1. 0x1438ffe70 (0x285da6500:0) [1024x1024] 8.515625 7.183594 7.035156 ..
|<- 1. 0x1438ffe70 (0x285da6500:0) [1024x1024] 0.050903 0.013435 0.011581 ..
CCV_NNC_GEMM_FORWARD [1181]: [2] -> [1] (0)
|-> 1. 0x1438fff90 (0x285da6500:0) [1x1024x1024] 0.050903 0.013435 0.011581 ..
|-> 2. 0x1438ffee0 (0x285da6300:0) [1x1024x80] -0.080444 -1.358398 0.574707 ..
|<- 1. 0x1439010d0 (0x285da6900:0) [1x1024x80] -0.305176 -0.811523 0.206787 ..
CCV_NNC_GEMM_FORWARD [1182]: [2] -> [1] (0)
|-> 1. 0x1439000b0 (0x285da61c0:0) [1x1024x80] -0.253906 -0.162476 -0.071960 ..
|-> 2. 0x143900000 (0x285da6440:0) [1x1024x80] -3.494141 -1.486328 -0.551758 ..
|<- 1. 0x1438b5850 (0x285da6500:0) [1x1024x1024] 8.273438 6.683594 6.355469 ..
CCV_NNC_SOFTMAX_FORWARD [1183]: [1] -> [1] (0)
|-> 1. 0x143900160 (0x285da6500:0) [1024x1024] 8.273438 6.683594 6.355469 ..
|<- 1. 0x143900160 (0x285da6500:0) [1024x1024] 0.035095 0.007156 0.005154 ..
CCV_NNC_GEMM_FORWARD [1184]: [2] -> [1] (0)
|-> 1. 0x143900280 (0x285da6500:0) [1x1024x1024] 0.035095 0.007156 0.005154 ..
|-> 2. 0x1439001d0 (0x285da6300:0) [1x1024x80] 0.285645 -0.017975 -0.390137 ..
|<- 1. 0x143901180 (0x285da6900:0) [1x1024x80] 0.384766 -0.544434 0.282471 ..
CCV_NNC_GEMM_FORWARD [1185]: [2] -> [1] (0)
|-> 1. 0x1439003a0 (0x285da61c0:0) [1x1024x80] -0.101196 0.080322 0.217285 ..
|-> 2. 0x1439002f0 (0x285da6440:0) [1x1024x80] -2.357422 0.837891 2.626953 ..
|<- 1. 0x1438b58c0 (0x285da6500:0) [1x1024x1024] 8.390625 6.953125 6.710938 ..
CCV_NNC_SOFTMAX_FORWARD [1186]: [1] -> [1] (0)
|-> 1. 0x143900450 (0x285da6500:0) [1024x1024] 8.390625 6.953125 6.710938 ..
|<- 1. 0x143900450 (0x285da6500:0) [1024x1024] 0.049194 0.011681 0.009171 ..
CCV_NNC_GEMM_FORWARD [1187]: [2] -> [1] (0)
|-> 1. 0x143900570 (0x285da6500:0) [1x1024x1024] 0.049194 0.011681 0.009171 ..
|-> 2. 0x1439004c0 (0x285da6300:0) [1x1024x80] -0.961426 -0.256592 0.435791 ..
|<- 1. 0x143901230 (0x285da6900:0) [1x1024x80] -0.064819 -0.468018 0.296387 ..
CCV_NNC_GEMM_FORWARD [1188]: [2] -> [1] (0)
|-> 1. 0x143900690 (0x285da61c0:0) [1x1024x80] 0.205688 0.085999 0.015152 ..
|-> 2. 0x1439005e0 (0x285da6440:0) [1x1024x80] 2.449219 1.639648 -0.094238 ..
|<- 1. 0x1438b5930 (0x285da6500:0) [1x1024x1024] 7.214844 6.191406 5.847656 ..
CCV_NNC_SOFTMAX_FORWARD [1189]: [1] -> [1] (0)
|-> 1. 0x143900740 (0x285da6500:0) [1024x1024] 7.214844 6.191406 5.847656 ..
|<- 1. 0x143900740 (0x285da6500:0) [1024x1024] 0.022034 0.007919 0.005615 ..
CCV_NNC_GEMM_FORWARD [1190]: [2] -> [1] (0)
|-> 1. 0x143900860 (0x285da6500:0) [1x1024x1024] 0.022034 0.007919 0.005615 ..
|-> 2. 0x1439007b0 (0x285da6300:0) [1x1024x80] -0.628906 -0.072571 -0.035248 ..
|<- 1. 0x1439012e0 (0x285da6900:0) [1x1024x80] 0.223145 -0.116089 0.053436 ..
CCV_NNC_TRANSPOSE_FORWARD [1191]: [1] -> [1] (0)
|-> 1. 0x143901390 (0x285da6900:0) [2x8x1024x80] 0.251709 0.124329 -0.160522 ..
|<- 1. 0x1438b5a10 (0x285da6300:0) [2x1024x8x80] 0.251709 0.124329 -0.160522 ..
CCV_NNC_GEMM_FORWARD [1192]: [3] -> [1] (0)
|-> 1. 0x143901400 (0x285da6300:0) [2x1024x640] 0.251709 0.124329 -0.160522 ..
|-> 2. 0x1438cbea0 (0x285d9b580:0) [640x640] -0.029297 0.035706 0.045868 ..
|-> 3. 0x1438cbf10 (0x285d9b5c0:0) [640] 0.019989 0.002819 0.027924 ..
|<- 1. 0x1438b5a80 (0x285da6900:0) [2x1024x640] -0.188843 0.015717 -0.780762 ..
CCV_NNC_ADD_FORWARD [1193]: [2] -> [1] (0)
|-> 1. 0x1438b5a80 (0x285da6900:0) [2x1024x640] -0.188843 0.015717 -0.780762 ..
|-> 2. 0x1438fd8d0 (0x285da6480:0) [2x1024x640] 0.435059 1.207031 -0.772461 ..
|<- 1. 0x1438b5a80 (0x285da6900:0) [2x1024x640] 0.246216 1.222656 -1.552734 ..
CCV_NNC_LAYER_NORM_FORWARD [1194]: [3] -> [3] (0)
|-> 1. 0x1438b5a80 (0x285da6900:0) [2x1024x640] 0.246216 1.222656 -1.552734 ..
|-> 2. 0x1438cbf80 (0x285d9b600:0) [1x1x640] 0.553223 0.550293 0.534668 ..
|-> 3. 0x1438cbff0 (0x285d9b640:0) [1x1x640] 0.002466 -0.014275 0.110657 ..
|<- 1. 0x1438b5af0 (0x285da6480:0) [2x1024x640] 0.138306 0.531250 -0.492432 ..
|<- 2. 0x1438b5b60 (0x285da66c0:0) [2x1024x1] -0.075439 ..
|<- 3. 0x1438b5bd0 (0x285da6700:0) [2x1024x1] 0.763672 ..
CCV_NNC_GEMM_FORWARD [1195]: [2] -> [1] (0)
|-> 1. 0x1438b5af0 (0x285da6480:0) [2x1024x640] 0.138306 0.531250 -0.492432 ..
|-> 2. 0x1438cc060 (0x285d9b680:0) [640x640] -0.029160 0.016571 0.088013 ..
|<- 1. 0x1438b5c40 (0x285da6300:0) [2x1024x640] 0.563965 -0.315918 0.181152 ..
CCV_NNC_SCALAR_MUL_FORWARD [1196]: [1] -> [1] (0)
|-> 1. 0x1438b5c40 (0x285da6300:0) [2x1024x640] 0.563965 -0.315918 0.181152 ..
|<- 1. 0x1438b5c40 (0x285da6300:0) [2x1024x640] 0.063049 -0.035339 0.020248 ..
CCV_NNC_TRANSPOSE_FORWARD [1197]: [1] -> [1] (0)
|-> 1. 0x1439014e0 (0x285da6300:0) [2x1024x8x80] 0.063049 -0.035339 0.020248 ..
|<- 1. 0x1438b5d90 (0x285da6440:0) [2x8x1024x80] 0.063049 -0.035339 0.020248 ..
CCV_NNC_GEMM_FORWARD [1198]: [2] -> [1] (0)
Wait: (0, 120)
|-> 1. 0x1438b5d90 (0x285da6440:0) [2x8x1024x80] 0.063049 -0.035339 0.020248 ..
|-> 2. 0x1438b5d20 (0x285df3940:0) [2x8x133x80] -0.090027 0.466309 0.978516 ..
|<- 1. 0x1438b5e00 (0x285da6bc0:0) [2x8x1024x133] 7.761719 -0.076050 -0.078796 ..
CCV_NNC_SOFTMAX_FORWARD [1199]: [1] -> [1] (0)
|-> 1. 0x143901550 (0x285da6bc0:0) [16384x133] 7.761719 -0.076050 -0.078796 ..
|<- 1. 0x143901550 (0x285da6bc0:0) [16384x133] 0.984375 0.000388 0.000387 ..
CCV_NNC_GEMM_FORWARD [1200]: [2] -> [1] (0)
Wait: (0, 121)
|-> 1. 0x143901630 (0x285da6bc0:0) [2x8x1024x133] 0.984375 0.000388 0.000387 ..
|-> 2. 0x1438b5ee0 (0x285df0740:0) [2x8x133x80] -0.021072 0.016312 -0.006813 ..
|<- 1. 0x1438b5f50 (0x285da6440:0) [2x8x1024x80] -0.015991 0.014717 0.004799 ..
CCV_NNC_TRANSPOSE_FORWARD [1201]: [1] -> [1] (0)
|-> 1. 0x1439016a0 (0x285da6440:0) [2x8x1024x80] -0.015991 0.014717 0.004799 ..
|<- 1. 0x1438b5fc0 (0x285da6480:0) [2x1024x8x80] -0.015991 0.014717 0.004799 ..
CCV_NNC_GEMM_FORWARD [1202]: [3] -> [1] (0)
|-> 1. 0x143901710 (0x285da6480:0) [2x1024x640] -0.015991 0.014717 0.004799 ..
|-> 2. 0x1438cc1b0 (0x285d9b740:0) [640x640] -0.003803 0.000083 -0.015236 ..
|-> 3. 0x1438cc220 (0x285d9b780:0) [640] 0.012428 0.010201 0.002695 ..
|<- 1. 0x1438b6030 (0x285da6400:0) [2x1024x640] 0.050354 0.122681 0.112183 ..
CCV_NNC_ADD_FORWARD [1203]: [2] -> [1] (0)
|-> 1. 0x1438b6030 (0x285da6400:0) [2x1024x640] 0.050354 0.122681 0.112183 ..
|-> 2. 0x1438b5a80 (0x285da6900:0) [2x1024x640] 0.246216 1.222656 -1.552734 ..
|<- 1. 0x1438b6030 (0x285da6400:0) [2x1024x640] 0.296631 1.345703 -1.440430 ..
CCV_NNC_LAYER_NORM_FORWARD [1204]: [3] -> [3] (0)
|-> 1. 0x1438b6030 (0x285da6400:0) [2x1024x640] 0.296631 1.345703 -1.440430 ..
|-> 2. 0x1438cc290 (0x285d9b7c0:0) [1x1x640] 0.484863 0.490723 0.497070 ..
|-> 3. 0x1438cc300 (0x285d9b800:0) [1x1x640] -0.067017 -0.081360 0.056183 ..
|<- 1. 0x1438b60a0 (0x285da6680:0) [2x1024x640] 0.067627 0.433838 -0.441162 ..
|<- 2. 0x1438b6110 (0x285da6cc0:0) [2x1024x1] -0.080811 ..
|<- 3. 0x1438b6180 (0x285da6d00:0) [2x1024x1] 0.735840 ..
Emit: (0, 122)
CCV_NNC_GEMM_FORWARD [1205]: [3] -> [1] (0)
|-> 1. 0x1438b60a0 (0x285da6680:0) [2x1024x640] 0.067627 0.433838 -0.441162 ..
|-> 2. 0x1438cc370 (0x285d9b840:0) [2560x640] 0.018646 0.016739 0.051910 ..
|-> 3. 0x1438cc3e0 (0x285d9b880:0) [2560] 0.071228 0.127563 -0.076660 ..
|<- 1. 0x1438b61f0 (0x285da6740:0) [2x1024x2560] 0.492188 1.601562 -1.694336 ..
CCV_NNC_GELU_FORWARD [1206]: [1] -> [1] (0)
|-> 1. 0x1438b61f0 (0x285da6740:0) [2x1024x2560] 0.492188 1.601562 -1.694336 ..
|<- 1. 0x1438b61f0 (0x285da6740:0) [2x1024x2560] 0.338867 1.513672 -0.076416 ..
CCV_NNC_GEMM_FORWARD [1207]: [3] -> [1] (1)
Wait: (1, 122)
|-> 1. 0x1438b60a0 (0x285da6680:0) [2x1024x640] 0.067627 0.433838 -0.441162 ..
|-> 2. 0x1438cc450 (0x285d9b8c0:0) [2560x640] 0.074402 -0.081177 -0.087036 ..
|-> 3. 0x1438cc4c0 (0x285d9b900:0) [2560] -0.020081 -0.023361 -0.066772 ..
|<- 1. 0x1438b6260 (0x285da6780:0) [2x1024x2560] 1.083008 0.969238 -1.455078 ..
Emit: (1, 123)
CCV_NNC_MUL_FORWARD [1208]: [2] -> [1] (0)
Wait: (0, 123)
|-> 1. 0x1438b6260 (0x285da6780:0) [2x1024x2560] 1.083008 0.969238 -1.455078 ..
|-> 2. 0x1438b61f0 (0x285da6740:0) [2x1024x2560] 0.338867 1.513672 -0.076416 ..
|<- 1. 0x1438b6260 (0x285da6780:0) [2x1024x2560] 0.366943 1.466797 0.111206 ..
CCV_NNC_GEMM_FORWARD [1209]: [3] -> [1] (0)
|-> 1. 0x1438b6260 (0x285da6780:0) [2x1024x2560] 0.366943 1.466797 0.111206 ..
|-> 2. 0x1438cc530 (0x285d9b940:0) [640x2560] 0.005070 -0.054199 -0.118164 ..
|-> 3. 0x1438cc5a0 (0x285d9b980:0) [640] 0.015045 0.004658 0.036041 ..
|<- 1. 0x1438b62d0 (0x285da6900:0) [2x1024x640] -0.155273 0.030228 0.603027 ..
CCV_NNC_ADD_FORWARD [1210]: [2] -> [1] (0)
|-> 1. 0x1438b62d0 (0x285da6900:0) [2x1024x640] -0.155273 0.030228 0.603027 ..
|-> 2. 0x1438b6030 (0x285da6400:0) [2x1024x640] 0.296631 1.345703 -1.440430 ..
|<- 1. 0x1438b62d0 (0x285da6900:0) [2x1024x640] 0.141357 1.375977 -0.837402 ..
CCV_NNC_CONVOLUTION_FORWARD [1211]: [3] -> [1] (0)
|-> 1. 0x143901780 (0x285da6900:0) [2x32x32x640] 0.141357 1.375977 -0.837402 ..
|-> 2. 0x1438cc610 (0x285d9b9c0:0) [640x640x1x1] 0.084778 ..
|-> 3. 0x1438cc680 (0x285d9ba00:0) [640] -0.016479 -0.011429 0.125610 ..
|<- 1. 0x1438b6340 (0x285da6480:0) [2x32x32x640] -1.904297 -1.546875 4.750000 ..
CCV_NNC_ADD_FORWARD [1212]: [2] -> [1] (0)
|-> 1. 0x1438b6340 (0x285da6480:0) [2x32x32x640] -1.904297 -1.546875 4.750000 ..
|-> 2. 0x1438b4c80 (0x285da62c0:0) [2x32x32x640] 6.160156 2.949219 -1.407227 ..
|<- 1. 0x1439017f0 (0x285df0000:0) [2x32x32x640] 4.257812 1.402344 3.343750 ..
Emit: (0, 125)
CCV_NNC_GROUP_NORM_FORWARD [1213]: [3] -> [3] (0)
|-> 1. 0x1438b63b0 (0x285df0000:0) [2x32x32x960] 4.257812 1.402344 3.343750 ..
|-> 2. 0x1438cc6f0 (0x285d9ba40:0) [1x1x1x960] 0.130371 0.134521 0.147949 ..
|-> 3. 0x1438cc760 (0x285d9ba80:0) [1x1x1x960] -0.003691 -0.007427 -0.000031 ..
|<- 1. 0x1438b6420 (0x285df1e80:0) [2x32x32x960] 0.398926 0.116272 0.354248 ..
|<- 2. 0x1438b6490 (0x285da68c0:0) [2x1x1x32] 0.192017 -0.113892 0.253906 ..
|<- 3. 0x1438b6500 (0x285da6880:0) [2x1x1x32] 0.759766 0.657227 0.633789 ..
CCV_NNC_SWISH_FORWARD [1214]: [1] -> [1] (0)
|-> 1. 0x1438b6420 (0x285df1e80:0) [2x32x32x960] 0.398926 0.116272 0.354248 ..
|<- 1. 0x1438b6420 (0x285df1e80:0) [2x32x32x960] 0.238770 0.061523 0.208130 ..
CCV_NNC_CONVOLUTION_FORWARD [1215]: [3] -> [1] (0)
|-> 1. 0x1438b6420 (0x285df1e80:0) [2x32x32x960] 0.238770 0.061523 0.208130 ..
|-> 2. 0x1438cc8b0 (0x285d9bb40:0) [640x960x3x3] 0.001464 -0.060089 -0.022614 ..
|-> 3. 0x1438cc920 (0x285d9bb80:0) [640] 0.025009 0.014687 0.039917 ..
|<- 1. 0x1438b65e0 (0x285da6900:0) [2x32x32x640] -0.379883 0.303955 -0.077393 ..
CCV_NNC_ADD_FORWARD [1216]: [2] -> [1] (0)
Wait: (0, 124)
|-> 1. 0x1438b65e0 (0x285da6900:0) [2x32x32x640] -0.379883 0.303955 -0.077393 ..
|-> 2. 0x143901950 (0x285dffc00:0) [2x1x1x640] -0.846680 0.141968 0.290283 ..
|<- 1. 0x1438b65e0 (0x285da6900:0) [2x32x32x640] -1.226562 0.445801 0.212891 ..
CCV_NNC_GROUP_NORM_FORWARD [1217]: [3] -> [3] (0)
|-> 1. 0x1438b65e0 (0x285da6900:0) [2x32x32x640] -1.226562 0.445801 0.212891 ..
|-> 2. 0x1438cc990 (0x285d9bbc0:0) [1x1x1x640] 0.585449 0.460938 0.664062 ..
|-> 3. 0x1438cca00 (0x285d9bc00:0) [1x1x1x640] -0.198730 -0.172363 -0.088135 ..
|<- 1. 0x1438b6650 (0x285da6480:0) [2x32x32x640] -1.051758 -0.029251 -0.045380 ..
|<- 2. 0x1438b66c0 (0x285da73c0:0) [2x1x1x32] 0.151978 0.126099 0.019089 ..
|<- 3. 0x1438b6730 (0x285da7400:0) [2x1x1x32] 1.056641 0.812500 1.041016 ..
CCV_NNC_SWISH_FORWARD [1218]: [1] -> [1] (0)
|-> 1. 0x1438b6650 (0x285da6480:0) [2x32x32x640] -1.051758 -0.029251 -0.045380 ..
|<- 1. 0x1438b6650 (0x285da6480:0) [2x32x32x640] -0.272217 -0.014412 -0.022171 ..
CCV_NNC_CONVOLUTION_FORWARD [1219]: [3] -> [1] (0)
|-> 1. 0x1438b6650 (0x285da6480:0) [2x32x32x640] -0.272217 -0.014412 -0.022171 ..
|-> 2. 0x1438cca70 (0x285d9bc40:0) [640x640x3x3] 0.039001 -0.051453 -0.022888 ..
|-> 3. 0x1438ccae0 (0x285d9bc80:0) [640] -0.038025 0.001854 0.016617 ..
|<- 1. 0x1438b67a0 (0x285da6900:0) [2x32x32x640] 0.955566 0.156372 -1.109375 ..
CCV_NNC_CONVOLUTION_FORWARD [1220]: [3] -> [1] (1)
Wait: (1, 125)
|-> 1. 0x1438b63b0 (0x285df0000:0) [2x32x32x960] 4.257812 1.402344 3.343750 ..
|-> 2. 0x1438ccb50 (0x285d9bcc0:0) [640x960x1x1] 0.018280 ..
|-> 3. 0x1438ccbc0 (0x285d9bd00:0) [640] -0.034088 0.013550 0.006313 ..
|<- 1. 0x1438b6810 (0x285da62c0:0) [2x32x32x640] 1.112305 -1.458984 -1.874023 ..
Emit: (1, 126)
CCV_NNC_ADD_FORWARD [1221]: [2] -> [1] (0)
Wait: (0, 126)
|-> 1. 0x1438b6810 (0x285da62c0:0) [2x32x32x640] 1.112305 -1.458984 -1.874023 ..
|-> 2. 0x1438b67a0 (0x285da6900:0) [2x32x32x640] 0.955566 0.156372 -1.109375 ..
|<- 1. 0x1438b6810 (0x285da62c0:0) [2x32x32x640] 2.068359 -1.302734 -2.984375 ..
CCV_NNC_GROUP_NORM_FORWARD [1222]: [3] -> [3] (0)
|-> 1. 0x1438b6810 (0x285da62c0:0) [2x32x32x640] 2.068359 -1.302734 -2.984375 ..
|-> 2. 0x1438ccc30 (0x285d9bd40:0) [1x1x1x640] 0.409912 0.435303 0.464600 ..
|-> 3. 0x1438ccca0 (0x285d9bd80:0) [1x1x1x640] -0.059753 0.007980 0.121460 ..
|<- 1. 0x1438b6880 (0x285da6900:0) [2x32x32x640] 0.562988 -0.450439 -0.964355 ..
|<- 2. 0x1438b68f0 (0x285da5700:0) [2x1x1x32] 0.077271 -0.033875 0.142822 ..
|<- 3. 0x1438b6960 (0x285da5740:0) [2x1x1x32] 0.763184 0.752930 0.822266 ..
CCV_NNC_CONVOLUTION_FORWARD [1223]: [3] -> [1] (0)
|-> 1. 0x1438b6880 (0x285da6900:0) [2x32x32x640] 0.562988 -0.450439 -0.964355 ..
|-> 2. 0x1438ccd10 (0x285d9bdc0:0) [640x640x1x1] -0.064270 ..
|-> 3. 0x1438ccd80 (0x285d9be00:0) [640] 0.024033 0.089966 -0.055878 ..
|<- 1. 0x1438b69d0 (0x285da6480:0) [2x32x32x640] -0.023529 1.790039 -0.033813 ..
CCV_NNC_LAYER_NORM_FORWARD [1224]: [3] -> [3] (0)
|-> 1. 0x1439019c0 (0x285da6480:0) [2x1024x640] -0.023529 1.790039 -0.033813 ..
|-> 2. 0x1438ccdf0 (0x285d9be40:0) [1x1x640] 0.560059 0.503906 0.536621 ..
|-> 3. 0x1438cce60 (0x285d9be80:0) [1x1x640] 0.001854 -0.038879 -0.017899 ..
|<- 1. 0x1438b6a40 (0x285da6900:0) [2x1024x640] -0.006580 0.780273 -0.030975 ..
|<- 2. 0x1438b6ab0 (0x285dfe740:0) [2x1024x1] -0.006882 ..
|<- 3. 0x1438b6b20 (0x285da6980:0) [2x1024x1] 0.904785 ..
Emit: (0, 127)
CCV_NNC_GEMM_FORWARD [1225]: [2] -> [1] (0)
|-> 1. 0x1438b6a40 (0x285da6900:0) [2x1024x640] -0.006580 0.780273 -0.030975 ..
|-> 2. 0x1438cced0 (0x285d9bec0:0) [640x640] -0.025726 -0.015991 -0.056732 ..
|<- 1. 0x1438b6b90 (0x285dff880:0) [2x1024x640] -0.450195 0.936523 -0.108704 ..
CCV_NNC_SCALAR_MUL_FORWARD [1226]: [1] -> [1] (0)
|-> 1. 0x1438b6b90 (0x285dff880:0) [2x1024x640] -0.450195 0.936523 -0.108704 ..
|<- 1. 0x1438b6b90 (0x285dff880:0) [2x1024x640] -0.050354 0.104736 -0.012154 ..
CCV_NNC_TRANSPOSE_FORWARD [1227]: [1] -> [1] (0)
|-> 1. 0x143901aa0 (0x285dff880:0) [2x1024x8x80] -0.050354 0.104736 -0.012154 ..
|<- 1. 0x1438b6ce0 (0x285da6a80:0) [2x8x1024x80] -0.050354 0.104736 -0.012154 ..
CCV_NNC_GEMM_FORWARD [1228]: [2] -> [1] (1)
Wait: (1, 127)
|-> 1. 0x1438b6a40 (0x285da6900:0) [2x1024x640] -0.006580 0.780273 -0.030975 ..
|-> 2. 0x1438ccf40 (0x285d9bf00:0) [640x640] -0.001433 0.037476 -0.064514 ..
|<- 1. 0x1438b6c00 (0x285da63c0:0) [2x1024x640] 0.940430 0.647461 0.417236 ..
CCV_NNC_TRANSPOSE_FORWARD [1229]: [1] -> [1] (1)
|-> 1. 0x143901a30 (0x285da63c0:0) [2x1024x8x80] 0.940430 0.647461 0.417236 ..
|<- 1. 0x1438b6c70 (0x285da6a00:0) [2x8x1024x80] 0.940430 0.647461 0.417236 ..
Emit: (1, 128)
CCV_NNC_GEMM_FORWARD [1230]: [2] -> [1] (2)
Wait: (2, 127)
|-> 1. 0x1438b6a40 (0x285da6900:0) [2x1024x640] -0.006580 0.780273 -0.030975 ..
|-> 2. 0x1438ccfb0 (0x285d9bf40:0) [640x640] -0.005463 -0.031769 -0.070190 ..
|<- 1. 0x1438b6d50 (0x285da64c0:0) [2x1024x640] -0.101990 -1.326172 -0.141235 ..
CCV_NNC_TRANSPOSE_FORWARD [1231]: [1] -> [1] (2)
|-> 1. 0x143901bf0 (0x285da64c0:0) [2x1024x8x80] -0.101990 -1.326172 -0.141235 ..
|<- 1. 0x1438b6e30 (0x285da61c0:0) [2x8x1024x80] -0.101990 -1.326172 -0.141235 ..
Emit: (2, 129)
CCV_NNC_GEMM_FORWARD [1232]: [2] -> [1] (0)
Wait: (0, 128)
|-> 1. 0x143901b80 (0x285da6a80:0) [1x1024x80] -0.050354 0.104736 -0.012154 ..
|-> 2. 0x143901b10 (0x285da6a00:0) [1x1024x80] 0.940430 0.647461 0.417236 ..
|<- 1. 0x1438b6dc0 (0x285dff840:0) [1x1024x1024] -0.089478 -0.564941 -0.164673 ..
CCV_NNC_SOFTMAX_FORWARD [1233]: [1] -> [1] (0)
|-> 1. 0x143901c60 (0x285dff840:0) [1024x1024] -0.089478 -0.564941 -0.164673 ..
|<- 1. 0x143901c60 (0x285dff840:0) [1024x1024] 0.001685 0.001047 0.001563 ..
CCV_NNC_GEMM_FORWARD [1234]: [2] -> [1] (0)
Wait: (0, 129)
|-> 1. 0x143901d40 (0x285dff840:0) [1x1024x1024] 0.001685 0.001047 0.001563 ..
|-> 2. 0x143901cd0 (0x285da61c0:0) [1x1024x80] -0.101990 -1.326172 -0.141235 ..
|<- 1. 0x1439049c0 (0x285da6900:0) [1x1024x80] 0.000070 -0.303711 0.164429 ..
CCV_NNC_GEMM_FORWARD [1235]: [2] -> [1] (0)
|-> 1. 0x143901e60 (0x285da6a80:0) [1x1024x80] 0.117065 0.192261 -0.019897 ..
|-> 2. 0x143901db0 (0x285da6a00:0) [1x1024x80] -0.199219 0.241577 2.347656 ..
|<- 1. 0x1438b6ea0 (0x285dff840:0) [1x1024x1024] 3.734375 1.133789 1.357422 ..
CCV_NNC_SOFTMAX_FORWARD [1236]: [1] -> [1] (0)
|-> 1. 0x143901f10 (0x285dff840:0) [1024x1024] 3.734375 1.133789 1.357422 ..
|<- 1. 0x143901f10 (0x285dff840:0) [1024x1024] 0.102051 0.007572 0.009468 ..
CCV_NNC_GEMM_FORWARD [1237]: [2] -> [1] (0)
|-> 1. 0x143902030 (0x285dff840:0) [1x1024x1024] 0.102051 0.007572 0.009468 ..
|-> 2. 0x143901f80 (0x285da61c0:0) [1x1024x80] 1.845703 0.251709 -1.130859 ..
|<- 1. 0x143904a30 (0x285da6900:0) [1x1024x80] 0.478271 -0.060730 -0.504883 ..
CCV_NNC_GEMM_FORWARD [1238]: [2] -> [1] (0)
|-> 1. 0x143902150 (0x285da6a80:0) [1x1024x80] 0.023941 -0.036591 -0.192139 ..
|-> 2. 0x1439020a0 (0x285da6a00:0) [1x1024x80] 0.074341 -0.892578 -0.059601 ..
|<- 1. 0x1438b6f10 (0x285dff840:0) [1x1024x1024] 1.791016 1.305664 1.003906 ..
CCV_NNC_SOFTMAX_FORWARD [1239]: [1] -> [1] (0)
|-> 1. 0x143902200 (0x285dff840:0) [1024x1024] 1.791016 1.305664 1.003906 ..
|<- 1. 0x143902200 (0x285dff840:0) [1024x1024] 0.009239 0.005688 0.004208 ..
CCV_NNC_GEMM_FORWARD [1240]: [2] -> [1] (0)
|-> 1. 0x143902320 (0x285dff840:0) [1x1024x1024] 0.009239 0.005688 0.004208 ..
|-> 2. 0x143902270 (0x285da61c0:0) [1x1024x80] 0.000818 -0.793945 1.489258 ..
|<- 1. 0x143904ae0 (0x285da6900:0) [1x1024x80] -0.088623 0.124084 -0.033447 ..
CCV_NNC_GEMM_FORWARD [1241]: [2] -> [1] (0)
|-> 1. 0x143902440 (0x285da6a80:0) [1x1024x80] 0.141479 -0.055817 0.021347 ..
|-> 2. 0x143902390 (0x285da6a00:0) [1x1024x80] 1.022461 -1.147461 1.112305 ..
|<- 1. 0x1438b6f80 (0x285dff840:0) [1x1024x1024] 2.380859 0.767578 1.263672 ..
CCV_NNC_SOFTMAX_FORWARD [1242]: [1] -> [1] (0)
|-> 1. 0x1439024f0 (0x285dff840:0) [1024x1024] 2.380859 0.767578 1.263672 ..
|<- 1. 0x1439024f0 (0x285dff840:0) [1024x1024] 0.010139 0.002020 0.003317 ..
CCV_NNC_GEMM_FORWARD [1243]: [2] -> [1] (0)
|-> 1. 0x143902610 (0x285dff840:0) [1x1024x1024] 0.010139 0.002020 0.003317 ..
|-> 2. 0x143902560 (0x285da61c0:0) [1x1024x80] 0.443604 -0.927246 0.185913 ..
|<- 1. 0x143904b90 (0x285da6900:0) [1x1024x80] 0.226440 -0.285400 0.151733 ..
CCV_NNC_GEMM_FORWARD [1244]: [2] -> [1] (0)
|-> 1. 0x143902730 (0x285da6a80:0) [1x1024x80] 0.142456 -0.021576 -0.005299 ..
|-> 2. 0x143902680 (0x285da6a00:0) [1x1024x80] 1.263672 0.920898 -0.771484 ..
|<- 1. 0x1438b6ff0 (0x285dff840:0) [1x1024x1024] 3.597656 2.455078 1.973633 ..
CCV_NNC_SOFTMAX_FORWARD [1245]: [1] -> [1] (0)
|-> 1. 0x1439027e0 (0x285dff840:0) [1024x1024] 3.597656 2.455078 1.973633 ..
|<- 1. 0x1439027e0 (0x285dff840:0) [1024x1024] 0.013466 0.004295 0.002653 ..
CCV_NNC_GEMM_FORWARD [1246]: [2] -> [1] (0)
|-> 1. 0x143902900 (0x285dff840:0) [1x1024x1024] 0.013466 0.004295 0.002653 ..
|-> 2. 0x143902850 (0x285da61c0:0) [1x1024x80] -0.461426 -0.364014 0.093506 ..
|<- 1. 0x143904c40 (0x285da6900:0) [1x1024x80] -0.563477 0.365234 -0.283691 ..
CCV_NNC_GEMM_FORWARD [1247]: [2] -> [1] (0)
|-> 1. 0x143902a20 (0x285da6a80:0) [1x1024x80] 0.055084 -0.009857 0.112244 ..
|-> 2. 0x143902970 (0x285da6a00:0) [1x1024x80] -2.332031 0.864258 -1.558594 ..
|<- 1. 0x1438b7060 (0x285dff840:0) [1x1024x1024] 6.550781 2.126953 2.304688 ..
CCV_NNC_SOFTMAX_FORWARD [1248]: [1] -> [1] (0)
|-> 1. 0x143902ad0 (0x285dff840:0) [1024x1024] 6.550781 2.126953 2.304688 ..
|<- 1. 0x143902ad0 (0x285dff840:0) [1024x1024] 0.097534 0.001169 0.001397 ..
CCV_NNC_GEMM_FORWARD [1249]: [2] -> [1] (0)
|-> 1. 0x143902bf0 (0x285dff840:0) [1x1024x1024] 0.097534 0.001169 0.001397 ..
|-> 2. 0x143902b40 (0x285da61c0:0) [1x1024x80] -0.192993 0.328857 0.298096 ..
|<- 1. 0x143904cf0 (0x285da6900:0) [1x1024x80] 0.023575 0.273682 0.152832 ..
CCV_NNC_GEMM_FORWARD [1250]: [2] -> [1] (0)
|-> 1. 0x143902d10 (0x285da6a80:0) [1x1024x80] 0.086487 -0.134888 0.087891 ..
|-> 2. 0x143902c60 (0x285da6a00:0) [1x1024x80] 0.727539 -0.129517 -0.079529 ..
|<- 1. 0x1438b70d0 (0x285dff840:0) [1x1024x1024] 4.707031 2.427734 2.566406 ..
CCV_NNC_SOFTMAX_FORWARD [1251]: [1] -> [1] (0)
|-> 1. 0x143902dc0 (0x285dff840:0) [1024x1024] 4.707031 2.427734 2.566406 ..
|<- 1. 0x143902dc0 (0x285dff840:0) [1024x1024] 0.031921 0.003267 0.003752 ..
CCV_NNC_GEMM_FORWARD [1252]: [2] -> [1] (0)
|-> 1. 0x143902ee0 (0x285dff840:0) [1x1024x1024] 0.031921 0.003267 0.003752 ..
|-> 2. 0x143902e30 (0x285da61c0:0) [1x1024x80] -0.069641 -0.373535 -0.208862 ..
|<- 1. 0x143904da0 (0x285da6900:0) [1x1024x80] -0.180786 -0.169189 0.177246 ..
CCV_NNC_GEMM_FORWARD [1253]: [2] -> [1] (0)
|-> 1. 0x143903000 (0x285da6a80:0) [1x1024x80] 0.069580 -0.042999 0.017075 ..
|-> 2. 0x143902f50 (0x285da6a00:0) [1x1024x80] -1.295898 -1.235352 -1.113281 ..
|<- 1. 0x1438b7140 (0x285dff840:0) [1x1024x1024] 3.189453 2.869141 2.613281 ..
CCV_NNC_SOFTMAX_FORWARD [1254]: [1] -> [1] (0)
|-> 1. 0x1439030b0 (0x285dff840:0) [1024x1024] 3.189453 2.869141 2.613281 ..
|<- 1. 0x1439030b0 (0x285dff840:0) [1024x1024] 0.008408 0.006107 0.004726 ..
CCV_NNC_GEMM_FORWARD [1255]: [2] -> [1] (0)
|-> 1. 0x1439031d0 (0x285dff840:0) [1x1024x1024] 0.008408 0.006107 0.004726 ..
|-> 2. 0x143903120 (0x285da61c0:0) [1x1024x80] 0.348877 0.081421 -0.234253 ..
|<- 1. 0x143904e50 (0x285da6900:0) [1x1024x80] 0.412354 -0.336426 0.131714 ..
CCV_NNC_GEMM_FORWARD [1256]: [2] -> [1] (0)
|-> 1. 0x1439032f0 (0x285da6a80:0) [1x1024x80] -0.013992 0.151733 -0.050781 ..
|-> 2. 0x143903240 (0x285da6a00:0) [1x1024x80] 0.730469 0.699219 0.505371 ..
|<- 1. 0x1438b71b0 (0x285dff840:0) [1x1024x1024] -0.512207 -0.715820 -0.435791 ..
CCV_NNC_SOFTMAX_FORWARD [1257]: [1] -> [1] (0)
|-> 1. 0x1439033a0 (0x285dff840:0) [1024x1024] -0.512207 -0.715820 -0.435791 ..
|<- 1. 0x1439033a0 (0x285dff840:0) [1024x1024] 0.001039 0.000847 0.001121 ..
CCV_NNC_GEMM_FORWARD [1258]: [2] -> [1] (0)
|-> 1. 0x1439034c0 (0x285dff840:0) [1x1024x1024] 0.001039 0.000847 0.001121 ..
|-> 2. 0x143903410 (0x285da61c0:0) [1x1024x80] -0.009598 -0.321289 0.741211 ..
|<- 1. 0x143904f00 (0x285da6900:0) [1x1024x80] 0.102600 0.171997 0.314941 ..
CCV_NNC_GEMM_FORWARD [1259]: [2] -> [1] (0)
|-> 1. 0x1439035e0 (0x285da6a80:0) [1x1024x80] 0.035126 0.071899 0.074951 ..
|-> 2. 0x143903530 (0x285da6a00:0) [1x1024x80] -0.478271 -0.206909 1.852539 ..
|<- 1. 0x1438b7220 (0x285dff840:0) [1x1024x1024] 3.445312 1.535156 1.330078 ..
CCV_NNC_SOFTMAX_FORWARD [1260]: [1] -> [1] (0)
|-> 1. 0x143903690 (0x285dff840:0) [1024x1024] 3.445312 1.535156 1.330078 ..
|<- 1. 0x143903690 (0x285dff840:0) [1024x1024] 0.069031 0.010223 0.008324 ..
CCV_NNC_GEMM_FORWARD [1261]: [2] -> [1] (0)
|-> 1. 0x1439037b0 (0x285dff840:0) [1x1024x1024] 0.069031 0.010223 0.008324 ..
|-> 2. 0x143903700 (0x285da61c0:0) [1x1024x80] 1.397461 -0.162842 -0.536621 ..
|<- 1. 0x143904fb0 (0x285da6900:0) [1x1024x80] -0.073486 0.129395 -0.122864 ..
CCV_NNC_GEMM_FORWARD [1262]: [2] -> [1] (0)
|-> 1. 0x1439038d0 (0x285da6a80:0) [1x1024x80] -0.005535 -0.049072 -0.142822 ..
|-> 2. 0x143903820 (0x285da6a00:0) [1x1024x80] 0.031525 -1.071289 0.246460 ..
|<- 1. 0x1438b7290 (0x285dff840:0) [1x1024x1024] 2.980469 2.539062 2.369141 ..
CCV_NNC_SOFTMAX_FORWARD [1263]: [1] -> [1] (0)
|-> 1. 0x143903980 (0x285dff840:0) [1024x1024] 2.980469 2.539062 2.369141 ..
|<- 1. 0x143903980 (0x285dff840:0) [1024x1024] 0.016754 0.010773 0.009087 ..
CCV_NNC_GEMM_FORWARD [1264]: [2] -> [1] (0)
|-> 1. 0x143903aa0 (0x285dff840:0) [1x1024x1024] 0.016754 0.010773 0.009087 ..
|-> 2. 0x1439039f0 (0x285da61c0:0) [1x1024x80] -0.380127 -1.108398 0.944824 ..
|<- 1. 0x143905060 (0x285da6900:0) [1x1024x80] -0.303711 0.193970 -0.044281 ..
CCV_NNC_GEMM_FORWARD [1265]: [2] -> [1] (0)
|-> 1. 0x143903bc0 (0x285da6a80:0) [1x1024x80] 0.071960 -0.104675 0.021057 ..
|-> 2. 0x143903b10 (0x285da6a00:0) [1x1024x80] 1.617188 -1.411133 1.475586 ..
|<- 1. 0x1438b7300 (0x285dff840:0) [1x1024x1024] 2.593750 1.662109 1.832031 ..
CCV_NNC_SOFTMAX_FORWARD [1266]: [1] -> [1] (0)
|-> 1. 0x143903c70 (0x285dff840:0) [1024x1024] 2.593750 1.662109 1.832031 ..
|<- 1. 0x143903c70 (0x285dff840:0) [1024x1024] 0.007851 0.003094 0.003666 ..
CCV_NNC_GEMM_FORWARD [1267]: [2] -> [1] (0)
|-> 1. 0x143903d90 (0x285dff840:0) [1x1024x1024] 0.007851 0.003094 0.003666 ..
|-> 2. 0x143903ce0 (0x285da61c0:0) [1x1024x80] 0.403564 -0.617188 0.310791 ..
|<- 1. 0x143905110 (0x285da6900:0) [1x1024x80] 0.305420 0.178223 0.007030 ..
CCV_NNC_GEMM_FORWARD [1268]: [2] -> [1] (0)
|-> 1. 0x143903eb0 (0x285da6a80:0) [1x1024x80] 0.119324 -0.018585 -0.060669 ..
|-> 2. 0x143903e00 (0x285da6a00:0) [1x1024x80] 0.730957 1.012695 -1.064453 ..
|<- 1. 0x1438b7370 (0x285dff840:0) [1x1024x1024] 2.958984 2.072266 1.892578 ..
CCV_NNC_SOFTMAX_FORWARD [1269]: [1] -> [1] (0)
|-> 1. 0x143903f60 (0x285dff840:0) [1024x1024] 2.958984 2.072266 1.892578 ..
|<- 1. 0x143903f60 (0x285dff840:0) [1024x1024] 0.007496 0.003088 0.002581 ..
CCV_NNC_GEMM_FORWARD [1270]: [2] -> [1] (0)
|-> 1. 0x143904080 (0x285dff840:0) [1x1024x1024] 0.007496 0.003088 0.002581 ..
|-> 2. 0x143903fd0 (0x285da61c0:0) [1x1024x80] -0.439453 -0.849609 -0.235474 ..
|<- 1. 0x1439051c0 (0x285da6900:0) [1x1024x80] -0.745605 0.161255 -0.291016 ..
CCV_NNC_GEMM_FORWARD [1271]: [2] -> [1] (0)
|-> 1. 0x1439041a0 (0x285da6a80:0) [1x1024x80] 0.054932 0.083557 0.015945 ..
|-> 2. 0x1439040f0 (0x285da6a00:0) [1x1024x80] -1.405273 1.541992 -1.188477 ..
|<- 1. 0x1438b73e0 (0x285dff840:0) [1x1024x1024] 6.273438 3.667969 3.595703 ..
CCV_NNC_SOFTMAX_FORWARD [1272]: [1] -> [1] (0)
|-> 1. 0x143904250 (0x285dff840:0) [1024x1024] 6.273438 3.667969 3.595703 ..
|<- 1. 0x143904250 (0x285dff840:0) [1024x1024] 0.090027 0.006649 0.006184 ..
CCV_NNC_GEMM_FORWARD [1273]: [2] -> [1] (0)
|-> 1. 0x143904370 (0x285dff840:0) [1x1024x1024] 0.090027 0.006649 0.006184 ..
|-> 2. 0x1439042c0 (0x285da61c0:0) [1x1024x80] -0.143677 0.469727 0.208618 ..
|<- 1. 0x143905270 (0x285da6900:0) [1x1024x80] -0.127930 0.135742 -0.100464 ..
CCV_NNC_GEMM_FORWARD [1274]: [2] -> [1] (0)
|-> 1. 0x143904490 (0x285da6a80:0) [1x1024x80] 0.062134 -0.073730 0.042847 ..
|-> 2. 0x1439043e0 (0x285da6a00:0) [1x1024x80] 0.434570 -0.187744 -0.913574 ..
|<- 1. 0x1438b7450 (0x285dff840:0) [1x1024x1024] 3.162109 1.710938 1.617188 ..
CCV_NNC_SOFTMAX_FORWARD [1275]: [1] -> [1] (0)
|-> 1. 0x143904540 (0x285dff840:0) [1024x1024] 3.162109 1.710938 1.617188 ..
|<- 1. 0x143904540 (0x285dff840:0) [1024x1024] 0.013161 0.003084 0.002808 ..
CCV_NNC_GEMM_FORWARD [1276]: [2] -> [1] (0)
|-> 1. 0x143904660 (0x285dff840:0) [1x1024x1024] 0.013161 0.003084 0.002808 ..
|-> 2. 0x1439045b0 (0x285da61c0:0) [1x1024x80] 0.213989 0.037750 -0.717285 ..
|<- 1. 0x143905320 (0x285da6900:0) [1x1024x80] -0.052582 0.033630 0.098328 ..
CCV_NNC_GEMM_FORWARD [1277]: [2] -> [1] (0)
|-> 1. 0x143904780 (0x285da6a80:0) [1x1024x80] 0.080933 0.015617 0.068115 ..
|-> 2. 0x1439046d0 (0x285da6a00:0) [1x1024x80] -1.032227 0.126343 -0.402100 ..
|<- 1. 0x1438b74c0 (0x285dff840:0) [1x1024x1024] 3.777344 2.722656 2.392578 ..
CCV_NNC_SOFTMAX_FORWARD [1278]: [1] -> [1] (0)
|-> 1. 0x143904830 (0x285dff840:0) [1024x1024] 3.777344 2.722656 2.392578 ..
|<- 1. 0x143904830 (0x285dff840:0) [1024x1024] 0.011330 0.003948 0.002838 ..
CCV_NNC_GEMM_FORWARD [1279]: [2] -> [1] (0)
|-> 1. 0x143904950 (0x285dff840:0) [1x1024x1024] 0.011330 0.003948 0.002838 ..
|-> 2. 0x1439048a0 (0x285da61c0:0) [1x1024x80] 0.742188 -0.063293 -0.087219 ..
|<- 1. 0x1439053d0 (0x285da6900:0) [1x1024x80] 0.560547 -0.281982 0.051788 ..
CCV_NNC_TRANSPOSE_FORWARD [1280]: [1] -> [1] (0)
|-> 1. 0x143905480 (0x285da6900:0) [2x8x1024x80] 0.000070 -0.303711 0.164429 ..
|<- 1. 0x1438b75a0 (0x285da61c0:0) [2x1024x8x80] 0.000070 -0.303711 0.164429 ..
CCV_NNC_GEMM_FORWARD [1281]: [3] -> [1] (0)
|-> 1. 0x1439054f0 (0x285da61c0:0) [2x1024x640] 0.000070 -0.303711 0.164429 ..
|-> 2. 0x1438cd020 (0x285d9bf80:0) [640x640] 0.026016 0.006371 0.137085 ..
|-> 3. 0x1438cd090 (0x285d9bfc0:0) [640] 0.003389 -0.013306 -0.018097 ..
|<- 1. 0x1438b7610 (0x285da6900:0) [2x1024x640] -0.080566 -0.426270 -0.087708 ..
CCV_NNC_ADD_FORWARD [1282]: [2] -> [1] (0)
|-> 1. 0x1438b7610 (0x285da6900:0) [2x1024x640] -0.080566 -0.426270 -0.087708 ..
|-> 2. 0x1439019c0 (0x285da6480:0) [2x1024x640] -0.023529 1.790039 -0.033813 ..
|<- 1. 0x1438b7610 (0x285da6900:0) [2x1024x640] -0.104126 1.363281 -0.121521 ..
CCV_NNC_LAYER_NORM_FORWARD [1283]: [3] -> [3] (0)
|-> 1. 0x1438b7610 (0x285da6900:0) [2x1024x640] -0.104126 1.363281 -0.121521 ..
|-> 2. 0x1438cd100 (0x285d9c000:0) [1x1x640] 0.572754 0.565430 0.583008 ..
|-> 3. 0x1438cd170 (0x285d9c040:0) [1x1x640] 0.126465 -0.019745 -0.088318 ..
|<- 1. 0x1438b7680 (0x285da6480:0) [2x1024x640] 0.075500 0.712891 -0.149780 ..
|<- 2. 0x1438b76f0 (0x285dfc780:0) [2x1024x1] -0.009888 ..
|<- 3. 0x1438b7760 (0x285de6c00:0) [2x1024x1] 0.943848 ..
CCV_NNC_GEMM_FORWARD [1284]: [2] -> [1] (0)
|-> 1. 0x1438b7680 (0x285da6480:0) [2x1024x640] 0.075500 0.712891 -0.149780 ..
|-> 2. 0x1438cd1e0 (0x285d9c080:0) [640x640] -0.145020 -0.061981 -0.010048 ..
|<- 1. 0x1438b77d0 (0x285da61c0:0) [2x1024x640] -1.089844 0.287109 -0.072510 ..
CCV_NNC_SCALAR_MUL_FORWARD [1285]: [1] -> [1] (0)
|-> 1. 0x1438b77d0 (0x285da61c0:0) [2x1024x640] -1.089844 0.287109 -0.072510 ..
|<- 1. 0x1438b77d0 (0x285da61c0:0) [2x1024x640] -0.121887 0.032104 -0.008110 ..
CCV_NNC_TRANSPOSE_FORWARD [1286]: [1] -> [1] (0)
|-> 1. 0x1439055d0 (0x285da61c0:0) [2x1024x8x80] -0.121887 0.032104 -0.008110 ..
|<- 1. 0x1438b7920 (0x285da6a00:0) [2x8x1024x80] -0.121887 0.032104 -0.008110 ..
CCV_NNC_GEMM_FORWARD [1287]: [2] -> [1] (0)
Wait: (0, 130)
|-> 1. 0x1438b7920 (0x285da6a00:0) [2x8x1024x80] -0.121887 0.032104 -0.008110 ..
|-> 2. 0x1438b78b0 (0x285de7a00:0) [2x8x133x80] -0.396484 -0.269043 -0.424072 ..
|<- 1. 0x1438b7990 (0x285da6bc0:0) [2x8x1024x133] 6.648438 -1.347656 -1.519531 ..
CCV_NNC_SOFTMAX_FORWARD [1288]: [1] -> [1] (0)
|-> 1. 0x143905640 (0x285da6bc0:0) [16384x133] 6.648438 -1.347656 -1.519531 ..
|<- 1. 0x143905640 (0x285da6bc0:0) [16384x133] 0.772949 0.000260 0.000219 ..
CCV_NNC_GEMM_FORWARD [1289]: [2] -> [1] (0)
Wait: (0, 131)
|-> 1. 0x143905720 (0x285da6bc0:0) [2x8x1024x133] 0.772949 0.000260 0.000219 ..
|-> 2. 0x1438b7a70 (0x285de0e80:0) [2x8x133x80] 0.022568 -0.025116 -0.027023 ..
|<- 1. 0x1438b7ae0 (0x285da6a00:0) [2x8x1024x80] -0.118896 0.157104 0.109497 ..
CCV_NNC_TRANSPOSE_FORWARD [1290]: [1] -> [1] (0)
|-> 1. 0x143905790 (0x285da6a00:0) [2x8x1024x80] -0.118896 0.157104 0.109497 ..
|<- 1. 0x1438b7b50 (0x285da6480:0) [2x1024x8x80] -0.118896 0.157104 0.109497 ..
CCV_NNC_GEMM_FORWARD [1291]: [3] -> [1] (0)
|-> 1. 0x143905800 (0x285da6480:0) [2x1024x640] -0.118896 0.157104 0.109497 ..
|-> 2. 0x1438cd330 (0x285d9c140:0) [640x640] 0.005894 -0.032928 0.001144 ..
|-> 3. 0x1438cd3a0 (0x285d9c180:0) [640] 0.014595 -0.021362 0.001012 ..
|<- 1. 0x1438b7bc0 (0x285dff880:0) [2x1024x640] 0.058136 -0.099854 -0.042206 ..
CCV_NNC_ADD_FORWARD [1292]: [2] -> [1] (0)
|-> 1. 0x1438b7bc0 (0x285dff880:0) [2x1024x640] 0.058136 -0.099854 -0.042206 ..
|-> 2. 0x1438b7610 (0x285da6900:0) [2x1024x640] -0.104126 1.363281 -0.121521 ..
|<- 1. 0x1438b7bc0 (0x285dff880:0) [2x1024x640] -0.045990 1.263672 -0.163696 ..
CCV_NNC_LAYER_NORM_FORWARD [1293]: [3] -> [3] (0)
|-> 1. 0x1438b7bc0 (0x285dff880:0) [2x1024x640] -0.045990 1.263672 -0.163696 ..
|-> 2. 0x1438cd410 (0x285d9c1c0:0) [1x1x640] 0.416748 0.404053 0.445801 ..
|-> 3. 0x1438cd480 (0x285d9c200:0) [1x1x640] 0.018936 0.015656 -0.009064 ..
|<- 1. 0x1438b7c30 (0x285da6400:0) [2x1024x640] 0.006565 0.499512 -0.071472 ..
|<- 2. 0x1438b7ca0 (0x285da6cc0:0) [2x1024x1] -0.014305 ..
|<- 3. 0x1438b7d10 (0x285da6d00:0) [2x1024x1] 0.937012 ..
Emit: (0, 132)
CCV_NNC_GEMM_FORWARD [1294]: [3] -> [1] (0)
|-> 1. 0x1438b7c30 (0x285da6400:0) [2x1024x640] 0.006565 0.499512 -0.071472 ..
|-> 2. 0x1438cd4f0 (0x285d9c240:0) [2560x640] -0.109924 -0.064636 -0.029663 ..
|-> 3. 0x1438cd560 (0x285d9c280:0) [2560] 0.117493 0.057129 -0.005646 ..
|<- 1. 0x1438b7d80 (0x285da6740:0) [2x1024x2560] 1.407227 0.571289 0.045685 ..
CCV_NNC_GELU_FORWARD [1295]: [1] -> [1] (0)
|-> 1. 0x1438b7d80 (0x285da6740:0) [2x1024x2560] 1.407227 0.571289 0.045685 ..
|<- 1. 0x1438b7d80 (0x285da6740:0) [2x1024x2560] 1.294922 0.409180 0.023682 ..
CCV_NNC_GEMM_FORWARD [1296]: [3] -> [1] (1)
Wait: (1, 132)
|-> 1. 0x1438b7c30 (0x285da6400:0) [2x1024x640] 0.006565 0.499512 -0.071472 ..
|-> 2. 0x1438cd5d0 (0x285d9c2c0:0) [2560x640] -0.040344 0.127808 0.014854 ..
|-> 3. 0x1438cd640 (0x285d9c300:0) [2560] -0.021179 0.004436 0.031342 ..
|<- 1. 0x1438b7df0 (0x285da6780:0) [2x1024x2560] 0.000820 0.217773 0.367432 ..
Emit: (1, 133)
CCV_NNC_MUL_FORWARD [1297]: [2] -> [1] (0)
Wait: (0, 133)
|-> 1. 0x1438b7df0 (0x285da6780:0) [2x1024x2560] 0.000820 0.217773 0.367432 ..
|-> 2. 0x1438b7d80 (0x285da6740:0) [2x1024x2560] 1.294922 0.409180 0.023682 ..
|<- 1. 0x1438b7df0 (0x285da6780:0) [2x1024x2560] 0.001061 0.089111 0.008705 ..
CCV_NNC_GEMM_FORWARD [1298]: [3] -> [1] (0)
|-> 1. 0x1438b7df0 (0x285da6780:0) [2x1024x2560] 0.001061 0.089111 0.008705 ..
|-> 2. 0x1438cd6b0 (0x285d9c340:0) [640x2560] 0.037018 0.042816 -0.029541 ..
|-> 3. 0x1438cd720 (0x285d9c380:0) [640] -0.000060 -0.003159 0.002666 ..
|<- 1. 0x1438b7e60 (0x285da6400:0) [2x1024x640] 0.938965 -1.089844 -0.162964 ..
CCV_NNC_ADD_FORWARD [1299]: [2] -> [1] (0)
|-> 1. 0x1438b7e60 (0x285da6400:0) [2x1024x640] 0.938965 -1.089844 -0.162964 ..
|-> 2. 0x1438b7bc0 (0x285dff880:0) [2x1024x640] -0.045990 1.263672 -0.163696 ..
|<- 1. 0x1438b7e60 (0x285da6400:0) [2x1024x640] 0.893066 0.173828 -0.326660 ..
CCV_NNC_CONVOLUTION_FORWARD [1300]: [3] -> [1] (0)
|-> 1. 0x143905870 (0x285da6400:0) [2x32x32x640] 0.893066 0.173828 -0.326660 ..
|-> 2. 0x1438cd790 (0x285d9c3c0:0) [640x640x1x1] 0.051941 ..
|-> 3. 0x1438cd800 (0x285d9c400:0) [640] -0.033844 -0.001174 -0.017700 ..
|<- 1. 0x1438b7ed0 (0x285dff880:0) [2x32x32x640] -0.842773 0.578125 3.449219 ..
CCV_NNC_ADD_FORWARD [1301]: [2] -> [1] (0)
|-> 1. 0x1438b7ed0 (0x285dff880:0) [2x32x32x640] -0.842773 0.578125 3.449219 ..
|-> 2. 0x1438b6810 (0x285da62c0:0) [2x32x32x640] 2.068359 -1.302734 -2.984375 ..
|<- 1. 0x1438b7ed0 (0x285dff880:0) [2x32x32x640] 1.225586 -0.724609 0.464844 ..
CCV_NNC_UPSAMPLE_FORWARD [1302]: [1] -> [1] (0)
|-> 1. 0x1438b7ed0 (0x285dff880:0) [2x32x32x640] 1.225586 -0.724609 0.464844 ..
|<- 1. 0x1438b7f40 (0x285da6780:0) [2x64x64x640] 1.225586 -0.724609 0.464844 ..
CCV_NNC_CONVOLUTION_FORWARD [1303]: [3] -> [1] (0)
|-> 1. 0x1438b7f40 (0x285da6780:0) [2x64x64x640] 1.225586 -0.724609 0.464844 ..
|-> 2. 0x1438cd870 (0x285d9c440:0) [640x640x3x3] 0.000939 -0.010376 -0.013756 ..
|-> 3. 0x1438cd8e0 (0x285d9c480:0) [640] 0.023178 0.061584 -0.032867 ..
|<- 1. 0x1439058e0 (0x285de0a40:0) [2x64x64x640] -3.783203 0.395020 1.876953 ..
Emit: (0, 135)
CCV_NNC_GROUP_NORM_FORWARD [1304]: [3] -> [3] (0)
|-> 1. 0x1438b7fb0 (0x285de0a40:0) [2x64x64x960] -3.783203 0.395020 1.876953 ..
|-> 2. 0x1438cd950 (0x285d9c4c0:0) [1x1x1x960] 0.545410 0.655762 0.421143 ..
|-> 3. 0x1438cd9c0 (0x285d9c500:0) [1x1x1x960] -0.252197 -0.313232 -0.081360 ..
|<- 1. 0x1438b8020 (0x285de18c0:0) [2x64x64x960] -1.106445 -0.170288 0.276855 ..
|<- 2. 0x1438b8090 (0x285da6100:0) [2x1x1x32] -0.115417 -0.030258 -0.100891 ..
|<- 3. 0x1438b8100 (0x285da6140:0) [2x1x1x32] 0.427002 0.455566 0.478027 ..
CCV_NNC_SWISH_FORWARD [1305]: [1] -> [1] (0)
|-> 1. 0x1438b8020 (0x285de18c0:0) [2x64x64x960] -1.106445 -0.170288 0.276855 ..
|<- 1. 0x1438b8020 (0x285de18c0:0) [2x64x64x960] -0.274902 -0.077942 0.157471 ..
CCV_NNC_CONVOLUTION_FORWARD [1306]: [3] -> [1] (0)
|-> 1. 0x1438b8020 (0x285de18c0:0) [2x64x64x960] -0.274902 -0.077942 0.157471 ..
|-> 2. 0x1438cdb10 (0x285d9c5c0:0) [320x960x3x3] 0.052460 -0.043915 0.051819 ..
|-> 3. 0x1438cdb80 (0x285d9c600:0) [320] -0.001501 0.076172 0.074036 ..
|<- 1. 0x1438b81e0 (0x285da5ac0:0) [2x64x64x320] -0.063782 0.292725 2.595703 ..
CCV_NNC_ADD_FORWARD [1307]: [2] -> [1] (0)
Wait: (0, 134)
|-> 1. 0x1438b81e0 (0x285da5ac0:0) [2x64x64x320] -0.063782 0.292725 2.595703 ..
|-> 2. 0x143905a40 (0x285def880:0) [2x1x1x320] 0.466797 0.149780 1.849609 ..
|<- 1. 0x1438b81e0 (0x285da5ac0:0) [2x64x64x320] 0.403076 0.442383 4.445312 ..
CCV_NNC_GROUP_NORM_FORWARD [1308]: [3] -> [3] (0)
|-> 1. 0x1438b81e0 (0x285da5ac0:0) [2x64x64x320] 0.403076 0.442383 4.445312 ..
|-> 2. 0x1438cdbf0 (0x285d9c640:0) [1x1x1x320] 0.740234 0.875488 0.598145 ..
|-> 3. 0x1438cdc60 (0x285d9c680:0) [1x1x1x320] -0.322021 0.020996 -0.186768 ..
|<- 1. 0x1438b8250 (0x285da56c0:0) [2x64x64x320] -0.206055 0.178955 1.375977 ..
|<- 2. 0x1438b82c0 (0x285ded980:0) [2x1x1x32] 0.145264 0.136963 0.254883 ..
|<- 3. 0x1438b8330 (0x285dd6500:0) [2x1x1x32] 0.607422 0.662109 0.757324 ..
CCV_NNC_SWISH_FORWARD [1309]: [1] -> [1] (0)
|-> 1. 0x1438b8250 (0x285da56c0:0) [2x64x64x320] -0.206055 0.178955 1.375977 ..
|<- 1. 0x1438b8250 (0x285da56c0:0) [2x64x64x320] -0.092468 0.097473 1.098633 ..
CCV_NNC_CONVOLUTION_FORWARD [1310]: [3] -> [1] (0)
|-> 1. 0x1438b8250 (0x285da56c0:0) [2x64x64x320] -0.092468 0.097473 1.098633 ..
|-> 2. 0x1438cdcd0 (0x285d9c6c0:0) [320x320x3x3] -0.012505 0.016617 -0.002302 ..
|-> 3. 0x1438cdd40 (0x285d9c700:0) [320] -0.009682 0.050598 0.019455 ..
|<- 1. 0x1438b83a0 (0x285da5680:0) [2x64x64x320] -0.659180 -1.076172 1.289062 ..
CCV_NNC_CONVOLUTION_FORWARD [1311]: [3] -> [1] (1)
Wait: (1, 135)
|-> 1. 0x1438b7fb0 (0x285de0a40:0) [2x64x64x960] -3.783203 0.395020 1.876953 ..
|-> 2. 0x1438cddb0 (0x285d9c740:0) [320x960x1x1] 0.042511 ..
|-> 3. 0x1438cde20 (0x285d9c780:0) [320] -0.017502 0.055573 0.025421 ..
|<- 1. 0x1438b8410 (0x285da5840:0) [2x64x64x320] 0.621582 -0.874512 2.087891 ..
Emit: (1, 136)
CCV_NNC_ADD_FORWARD [1312]: [2] -> [1] (0)
Wait: (0, 136)
|-> 1. 0x1438b8410 (0x285da5840:0) [2x64x64x320] 0.621582 -0.874512 2.087891 ..
|-> 2. 0x1438b83a0 (0x285da5680:0) [2x64x64x320] -0.659180 -1.076172 1.289062 ..
|<- 1. 0x1438b8410 (0x285da5840:0) [2x64x64x320] -0.037598 -1.951172 3.376953 ..
CCV_NNC_GROUP_NORM_FORWARD [1313]: [3] -> [3] (0)
|-> 1. 0x1438b8410 (0x285da5840:0) [2x64x64x320] -0.037598 -1.951172 3.376953 ..
|-> 2. 0x1438cde90 (0x285d9c7c0:0) [1x1x1x320] 0.430664 0.520020 0.451904 ..
|-> 3. 0x1438cdf00 (0x285d9c800:0) [1x1x1x320] -0.103699 0.002209 -0.110107 ..
|<- 1. 0x1438b8480 (0x285da5680:0) [2x64x64x320] 0.104492 -0.439697 1.183594 ..
|<- 2. 0x1438b84f0 (0x285da5700:0) [2x1x1x32] -0.731445 -0.323486 -0.154175 ..
|<- 3. 0x1438b8560 (0x285da5740:0) [2x1x1x32] 0.696777 0.739258 0.566406 ..
CCV_NNC_CONVOLUTION_FORWARD [1314]: [3] -> [1] (0)
|-> 1. 0x1438b8480 (0x285da5680:0) [2x64x64x320] 0.104492 -0.439697 1.183594 ..
|-> 2. 0x1438cdf70 (0x285d9c840:0) [320x320x1x1] -0.012505 ..
|-> 3. 0x1438cdfe0 (0x285d9c880:0) [320] 0.014336 0.037598 0.015839 ..
|<- 1. 0x1438b85d0 (0x285da56c0:0) [2x64x64x320] 0.083008 -0.380371 -0.271973 ..
CCV_NNC_LAYER_NORM_FORWARD [1315]: [3] -> [3] (0)
|-> 1. 0x143905ab0 (0x285da56c0:0) [2x4096x320] 0.083008 -0.380371 -0.271973 ..
|-> 2. 0x1438ce050 (0x285d9c8c0:0) [1x1x320] 1.156250 0.857422 0.963867 ..
|-> 3. 0x1438ce0c0 (0x285d9c900:0) [1x1x320] 0.141479 0.109985 -0.043854 ..
|<- 1. 0x1438b8640 (0x285da5680:0) [2x4096x320] 0.260498 -0.440918 -0.495117 ..
|<- 2. 0x1438b86b0 (0x285dd7f00:0) [2x4096x1] 0.019073 ..
|<- 3. 0x1438b8720 (0x285dd6d00:0) [2x4096x1] 1.608398 ..
Emit: (0, 137)
CCV_NNC_GEMM_FORWARD [1316]: [2] -> [1] (0)
|-> 1. 0x1438b8640 (0x285da5680:0) [2x4096x320] 0.260498 -0.440918 -0.495117 ..
|-> 2. 0x1438ce130 (0x285d9c940:0) [320x320] -0.113586 0.118835 0.039001 ..
|<- 1. 0x1438b8790 (0x285da5ac0:0) [2x4096x320] -0.004326 -0.940918 -0.039307 ..
CCV_NNC_SCALAR_MUL_FORWARD [1317]: [1] -> [1] (0)
|-> 1. 0x1438b8790 (0x285da5ac0:0) [2x4096x320] -0.004326 -0.940918 -0.039307 ..
|<- 1. 0x1438b8790 (0x285da5ac0:0) [2x4096x320] -0.000684 -0.148682 -0.006214 ..
CCV_NNC_TRANSPOSE_FORWARD [1318]: [1] -> [1] (0)
|-> 1. 0x143905b90 (0x285da5ac0:0) [2x4096x8x40] -0.000684 -0.148682 -0.006214 ..
|<- 1. 0x1438b88e0 (0x285da5980:0) [2x8x4096x40] -0.000684 -0.148682 -0.006214 ..
CCV_NNC_GEMM_FORWARD [1319]: [2] -> [1] (1)
Wait: (1, 137)
|-> 1. 0x1438b8640 (0x285da5680:0) [2x4096x320] 0.260498 -0.440918 -0.495117 ..
|-> 2. 0x1438ce1a0 (0x285d9c980:0) [320x320] -0.006836 0.111511 0.062927 ..
|<- 1. 0x1438b8800 (0x285da5940:0) [2x4096x320] 0.905762 -1.722656 1.172852 ..
CCV_NNC_TRANSPOSE_FORWARD [1320]: [1] -> [1] (1)
|-> 1. 0x143905b20 (0x285da5940:0) [2x4096x8x40] 0.905762 -1.722656 1.172852 ..
|<- 1. 0x1438b8870 (0x285da5e80:0) [2x8x4096x40] 0.905762 -1.722656 1.172852 ..
Emit: (1, 138)
CCV_NNC_GEMM_FORWARD [1321]: [2] -> [1] (2)
Wait: (2, 137)
|-> 1. 0x1438b8640 (0x285da5680:0) [2x4096x320] 0.260498 -0.440918 -0.495117 ..
|-> 2. 0x1438ce210 (0x285d9c9c0:0) [320x320] 0.026413 -0.134888 0.119385 ..
|<- 1. 0x1438b8950 (0x285da5ec0:0) [2x4096x320] 0.089783 -0.391602 -0.388428 ..
CCV_NNC_TRANSPOSE_FORWARD [1322]: [1] -> [1] (2)
|-> 1. 0x143905ce0 (0x285da5ec0:0) [2x4096x8x40] 0.089783 -0.391602 -0.388428 ..
|<- 1. 0x1438b8a30 (0x285da59c0:0) [2x8x4096x40] 0.089783 -0.391602 -0.388428 ..
Emit: (2, 139)
CCV_NNC_GEMM_FORWARD [1323]: [2] -> [1] (0)
Wait: (0, 138)
|-> 1. 0x143905c70 (0x285da5980:0) [1x4096x40] -0.000684 -0.148682 -0.006214 ..
|-> 2. 0x143905c00 (0x285da5e80:0) [1x4096x40] 0.905762 -1.722656 1.172852 ..
|<- 1. 0x1438b89c0 (0x285da5a40:0) [1x4096x4096] 19.953125 18.968750 18.093750 ..
CCV_NNC_SOFTMAX_FORWARD [1324]: [1] -> [1] (0)
|-> 1. 0x143905d50 (0x285da5a40:0) [4096x4096] 19.953125 18.968750 18.093750 ..
|<- 1. 0x143905d50 (0x285da5a40:0) [4096x4096] 0.032288 0.012070 0.005032 ..
CCV_NNC_GEMM_FORWARD [1325]: [2] -> [1] (0)
Wait: (0, 139)
|-> 1. 0x143905e30 (0x285da5a40:0) [1x4096x4096] 0.032288 0.012070 0.005032 ..
|-> 2. 0x143905dc0 (0x285da59c0:0) [1x4096x40] 0.089783 -0.391602 -0.388428 ..
|<- 1. 0x143908ab0 (0x285da5680:0) [1x4096x40] 0.165527 -0.240356 -0.292480 ..
CCV_NNC_GEMM_FORWARD [1326]: [2] -> [1] (0)
|-> 1. 0x143905f50 (0x285da5980:0) [1x4096x40] 0.174561 -0.205322 0.276611 ..
|-> 2. 0x143905ea0 (0x285da5e80:0) [1x4096x40] 0.327148 -3.205078 3.839844 ..
|<- 1. 0x1438b8aa0 (0x285da5a40:0) [1x4096x4096] 16.875000 16.000000 15.406250 ..
CCV_NNC_SOFTMAX_FORWARD [1327]: [1] -> [1] (0)
|-> 1. 0x143906000 (0x285da5a40:0) [4096x4096] 16.875000 16.000000 15.406250 ..
|<- 1. 0x143906000 (0x285da5a40:0) [4096x4096] 0.016571 0.006905 0.003813 ..
CCV_NNC_GEMM_FORWARD [1328]: [2] -> [1] (0)
|-> 1. 0x143906120 (0x285da5a40:0) [1x4096x4096] 0.016571 0.006905 0.003813 ..
|-> 2. 0x143906070 (0x285da59c0:0) [1x4096x40] -0.635254 -0.266602 -0.316406 ..
|<- 1. 0x143908b20 (0x285da5680:0) [1x4096x40] -0.333496 -0.261719 0.043762 ..
CCV_NNC_GEMM_FORWARD [1329]: [2] -> [1] (0)
|-> 1. 0x143906240 (0x285da5980:0) [1x4096x40] 0.073303 -0.222412 0.144043 ..
|-> 2. 0x143906190 (0x285da5e80:0) [1x4096x40] -1.830078 -1.434570 1.470703 ..
|<- 1. 0x1438b8b10 (0x285da5a40:0) [1x4096x4096] 11.554688 10.343750 9.640625 ..
CCV_NNC_SOFTMAX_FORWARD [1330]: [1] -> [1] (0)
|-> 1. 0x1439062f0 (0x285da5a40:0) [4096x4096] 11.554688 10.343750 9.640625 ..
|<- 1. 0x1439062f0 (0x285da5a40:0) [4096x4096] 0.021713 0.006470 0.003202 ..
CCV_NNC_GEMM_FORWARD [1331]: [2] -> [1] (0)
|-> 1. 0x143906410 (0x285da5a40:0) [1x4096x4096] 0.021713 0.006470 0.003202 ..
|-> 2. 0x143906360 (0x285da59c0:0) [1x4096x40] 0.383301 0.287598 -1.141602 ..
|<- 1. 0x143908bd0 (0x285da5680:0) [1x4096x40] 0.461182 0.411133 -0.490479 ..
CCV_NNC_GEMM_FORWARD [1332]: [2] -> [1] (0)
|-> 1. 0x143906530 (0x285da5980:0) [1x4096x40] -0.062469 0.169922 0.109985 ..
|-> 2. 0x143906480 (0x285da5e80:0) [1x4096x40] -0.499756 1.308594 1.675781 ..
|<- 1. 0x1438b8b80 (0x285da5a40:0) [1x4096x4096] 17.312500 16.250000 15.640625 ..
CCV_NNC_SOFTMAX_FORWARD [1333]: [1] -> [1] (0)
|-> 1. 0x1439065e0 (0x285da5a40:0) [4096x4096] 17.312500 16.250000 15.640625 ..
|<- 1. 0x1439065e0 (0x285da5a40:0) [4096x4096] 0.040741 0.014076 0.007656 ..
CCV_NNC_GEMM_FORWARD [1334]: [2] -> [1] (0)
|-> 1. 0x143906700 (0x285da5a40:0) [1x4096x4096] 0.040741 0.014076 0.007656 ..
|-> 2. 0x143906650 (0x285da59c0:0) [1x4096x40] 0.402832 -0.486328 0.188354 ..
|<- 1. 0x143908c80 (0x285da5680:0) [1x4096x40] -0.025589 -0.186890 0.389404 ..
CCV_NNC_GEMM_FORWARD [1335]: [2] -> [1] (0)
|-> 1. 0x143906820 (0x285da5980:0) [1x4096x40] 0.268311 0.226318 0.001414 ..
|-> 2. 0x143906770 (0x285da5e80:0) [1x4096x40] 1.641602 2.652344 -0.117310 ..
|<- 1. 0x1438b8bf0 (0x285da5a40:0) [1x4096x4096] 16.171875 14.882812 14.484375 ..
CCV_NNC_SOFTMAX_FORWARD [1336]: [1] -> [1] (0)
|-> 1. 0x1439068d0 (0x285da5a40:0) [4096x4096] 16.171875 14.882812 14.484375 ..
|<- 1. 0x1439068d0 (0x285da5a40:0) [4096x4096] 0.028397 0.007828 0.005253 ..
CCV_NNC_GEMM_FORWARD [1337]: [2] -> [1] (0)
|-> 1. 0x1439069f0 (0x285da5a40:0) [1x4096x4096] 0.028397 0.007828 0.005253 ..
|-> 2. 0x143906940 (0x285da59c0:0) [1x4096x40] 0.212158 0.656738 0.294922 ..
|<- 1. 0x143908d30 (0x285da5680:0) [1x4096x40] 0.109802 0.434570 0.120728 ..
CCV_NNC_GEMM_FORWARD [1338]: [2] -> [1] (0)
|-> 1. 0x143906b10 (0x285da5980:0) [1x4096x40] 0.164307 -0.314209 0.086914 ..
|-> 2. 0x143906a60 (0x285da5e80:0) [1x4096x40] 3.753906 -3.740234 1.285156 ..
|<- 1. 0x1438b8c60 (0x285da5a40:0) [1x4096x4096] 14.921875 14.640625 13.804688 ..
CCV_NNC_SOFTMAX_FORWARD [1339]: [1] -> [1] (0)
|-> 1. 0x143906bc0 (0x285da5a40:0) [4096x4096] 14.921875 14.640625 13.804688 ..
|<- 1. 0x143906bc0 (0x285da5a40:0) [4096x4096] 0.022324 0.016846 0.007305 ..
CCV_NNC_GEMM_FORWARD [1340]: [2] -> [1] (0)
|-> 1. 0x143906ce0 (0x285da5a40:0) [1x4096x4096] 0.022324 0.016846 0.007305 ..
|-> 2. 0x143906c30 (0x285da59c0:0) [1x4096x40] 0.119873 -0.119568 0.225220 ..
|<- 1. 0x143908de0 (0x285da5680:0) [1x4096x40] 0.030884 -0.236694 -0.027252 ..
CCV_NNC_GEMM_FORWARD [1341]: [2] -> [1] (0)
|-> 1. 0x143906e00 (0x285da5980:0) [1x4096x40] 0.178955 -0.022171 0.248047 ..
|-> 2. 0x143906d50 (0x285da5e80:0) [1x4096x40] 1.395508 -0.348633 2.218750 ..
|<- 1. 0x1438b8cd0 (0x285da5a40:0) [1x4096x4096] 17.515625 14.500000 13.531250 ..
CCV_NNC_SOFTMAX_FORWARD [1342]: [1] -> [1] (0)
|-> 1. 0x143906eb0 (0x285da5a40:0) [4096x4096] 17.515625 14.500000 13.531250 ..
|<- 1. 0x143906eb0 (0x285da5a40:0) [4096x4096] 0.052612 0.002579 0.000979 ..
CCV_NNC_GEMM_FORWARD [1343]: [2] -> [1] (0)
|-> 1. 0x143906fd0 (0x285da5a40:0) [1x4096x4096] 0.052612 0.002579 0.000979 ..
|-> 2. 0x143906f20 (0x285da59c0:0) [1x4096x40] 0.891113 0.083496 -1.502930 ..
|<- 1. 0x143908e90 (0x285da5680:0) [1x4096x40] 0.770996 -0.200562 -1.390625 ..
CCV_NNC_GEMM_FORWARD [1344]: [2] -> [1] (0)
|-> 1. 0x1439070f0 (0x285da5980:0) [1x4096x40] -0.335205 0.422607 -0.288574 ..
|-> 2. 0x143907040 (0x285da5e80:0) [1x4096x40] -3.613281 4.593750 -2.001953 ..
|<- 1. 0x1438b8d40 (0x285da5a40:0) [1x4096x4096] 17.578125 17.000000 16.859375 ..
CCV_NNC_SOFTMAX_FORWARD [1345]: [1] -> [1] (0)
|-> 1. 0x1439071a0 (0x285da5a40:0) [4096x4096] 17.578125 17.000000 16.859375 ..
|<- 1. 0x1439071a0 (0x285da5a40:0) [4096x4096] 0.008347 0.004684 0.004070 ..
CCV_NNC_GEMM_FORWARD [1346]: [2] -> [1] (0)
|-> 1. 0x1439072c0 (0x285da5a40:0) [1x4096x4096] 0.008347 0.004684 0.004070 ..
|-> 2. 0x143907210 (0x285da59c0:0) [1x4096x40] -0.195068 0.134644 0.213501 ..
|<- 1. 0x143908f40 (0x285da5680:0) [1x4096x40] 0.218628 -0.019180 0.120667 ..
CCV_NNC_GEMM_FORWARD [1347]: [2] -> [1] (0)
|-> 1. 0x1439073e0 (0x285da5980:0) [1x4096x40] 0.082458 -0.206543 -0.010803 ..
|-> 2. 0x143907330 (0x285da5e80:0) [1x4096x40] 0.743652 -1.208984 1.195312 ..
|<- 1. 0x1438b8db0 (0x285da5a40:0) [1x4096x4096] 18.671875 18.359375 17.468750 ..
CCV_NNC_SOFTMAX_FORWARD [1348]: [1] -> [1] (0)
|-> 1. 0x143907490 (0x285da5a40:0) [4096x4096] 18.671875 18.359375 17.468750 ..
|<- 1. 0x143907490 (0x285da5a40:0) [4096x4096] 0.028854 0.021118 0.008667 ..
CCV_NNC_GEMM_FORWARD [1349]: [2] -> [1] (0)
|-> 1. 0x1439075b0 (0x285da5a40:0) [1x4096x4096] 0.028854 0.021118 0.008667 ..
|-> 2. 0x143907500 (0x285da59c0:0) [1x4096x40] 0.318848 -0.522949 -0.343506 ..
|<- 1. 0x143908ff0 (0x285da5680:0) [1x4096x40] 0.225830 -0.331299 -0.181030 ..
CCV_NNC_GEMM_FORWARD [1350]: [2] -> [1] (0)
|-> 1. 0x1439076d0 (0x285da5980:0) [1x4096x40] 0.147949 -0.276611 0.256592 ..
|-> 2. 0x143907620 (0x285da5e80:0) [1x4096x40] -0.259521 -4.003906 3.429688 ..
|<- 1. 0x1438b8e20 (0x285da5a40:0) [1x4096x4096] 16.093750 15.843750 15.273438 ..
CCV_NNC_SOFTMAX_FORWARD [1351]: [1] -> [1] (0)
|-> 1. 0x143907780 (0x285da5a40:0) [4096x4096] 16.093750 15.843750 15.273438 ..
|<- 1. 0x143907780 (0x285da5a40:0) [4096x4096] 0.012375 0.009636 0.005447 ..
CCV_NNC_GEMM_FORWARD [1352]: [2] -> [1] (0)
|-> 1. 0x1439078a0 (0x285da5a40:0) [1x4096x4096] 0.012375 0.009636 0.005447 ..
|-> 2. 0x1439077f0 (0x285da59c0:0) [1x4096x40] -0.512695 -0.149292 -0.083313 ..
|<- 1. 0x1439090a0 (0x285da5680:0) [1x4096x40] -0.452637 -0.240234 0.088196 ..
CCV_NNC_GEMM_FORWARD [1353]: [2] -> [1] (0)
|-> 1. 0x1439079c0 (0x285da5980:0) [1x4096x40] 0.107422 -0.286133 0.125854 ..
|-> 2. 0x143907910 (0x285da5e80:0) [1x4096x40] -1.751953 -1.720703 1.762695 ..
|<- 1. 0x1438b8e90 (0x285da5a40:0) [1x4096x4096] 11.031250 10.484375 9.882812 ..
CCV_NNC_SOFTMAX_FORWARD [1354]: [1] -> [1] (0)
|-> 1. 0x143907a70 (0x285da5a40:0) [4096x4096] 11.031250 10.484375 9.882812 ..
|<- 1. 0x143907a70 (0x285da5a40:0) [4096x4096] 0.012192 0.007053 0.003866 ..
CCV_NNC_GEMM_FORWARD [1355]: [2] -> [1] (0)
|-> 1. 0x143907b90 (0x285da5a40:0) [1x4096x4096] 0.012192 0.007053 0.003866 ..
|-> 2. 0x143907ae0 (0x285da59c0:0) [1x4096x40] 0.530762 0.905273 -0.472656 ..
|<- 1. 0x143909150 (0x285da5680:0) [1x4096x40] 0.502930 0.651367 -0.339111 ..
CCV_NNC_GEMM_FORWARD [1356]: [2] -> [1] (0)
|-> 1. 0x143907cb0 (0x285da5980:0) [1x4096x40] 0.020615 0.116943 0.180664 ..
|-> 2. 0x143907c00 (0x285da5e80:0) [1x4096x40] 0.034332 0.680664 2.195312 ..
|<- 1. 0x1438b8f00 (0x285da5a40:0) [1x4096x4096] 16.562500 16.093750 15.710938 ..
CCV_NNC_SOFTMAX_FORWARD [1357]: [1] -> [1] (0)
|-> 1. 0x143907d60 (0x285da5a40:0) [4096x4096] 16.562500 16.093750 15.710938 ..
|<- 1. 0x143907d60 (0x285da5a40:0) [4096x4096] 0.023911 0.014961 0.010201 ..
CCV_NNC_GEMM_FORWARD [1358]: [2] -> [1] (0)
|-> 1. 0x143907e80 (0x285da5a40:0) [1x4096x4096] 0.023911 0.014961 0.010201 ..
|-> 2. 0x143907dd0 (0x285da59c0:0) [1x4096x40] 0.365967 -0.692871 0.613770 ..
|<- 1. 0x143909200 (0x285da5680:0) [1x4096x40] -0.136719 -0.275635 0.575684 ..
CCV_NNC_GEMM_FORWARD [1359]: [2] -> [1] (0)
|-> 1. 0x143907fa0 (0x285da5980:0) [1x4096x40] 0.225708 0.262695 -0.012726 ..
|-> 2. 0x143907ef0 (0x285da5e80:0) [1x4096x40] 1.378906 2.330078 -0.319336 ..
|<- 1. 0x1438b8f70 (0x285da5a40:0) [1x4096x4096] 15.375000 14.468750 14.609375 ..
CCV_NNC_SOFTMAX_FORWARD [1360]: [1] -> [1] (0)
|-> 1. 0x143908050 (0x285da5a40:0) [4096x4096] 15.375000 14.468750 14.609375 ..
|<- 1. 0x143908050 (0x285da5a40:0) [4096x4096] 0.017853 0.007214 0.008301 ..
CCV_NNC_GEMM_FORWARD [1361]: [2] -> [1] (0)
|-> 1. 0x143908170 (0x285da5a40:0) [1x4096x4096] 0.017853 0.007214 0.008301 ..
|-> 2. 0x1439080c0 (0x285da59c0:0) [1x4096x40] -0.076904 0.568359 0.285156 ..
|<- 1. 0x1439092b0 (0x285da5680:0) [1x4096x40] 0.083252 0.612305 0.185913 ..
CCV_NNC_GEMM_FORWARD [1362]: [2] -> [1] (0)
|-> 1. 0x143908290 (0x285da5980:0) [1x4096x40] 0.194458 -0.200562 0.066528 ..
|-> 2. 0x1439081e0 (0x285da5e80:0) [1x4096x40] 4.214844 -3.341797 1.146484 ..
|<- 1. 0x1438b8fe0 (0x285da5a40:0) [1x4096x4096] 14.242188 14.078125 13.296875 ..
CCV_NNC_SOFTMAX_FORWARD [1363]: [1] -> [1] (0)
|-> 1. 0x143908340 (0x285da5a40:0) [4096x4096] 14.242188 14.078125 13.296875 ..
|<- 1. 0x143908340 (0x285da5a40:0) [4096x4096] 0.015884 0.013489 0.006176 ..
CCV_NNC_GEMM_FORWARD [1364]: [2] -> [1] (0)
|-> 1. 0x143908460 (0x285da5a40:0) [1x4096x4096] 0.015884 0.013489 0.006176 ..
|-> 2. 0x1439083b0 (0x285da59c0:0) [1x4096x40] -0.081360 -0.488281 0.327393 ..
|<- 1. 0x143909360 (0x285da5680:0) [1x4096x40] 0.026047 -0.492432 0.160767 ..
CCV_NNC_GEMM_FORWARD [1365]: [2] -> [1] (0)
|-> 1. 0x143908580 (0x285da5980:0) [1x4096x40] 0.150269 0.068481 0.220581 ..
|-> 2. 0x1439084d0 (0x285da5e80:0) [1x4096x40] 1.664062 0.164551 1.584961 ..
|<- 1. 0x1438b9050 (0x285da5a40:0) [1x4096x4096] 17.500000 15.343750 14.601562 ..
CCV_NNC_SOFTMAX_FORWARD [1366]: [1] -> [1] (0)
|-> 1. 0x143908630 (0x285da5a40:0) [4096x4096] 17.500000 15.343750 14.601562 ..
|<- 1. 0x143908630 (0x285da5a40:0) [4096x4096] 0.052032 0.006023 0.002867 ..
CCV_NNC_GEMM_FORWARD [1367]: [2] -> [1] (0)
|-> 1. 0x143908750 (0x285da5a40:0) [1x4096x4096] 0.052032 0.006023 0.002867 ..
|-> 2. 0x1439086a0 (0x285da59c0:0) [1x4096x40] 0.544922 0.324219 -1.807617 ..
|<- 1. 0x143909410 (0x285da5680:0) [1x4096x40] 0.296631 0.026154 -1.659180 ..
CCV_NNC_GEMM_FORWARD [1368]: [2] -> [1] (0)
|-> 1. 0x143908870 (0x285da5980:0) [1x4096x40] -0.333740 0.471436 -0.136841 ..
|-> 2. 0x1439087c0 (0x285da5e80:0) [1x4096x40] -3.929688 3.814453 -3.291016 ..
|<- 1. 0x1438b90c0 (0x285da5a40:0) [1x4096x4096] 17.078125 16.312500 15.968750 ..
CCV_NNC_SOFTMAX_FORWARD [1369]: [1] -> [1] (0)
|-> 1. 0x143908920 (0x285da5a40:0) [4096x4096] 17.078125 16.312500 15.968750 ..
|<- 1. 0x143908920 (0x285da5a40:0) [4096x4096] 0.012802 0.005955 0.004223 ..
CCV_NNC_GEMM_FORWARD [1370]: [2] -> [1] (0)
|-> 1. 0x143908a40 (0x285da5a40:0) [1x4096x4096] 0.012802 0.005955 0.004223 ..
|-> 2. 0x143908990 (0x285da59c0:0) [1x4096x40] 0.003660 0.219727 -0.337158 ..
|<- 1. 0x1439094c0 (0x285da5680:0) [1x4096x40] 0.185303 -0.075867 -0.177490 ..
CCV_NNC_TRANSPOSE_FORWARD [1371]: [1] -> [1] (0)
|-> 1. 0x143909570 (0x285da5680:0) [2x8x4096x40] 0.165527 -0.240356 -0.292480 ..
|<- 1. 0x1438b91a0 (0x285da5940:0) [2x4096x8x40] 0.165527 -0.240356 -0.292480 ..
CCV_NNC_GEMM_FORWARD [1372]: [3] -> [1] (0)
|-> 1. 0x1439095e0 (0x285da5940:0) [2x4096x320] 0.165527 -0.240356 -0.292480 ..
|-> 2. 0x1438ce280 (0x285d9ca00:0) [320x320] 0.033112 -0.019180 0.030136 ..
|-> 3. 0x1438ce2f0 (0x285d9ca40:0) [320] 0.000849 0.056000 -0.002743 ..
|<- 1. 0x1438b9210 (0x285da5ac0:0) [2x4096x320] 0.304688 0.017227 0.258789 ..
CCV_NNC_ADD_FORWARD [1373]: [2] -> [1] (0)
|-> 1. 0x1438b9210 (0x285da5ac0:0) [2x4096x320] 0.304688 0.017227 0.258789 ..
|-> 2. 0x143905ab0 (0x285da56c0:0) [2x4096x320] 0.083008 -0.380371 -0.271973 ..
|<- 1. 0x1438b9210 (0x285da5ac0:0) [2x4096x320] 0.387695 -0.363037 -0.013184 ..
CCV_NNC_LAYER_NORM_FORWARD [1374]: [3] -> [3] (0)
|-> 1. 0x1438b9210 (0x285da5ac0:0) [2x4096x320] 0.387695 -0.363037 -0.013184 ..
|-> 2. 0x1438ce360 (0x285d9ca80:0) [1x1x320] 0.353027 0.337158 0.348389 ..
|-> 3. 0x1438ce3d0 (0x285d9cac0:0) [1x1x320] -0.069946 -0.029770 -0.196045 ..
|<- 1. 0x1438b9280 (0x285da5940:0) [2x4096x320] 0.134888 -0.320068 -0.261963 ..
|<- 2. 0x1438b92f0 (0x285da5b40:0) [2x4096x1] 0.085510 ..
|<- 3. 0x1438b9360 (0x285da5b00:0) [2x4096x1] 1.919922 ..
CCV_NNC_GEMM_FORWARD [1375]: [2] -> [1] (0)
|-> 1. 0x1438b9280 (0x285da5940:0) [2x4096x320] 0.134888 -0.320068 -0.261963 ..
|-> 2. 0x1438ce440 (0x285d9cb00:0) [320x320] 0.097656 -0.086975 -0.080811 ..
|<- 1. 0x1438b93d0 (0x285da5900:0) [2x4096x320] 0.525391 -0.557129 -0.198853 ..
CCV_NNC_SCALAR_MUL_FORWARD [1376]: [1] -> [1] (0)
|-> 1. 0x1438b93d0 (0x285da5900:0) [2x4096x320] 0.525391 -0.557129 -0.198853 ..
|<- 1. 0x1438b93d0 (0x285da5900:0) [2x4096x320] 0.083069 -0.088074 -0.031433 ..
CCV_NNC_TRANSPOSE_FORWARD [1377]: [1] -> [1] (0)
|-> 1. 0x1439096c0 (0x285da5900:0) [2x4096x8x40] 0.083069 -0.088074 -0.031433 ..
|<- 1. 0x1438b9520 (0x285da56c0:0) [2x8x4096x40] 0.083069 -0.088074 -0.031433 ..
CCV_NNC_GEMM_FORWARD [1378]: [2] -> [1] (0)
Wait: (0, 140)
|-> 1. 0x1438b9520 (0x285da56c0:0) [2x8x4096x40] 0.083069 -0.088074 -0.031433 ..
|-> 2. 0x1438b94b0 (0x285e2f300:0) [2x8x133x40] 2.285156 0.156494 -1.203125 ..
|<- 1. 0x1438b9590 (0x285da5c00:0) [2x8x4096x133] 8.453125 2.052734 2.291016 ..
CCV_NNC_SOFTMAX_FORWARD [1379]: [1] -> [1] (0)
|-> 1. 0x143909730 (0x285da5c00:0) [65536x133] 8.453125 2.052734 2.291016 ..
|<- 1. 0x143909730 (0x285da5c00:0) [65536x133] 0.943848 0.001568 0.001989 ..
CCV_NNC_GEMM_FORWARD [1380]: [2] -> [1] (0)
Wait: (0, 141)
|-> 1. 0x143909810 (0x285da5c00:0) [2x8x4096x133] 0.943848 0.001568 0.001989 ..
|-> 2. 0x1438b9670 (0x285e2ee80:0) [2x8x133x40] -0.004307 -0.029922 0.005905 ..
|<- 1. 0x1438b96e0 (0x285da56c0:0) [2x8x4096x40] 0.032410 -0.042358 0.029572 ..
CCV_NNC_TRANSPOSE_FORWARD [1381]: [1] -> [1] (0)
|-> 1. 0x143909880 (0x285da56c0:0) [2x8x4096x40] 0.032410 -0.042358 0.029572 ..
|<- 1. 0x1438b9750 (0x285da5940:0) [2x4096x8x40] 0.032410 -0.042358 0.029572 ..
CCV_NNC_GEMM_FORWARD [1382]: [3] -> [1] (0)
|-> 1. 0x1439098f0 (0x285da5940:0) [2x4096x320] 0.032410 -0.042358 0.029572 ..
|-> 2. 0x1438ce590 (0x285d9cbc0:0) [320x320] 0.002432 -0.001113 -0.005413 ..
|-> 3. 0x1438ce600 (0x285d9cc00:0) [320] -0.036072 -0.000483 -0.027740 ..
|<- 1. 0x1438b97c0 (0x285da6000:0) [2x4096x320] -0.104126 -0.035950 0.011284 ..
CCV_NNC_ADD_FORWARD [1383]: [2] -> [1] (0)
|-> 1. 0x1438b97c0 (0x285da6000:0) [2x4096x320] -0.104126 -0.035950 0.011284 ..
|-> 2. 0x1438b9210 (0x285da5ac0:0) [2x4096x320] 0.387695 -0.363037 -0.013184 ..
|<- 1. 0x1438b97c0 (0x285da6000:0) [2x4096x320] 0.283691 -0.398926 -0.001900 ..
CCV_NNC_LAYER_NORM_FORWARD [1384]: [3] -> [3] (0)
|-> 1. 0x1438b97c0 (0x285da6000:0) [2x4096x320] 0.283691 -0.398926 -0.001900 ..
|-> 2. 0x1438ce670 (0x285d9cc40:0) [1x1x320] 0.888184 0.930664 0.814941 ..
|-> 3. 0x1438ce6e0 (0x285d9cc80:0) [1x1x320] 0.144531 -0.034454 -0.101807 ..
|<- 1. 0x1438b9830 (0x285da5ac0:0) [2x4096x320] 0.481445 -0.902832 -0.240234 ..
|<- 2. 0x1438b98a0 (0x285da5cc0:0) [2x4096x1] 0.086426 ..
|<- 3. 0x1438b9910 (0x285da5d00:0) [2x4096x1] 1.922852 ..
Emit: (0, 142)
CCV_NNC_GEMM_FORWARD [1385]: [3] -> [1] (0)
|-> 1. 0x1438b9830 (0x285da5ac0:0) [2x4096x320] 0.481445 -0.902832 -0.240234 ..
|-> 2. 0x1438ce750 (0x285d9ccc0:0) [1280x320] 0.018280 -0.093872 -0.108826 ..
|-> 3. 0x1438ce7c0 (0x285d9cd00:0) [1280] -0.036865 0.083435 0.004330 ..
|<- 1. 0x1438b9980 (0x285da5d40:0) [2x4096x1280] -0.005791 0.863770 0.610840 ..
CCV_NNC_GELU_FORWARD [1386]: [1] -> [1] (0)
|-> 1. 0x1438b9980 (0x285da5d40:0) [2x4096x1280] -0.005791 0.863770 0.610840 ..
|<- 1. 0x1438b9980 (0x285da5d40:0) [2x4096x1280] -0.002882 0.696289 0.445557 ..
CCV_NNC_GEMM_FORWARD [1387]: [3] -> [1] (1)
Wait: (1, 142)
|-> 1. 0x1438b9830 (0x285da5ac0:0) [2x4096x320] 0.481445 -0.902832 -0.240234 ..
|-> 2. 0x1438ce830 (0x285d9cd40:0) [1280x320] 0.035645 -0.060822 -0.037689 ..
|-> 3. 0x1438ce8a0 (0x285d9cd80:0) [1280] -0.105286 0.018463 0.044159 ..
|<- 1. 0x1438b99f0 (0x285da5d80:0) [2x4096x1280] -0.597656 -0.955078 0.382324 ..
Emit: (1, 143)
CCV_NNC_MUL_FORWARD [1388]: [2] -> [1] (0)
Wait: (0, 143)
|-> 1. 0x1438b99f0 (0x285da5d80:0) [2x4096x1280] -0.597656 -0.955078 0.382324 ..
|-> 2. 0x1438b9980 (0x285da5d40:0) [2x4096x1280] -0.002882 0.696289 0.445557 ..
|<- 1. 0x1438b99f0 (0x285da5d80:0) [2x4096x1280] 0.001722 -0.665039 0.170288 ..
CCV_NNC_GEMM_FORWARD [1389]: [3] -> [1] (0)
|-> 1. 0x1438b99f0 (0x285da5d80:0) [2x4096x1280] 0.001722 -0.665039 0.170288 ..
|-> 2. 0x1438ce910 (0x285d9cdc0:0) [320x1280] -0.074341 0.044128 0.002029 ..
|-> 3. 0x1438ce980 (0x285d9ce00:0) [320] -0.014694 -0.008881 0.018158 ..
|<- 1. 0x1438b9a60 (0x285da56c0:0) [2x4096x320] 2.130859 -0.796387 -0.145020 ..
CCV_NNC_ADD_FORWARD [1390]: [2] -> [1] (0)
|-> 1. 0x1438b9a60 (0x285da56c0:0) [2x4096x320] 2.130859 -0.796387 -0.145020 ..
|-> 2. 0x1438b97c0 (0x285da6000:0) [2x4096x320] 0.283691 -0.398926 -0.001900 ..
|<- 1. 0x1438b9a60 (0x285da56c0:0) [2x4096x320] 2.414062 -1.195312 -0.146973 ..
CCV_NNC_CONVOLUTION_FORWARD [1391]: [3] -> [1] (0)
|-> 1. 0x143909960 (0x285da56c0:0) [2x64x64x320] 2.414062 -1.195312 -0.146973 ..
|-> 2. 0x1438ce9f0 (0x285d9ce40:0) [320x320x1x1] -0.036530 ..
|-> 3. 0x1438cea60 (0x285d9ce80:0) [320] 0.044312 -0.018341 0.011383 ..
|<- 1. 0x1438b9ad0 (0x285da5940:0) [2x64x64x320] 0.490479 1.916016 -0.887695 ..
CCV_NNC_ADD_FORWARD [1392]: [2] -> [1] (0)
|-> 1. 0x1438b9ad0 (0x285da5940:0) [2x64x64x320] 0.490479 1.916016 -0.887695 ..
|-> 2. 0x1438b8410 (0x285da5840:0) [2x64x64x320] -0.037598 -1.951172 3.376953 ..
|<- 1. 0x1439099d0 (0x285e6d340:0) [2x64x64x320] 0.452881 -0.035156 2.488281 ..
Emit: (0, 145)
CCV_NNC_GROUP_NORM_FORWARD [1393]: [3] -> [3] (0)
|-> 1. 0x1438b9b40 (0x285e6d340:0) [2x64x64x640] 0.452881 -0.035156 2.488281 ..
|-> 2. 0x1438cead0 (0x285d9cec0:0) [1x1x1x640] 0.222168 0.446777 0.263916 ..
|-> 3. 0x1438ceb40 (0x285d9cf00:0) [1x1x1x640] -0.021072 -0.214111 -0.045624 ..
|<- 1. 0x1438b9bb0 (0x285e6b400:0) [2x64x64x640] 0.080078 -0.163818 0.451660 ..
|<- 2. 0x1438b9c20 (0x285da5700:0) [2x1x1x32] -0.195557 -0.057098 -0.259277 ..
|<- 3. 0x1438b9c90 (0x285da5740:0) [2x1x1x32] 0.702148 0.661133 0.733887 ..
CCV_NNC_SWISH_FORWARD [1394]: [1] -> [1] (0)
|-> 1. 0x1438b9bb0 (0x285e6b400:0) [2x64x64x640] 0.080078 -0.163818 0.451660 ..
|<- 1. 0x1438b9bb0 (0x285e6b400:0) [2x64x64x640] 0.041656 -0.075195 0.275879 ..
CCV_NNC_CONVOLUTION_FORWARD [1395]: [3] -> [1] (0)
|-> 1. 0x1438b9bb0 (0x285e6b400:0) [2x64x64x640] 0.041656 -0.075195 0.275879 ..
|-> 2. 0x1438cec90 (0x285d9cfc0:0) [320x640x3x3] 0.019547 0.002209 0.010590 ..
|-> 3. 0x1438ced00 (0x285d9d000:0) [320] 0.027206 -0.053009 0.116943 ..
|<- 1. 0x1438b9d70 (0x285da56c0:0) [2x64x64x320] -0.235840 -0.365967 1.656250 ..
CCV_NNC_ADD_FORWARD [1396]: [2] -> [1] (0)
Wait: (0, 144)
|-> 1. 0x1438b9d70 (0x285da56c0:0) [2x64x64x320] -0.235840 -0.365967 1.656250 ..
|-> 2. 0x143909b30 (0x285e6b440:0) [2x1x1x320] 0.176636 -1.454102 0.976562 ..
|<- 1. 0x1438b9d70 (0x285da56c0:0) [2x64x64x320] -0.059204 -1.820312 2.632812 ..
CCV_NNC_GROUP_NORM_FORWARD [1397]: [3] -> [3] (0)
|-> 1. 0x1438b9d70 (0x285da56c0:0) [2x64x64x320] -0.059204 -1.820312 2.632812 ..
|-> 2. 0x1438ced70 (0x285d9d040:0) [1x1x1x320] 0.740234 0.756348 0.365723 ..
|-> 3. 0x1438cede0 (0x285d9d080:0) [1x1x1x320] -0.278809 -0.094238 -0.340576 ..
|<- 1. 0x1438b9de0 (0x285da5940:0) [2x64x64x320] -0.369629 -1.215820 0.374512 ..
|<- 2. 0x1438b9e50 (0x285e6b480:0) [2x1x1x32] 0.099792 0.359863 0.080627 ..
|<- 3. 0x1438b9ec0 (0x285e6b3c0:0) [2x1x1x32] 0.771973 0.726562 0.973145 ..
CCV_NNC_SWISH_FORWARD [1398]: [1] -> [1] (0)
|-> 1. 0x1438b9de0 (0x285da5940:0) [2x64x64x320] -0.369629 -1.215820 0.374512 ..
|<- 1. 0x1438b9de0 (0x285da5940:0) [2x64x64x320] -0.151001 -0.278076 0.221924 ..
CCV_NNC_CONVOLUTION_FORWARD [1399]: [3] -> [1] (0)
|-> 1. 0x1438b9de0 (0x285da5940:0) [2x64x64x320] -0.151001 -0.278076 0.221924 ..
|-> 2. 0x1438cee50 (0x285d9d0c0:0) [320x320x3x3] -0.018951 -0.014046 -0.001357 ..
|-> 3. 0x1438ceec0 (0x285d9d100:0) [320] 0.043396 0.008461 0.005844 ..
|<- 1. 0x1438b9f30 (0x285da56c0:0) [2x64x64x320] -0.217529 -0.586914 0.395752 ..
CCV_NNC_CONVOLUTION_FORWARD [1400]: [3] -> [1] (1)
Wait: (1, 145)
|-> 1. 0x1438b9b40 (0x285e6d340:0) [2x64x64x640] 0.452881 -0.035156 2.488281 ..
|-> 2. 0x1438cef30 (0x285d9d140:0) [320x640x1x1] 0.018433 ..
|-> 3. 0x1438cefa0 (0x285d9d180:0) [320] 0.055603 0.014923 0.018753 ..
|<- 1. 0x1438b9fa0 (0x285da5840:0) [2x64x64x320] -0.394775 1.056641 -0.672363 ..
Emit: (1, 146)
CCV_NNC_ADD_FORWARD [1401]: [2] -> [1] (0)
Wait: (0, 146)
|-> 1. 0x1438b9fa0 (0x285da5840:0) [2x64x64x320] -0.394775 1.056641 -0.672363 ..
|-> 2. 0x1438b9f30 (0x285da56c0:0) [2x64x64x320] -0.217529 -0.586914 0.395752 ..
|<- 1. 0x1438b9fa0 (0x285da5840:0) [2x64x64x320] -0.612305 0.469727 -0.276611 ..
CCV_NNC_GROUP_NORM_FORWARD [1402]: [3] -> [3] (0)
|-> 1. 0x1438b9fa0 (0x285da5840:0) [2x64x64x320] -0.612305 0.469727 -0.276611 ..
|-> 2. 0x1438cf010 (0x285d9d1c0:0) [1x1x1x320] 0.543457 0.488037 0.537109 ..
|-> 3. 0x1438cf080 (0x285d9d200:0) [1x1x1x320] -0.036194 -0.075378 -0.059967 ..
|<- 1. 0x1438ba010 (0x285da5940:0) [2x64x64x320] -0.244751 0.200439 -0.107910 ..
|<- 2. 0x1438ba080 (0x285da5740:0) [2x1x1x32] -0.174805 -0.386475 0.012535 ..
|<- 3. 0x1438ba0f0 (0x285da5700:0) [2x1x1x32] 0.876953 0.940918 1.223633 ..
CCV_NNC_CONVOLUTION_FORWARD [1403]: [3] -> [1] (0)
|-> 1. 0x1438ba010 (0x285da5940:0) [2x64x64x320] -0.244751 0.200439 -0.107910 ..
|-> 2. 0x1438cf0f0 (0x285d9d240:0) [320x320x1x1] -0.033691 ..
|-> 3. 0x1438cf160 (0x285d9d280:0) [320] -0.055481 0.040924 0.038116 ..
|<- 1. 0x1438ba160 (0x285da56c0:0) [2x64x64x320] 0.386963 0.230591 0.273193 ..
CCV_NNC_LAYER_NORM_FORWARD [1404]: [3] -> [3] (0)
|-> 1. 0x143909ba0 (0x285da56c0:0) [2x4096x320] 0.386963 0.230591 0.273193 ..
|-> 2. 0x1438cf1d0 (0x285d9d2c0:0) [1x1x320] 0.911133 0.854980 0.963867 ..
|-> 3. 0x1438cf240 (0x285d9d300:0) [1x1x320] -0.124084 -0.142822 -0.009514 ..
|<- 1. 0x1438ba1d0 (0x285da5680:0) [2x4096x320] 0.335938 0.099243 0.321777 ..
|<- 2. 0x1438ba240 (0x285da5d00:0) [2x4096x1] 0.031052 ..
|<- 3. 0x1438ba2b0 (0x285da5cc0:0) [2x4096x1] 1.418945 ..
Emit: (0, 147)
CCV_NNC_GEMM_FORWARD [1405]: [2] -> [1] (0)
|-> 1. 0x1438ba1d0 (0x285da5680:0) [2x4096x320] 0.335938 0.099243 0.321777 ..
|-> 2. 0x1438cf2b0 (0x285d9d340:0) [320x320] 0.103699 -0.043152 -0.059509 ..
|<- 1. 0x1438ba320 (0x285da5940:0) [2x4096x320] 1.034180 -5.035156 -0.239380 ..
CCV_NNC_SCALAR_MUL_FORWARD [1406]: [1] -> [1] (0)
|-> 1. 0x1438ba320 (0x285da5940:0) [2x4096x320] 1.034180 -5.035156 -0.239380 ..
|<- 1. 0x1438ba320 (0x285da5940:0) [2x4096x320] 0.163452 -0.795898 -0.037842 ..
CCV_NNC_TRANSPOSE_FORWARD [1407]: [1] -> [1] (0)
|-> 1. 0x143909c80 (0x285da5940:0) [2x4096x8x40] 0.163452 -0.795898 -0.037842 ..
|<- 1. 0x1438ba470 (0x285da5a80:0) [2x8x4096x40] 0.163452 -0.795898 -0.037842 ..
CCV_NNC_GEMM_FORWARD [1408]: [2] -> [1] (1)
Wait: (1, 147)
|-> 1. 0x1438ba1d0 (0x285da5680:0) [2x4096x320] 0.335938 0.099243 0.321777 ..
|-> 2. 0x1438cf320 (0x285d9d380:0) [320x320] 0.037842 -0.132935 0.036316 ..
|<- 1. 0x1438ba390 (0x285da5900:0) [2x4096x320] 2.597656 -6.636719 -2.279297 ..
CCV_NNC_TRANSPOSE_FORWARD [1409]: [1] -> [1] (1)
|-> 1. 0x143909c10 (0x285da5900:0) [2x4096x8x40] 2.597656 -6.636719 -2.279297 ..
|<- 1. 0x1438ba400 (0x285da59c0:0) [2x8x4096x40] 2.597656 -6.636719 -2.279297 ..
Emit: (1, 148)
CCV_NNC_GEMM_FORWARD [1410]: [2] -> [1] (2)
Wait: (2, 147)
|-> 1. 0x1438ba1d0 (0x285da5680:0) [2x4096x320] 0.335938 0.099243 0.321777 ..
|-> 2. 0x1438cf390 (0x285d9d3c0:0) [320x320] 0.069397 0.066040 0.050842 ..
|<- 1. 0x1438ba4e0 (0x285da5a00:0) [2x4096x320] 0.349365 -0.399414 0.704102 ..
CCV_NNC_TRANSPOSE_FORWARD [1411]: [1] -> [1] (2)
|-> 1. 0x143909dd0 (0x285da5a00:0) [2x4096x8x40] 0.349365 -0.399414 0.704102 ..
|<- 1. 0x1438ba5c0 (0x285da5980:0) [2x8x4096x40] 0.349365 -0.399414 0.704102 ..
Emit: (2, 149)
CCV_NNC_GEMM_FORWARD [1412]: [2] -> [1] (0)
Wait: (0, 148)
|-> 1. 0x143909d60 (0x285da5a80:0) [1x4096x40] 0.163452 -0.795898 -0.037842 ..
|-> 2. 0x143909cf0 (0x285da59c0:0) [1x4096x40] 2.597656 -6.636719 -2.279297 ..
|<- 1. 0x1438ba550 (0x285da5a40:0) [1x4096x4096] 31.562500 30.796875 30.312500 ..
CCV_NNC_SOFTMAX_FORWARD [1413]: [1] -> [1] (0)
|-> 1. 0x143909e40 (0x285da5a40:0) [4096x4096] 31.562500 30.796875 30.312500 ..
|<- 1. 0x143909e40 (0x285da5a40:0) [4096x4096] 0.009254 0.004307 0.002653 ..
CCV_NNC_GEMM_FORWARD [1414]: [2] -> [1] (0)
Wait: (0, 149)
|-> 1. 0x143909f20 (0x285da5a40:0) [1x4096x4096] 0.009254 0.004307 0.002653 ..
|-> 2. 0x143909eb0 (0x285da5980:0) [1x4096x40] 0.349365 -0.399414 0.704102 ..
|<- 1. 0x14390cba0 (0x285da5680:0) [1x4096x40] 0.403809 -0.681641 0.362061 ..
CCV_NNC_GEMM_FORWARD [1415]: [2] -> [1] (0)
|-> 1. 0x14390a040 (0x285da5a80:0) [1x4096x40] 0.319580 -0.025375 -0.428467 ..
|-> 2. 0x143909f90 (0x285da59c0:0) [1x4096x40] 3.173828 1.068359 -4.675781 ..
|<- 1. 0x1438ba630 (0x285da5a40:0) [1x4096x4096] 28.000000 27.484375 27.171875 ..
CCV_NNC_SOFTMAX_FORWARD [1416]: [1] -> [1] (0)
|-> 1. 0x14390a0f0 (0x285da5a40:0) [4096x4096] 28.000000 27.484375 27.171875 ..
|<- 1. 0x14390a0f0 (0x285da5a40:0) [4096x4096] 0.018692 0.011162 0.008163 ..
CCV_NNC_GEMM_FORWARD [1417]: [2] -> [1] (0)
|-> 1. 0x14390a210 (0x285da5a40:0) [1x4096x4096] 0.018692 0.011162 0.008163 ..
|-> 2. 0x14390a160 (0x285da5980:0) [1x4096x40] -0.356689 -0.084534 0.624023 ..
|<- 1. 0x14390cc10 (0x285da5680:0) [1x4096x40] -0.203735 0.123413 0.368164 ..
CCV_NNC_GEMM_FORWARD [1418]: [2] -> [1] (0)
|-> 1. 0x14390a330 (0x285da5a80:0) [1x4096x40] -0.200562 0.474121 -0.026245 ..
|-> 2. 0x14390a280 (0x285da59c0:0) [1x4096x40] -2.310547 4.902344 -0.715332 ..
|<- 1. 0x1438ba6a0 (0x285da5a40:0) [1x4096x4096] 32.125000 31.593750 31.578125 ..
CCV_NNC_SOFTMAX_FORWARD [1419]: [1] -> [1] (0)
|-> 1. 0x14390a3e0 (0x285da5a40:0) [4096x4096] 32.125000 31.593750 31.578125 ..
|<- 1. 0x14390a3e0 (0x285da5a40:0) [4096x4096] 0.011955 0.007027 0.006916 ..
CCV_NNC_GEMM_FORWARD [1420]: [2] -> [1] (0)
|-> 1. 0x14390a500 (0x285da5a40:0) [1x4096x4096] 0.011955 0.007027 0.006916 ..
|-> 2. 0x14390a450 (0x285da5980:0) [1x4096x40] -0.653320 0.584961 0.045380 ..
|<- 1. 0x14390ccc0 (0x285da5680:0) [1x4096x40] -0.250000 0.701172 -0.247681 ..
CCV_NNC_GEMM_FORWARD [1421]: [2] -> [1] (0)
|-> 1. 0x14390a620 (0x285da5a80:0) [1x4096x40] 0.391846 -0.003901 0.034180 ..
|-> 2. 0x14390a570 (0x285da59c0:0) [1x4096x40] 3.427734 0.782227 0.621582 ..
|<- 1. 0x1438ba710 (0x285da5a40:0) [1x4096x4096] 24.750000 25.062500 24.906250 ..
CCV_NNC_SOFTMAX_FORWARD [1422]: [1] -> [1] (0)
|-> 1. 0x14390a6d0 (0x285da5a40:0) [4096x4096] 24.750000 25.062500 24.906250 ..
|<- 1. 0x14390a6d0 (0x285da5a40:0) [4096x4096] 0.002506 0.003428 0.002932 ..
CCV_NNC_GEMM_FORWARD [1423]: [2] -> [1] (0)
|-> 1. 0x14390a7f0 (0x285da5a40:0) [1x4096x4096] 0.002506 0.003428 0.002932 ..
|-> 2. 0x14390a740 (0x285da5980:0) [1x4096x40] 0.489990 -0.343262 -0.961914 ..
|<- 1. 0x14390cd70 (0x285da5680:0) [1x4096x40] 0.168213 -0.097229 -0.058624 ..
CCV_NNC_GEMM_FORWARD [1424]: [2] -> [1] (0)
|-> 1. 0x14390a910 (0x285da5a80:0) [1x4096x40] 0.732910 0.154175 -0.162598 ..
|-> 2. 0x14390a860 (0x285da59c0:0) [1x4096x40] 5.941406 -1.215820 -3.304688 ..
|<- 1. 0x1438ba780 (0x285da5a40:0) [1x4096x4096] 23.140625 21.375000 21.125000 ..
CCV_NNC_SOFTMAX_FORWARD [1425]: [1] -> [1] (0)
|-> 1. 0x14390a9c0 (0x285da5a40:0) [4096x4096] 23.140625 21.375000 21.125000 ..
|<- 1. 0x14390a9c0 (0x285da5a40:0) [4096x4096] 0.046661 0.007988 0.006218 ..
CCV_NNC_GEMM_FORWARD [1426]: [2] -> [1] (0)
|-> 1. 0x14390aae0 (0x285da5a40:0) [1x4096x4096] 0.046661 0.007988 0.006218 ..
|-> 2. 0x14390aa30 (0x285da5980:0) [1x4096x40] 0.360840 0.028427 -0.185059 ..
|<- 1. 0x14390ce20 (0x285da5680:0) [1x4096x40] 0.059509 0.155029 0.005760 ..
CCV_NNC_GEMM_FORWARD [1427]: [2] -> [1] (0)
|-> 1. 0x14390ac00 (0x285da5a80:0) [1x4096x40] -0.346436 -0.351074 0.042603 ..
|-> 2. 0x14390ab50 (0x285da59c0:0) [1x4096x40] -2.867188 -3.609375 0.840332 ..
|<- 1. 0x1438ba7f0 (0x285da5a40:0) [1x4096x4096] 19.265625 17.953125 18.187500 ..
CCV_NNC_SOFTMAX_FORWARD [1428]: [1] -> [1] (0)
|-> 1. 0x14390acb0 (0x285da5a40:0) [4096x4096] 19.265625 17.953125 18.187500 ..
|<- 1. 0x14390acb0 (0x285da5a40:0) [4096x4096] 0.012459 0.003353 0.004238 ..
CCV_NNC_GEMM_FORWARD [1429]: [2] -> [1] (0)
|-> 1. 0x14390add0 (0x285da5a40:0) [1x4096x4096] 0.012459 0.003353 0.004238 ..
|-> 2. 0x14390ad20 (0x285da5980:0) [1x4096x40] -0.114868 0.055420 0.589844 ..
|<- 1. 0x14390ced0 (0x285da5680:0) [1x4096x40] -0.106079 0.068542 -0.036865 ..
CCV_NNC_GEMM_FORWARD [1430]: [2] -> [1] (0)
|-> 1. 0x14390aef0 (0x285da5a80:0) [1x4096x40] -0.200073 0.337158 0.065002 ..
|-> 2. 0x14390ae40 (0x285da59c0:0) [1x4096x40] -1.202148 1.389648 1.197266 ..
|<- 1. 0x1438ba860 (0x285da5a40:0) [1x4096x4096] 21.156250 20.906250 21.031250 ..
CCV_NNC_SOFTMAX_FORWARD [1431]: [1] -> [1] (0)
|-> 1. 0x14390afa0 (0x285da5a40:0) [4096x4096] 21.156250 20.906250 21.031250 ..
|<- 1. 0x14390afa0 (0x285da5a40:0) [4096x4096] 0.005661 0.004410 0.004997 ..
CCV_NNC_GEMM_FORWARD [1432]: [2] -> [1] (0)
|-> 1. 0x14390b0c0 (0x285da5a40:0) [1x4096x4096] 0.005661 0.004410 0.004997 ..
|-> 2. 0x14390b010 (0x285da5980:0) [1x4096x40] 0.461914 0.326660 0.252686 ..
|<- 1. 0x14390cf80 (0x285da5680:0) [1x4096x40] 0.260986 0.046295 0.193848 ..
CCV_NNC_GEMM_FORWARD [1433]: [2] -> [1] (0)
|-> 1. 0x14390b1e0 (0x285da5a80:0) [1x4096x40] -0.149414 0.153809 0.112366 ..
|-> 2. 0x14390b130 (0x285da59c0:0) [1x4096x40] 0.341797 1.525391 -0.011078 ..
|<- 1. 0x1438ba8d0 (0x285da5a40:0) [1x4096x4096] 10.140625 9.351562 9.203125 ..
CCV_NNC_SOFTMAX_FORWARD [1434]: [1] -> [1] (0)
|-> 1. 0x14390b290 (0x285da5a40:0) [4096x4096] 10.140625 9.351562 9.203125 ..
|<- 1. 0x14390b290 (0x285da5a40:0) [4096x4096] 0.001595 0.000724 0.000624 ..
CCV_NNC_GEMM_FORWARD [1435]: [2] -> [1] (0)
|-> 1. 0x14390b3b0 (0x285da5a40:0) [1x4096x4096] 0.001595 0.000724 0.000624 ..
|-> 2. 0x14390b300 (0x285da5980:0) [1x4096x40] 0.433350 -0.510742 -0.448975 ..
|<- 1. 0x14390d030 (0x285da5680:0) [1x4096x40] -0.031494 0.388428 -0.228638 ..
CCV_NNC_GEMM_FORWARD [1436]: [2] -> [1] (0)
|-> 1. 0x14390b4d0 (0x285da5a80:0) [1x4096x40] 0.094299 -0.801758 -0.006428 ..
|-> 2. 0x14390b420 (0x285da59c0:0) [1x4096x40] 1.730469 -6.441406 -2.611328 ..
|<- 1. 0x1438ba940 (0x285da5a40:0) [1x4096x4096] 31.031250 30.593750 30.046875 ..
CCV_NNC_SOFTMAX_FORWARD [1437]: [1] -> [1] (0)
|-> 1. 0x14390b580 (0x285da5a40:0) [4096x4096] 31.031250 30.593750 30.046875 ..
|<- 1. 0x14390b580 (0x285da5a40:0) [4096x4096] 0.007820 0.005051 0.002924 ..
CCV_NNC_GEMM_FORWARD [1438]: [2] -> [1] (0)
|-> 1. 0x14390b6a0 (0x285da5a40:0) [1x4096x4096] 0.007820 0.005051 0.002924 ..
|-> 2. 0x14390b5f0 (0x285da5980:0) [1x4096x40] 0.398193 -0.484863 0.333740 ..
|<- 1. 0x14390d0e0 (0x285da5680:0) [1x4096x40] 0.293213 -0.529785 0.206787 ..
CCV_NNC_GEMM_FORWARD [1439]: [2] -> [1] (0)
|-> 1. 0x14390b7c0 (0x285da5a80:0) [1x4096x40] 0.265869 -0.017120 -0.385742 ..
|-> 2. 0x14390b710 (0x285da59c0:0) [1x4096x40] 2.261719 1.733398 -4.933594 ..
|<- 1. 0x1438ba9b0 (0x285da5a40:0) [1x4096x4096] 27.406250 27.328125 26.656250 ..
CCV_NNC_SOFTMAX_FORWARD [1440]: [1] -> [1] (0)
|-> 1. 0x14390b870 (0x285da5a40:0) [4096x4096] 27.406250 27.328125 26.656250 ..
|<- 1. 0x14390b870 (0x285da5a40:0) [4096x4096] 0.011154 0.010315 0.005268 ..
CCV_NNC_GEMM_FORWARD [1441]: [2] -> [1] (0)
|-> 1. 0x14390b990 (0x285da5a40:0) [1x4096x4096] 0.011154 0.010315 0.005268 ..
|-> 2. 0x14390b8e0 (0x285da5980:0) [1x4096x40] -0.323486 0.069824 0.541504 ..
|<- 1. 0x14390d190 (0x285da5680:0) [1x4096x40] -0.213989 0.158936 0.324219 ..
CCV_NNC_GEMM_FORWARD [1442]: [2] -> [1] (0)
|-> 1. 0x14390bab0 (0x285da5a80:0) [1x4096x40] -0.234863 0.510742 -0.080872 ..
|-> 2. 0x14390ba00 (0x285da59c0:0) [1x4096x40] -2.763672 5.031250 -1.118164 ..
|<- 1. 0x1438baa20 (0x285da5a40:0) [1x4096x4096] 31.671875 31.484375 31.312500 ..
CCV_NNC_SOFTMAX_FORWARD [1443]: [1] -> [1] (0)
|-> 1. 0x14390bb60 (0x285da5a40:0) [4096x4096] 31.671875 31.484375 31.312500 ..
|<- 1. 0x14390bb60 (0x285da5a40:0) [4096x4096] 0.006725 0.005573 0.004696 ..
CCV_NNC_GEMM_FORWARD [1444]: [2] -> [1] (0)
|-> 1. 0x14390bc80 (0x285da5a40:0) [1x4096x4096] 0.006725 0.005573 0.004696 ..
|-> 2. 0x14390bbd0 (0x285da5980:0) [1x4096x40] -0.598145 0.750488 0.204956 ..
|<- 1. 0x14390d240 (0x285da5680:0) [1x4096x40] -0.074219 0.740723 -0.277100 ..
CCV_NNC_GEMM_FORWARD [1445]: [2] -> [1] (0)
|-> 1. 0x14390bda0 (0x285da5a80:0) [1x4096x40] 0.430664 0.001458 0.057892 ..
|-> 2. 0x14390bcf0 (0x285da59c0:0) [1x4096x40] 3.707031 0.800293 0.935059 ..
|<- 1. 0x1438baa90 (0x285da5a40:0) [1x4096x4096] 25.000000 25.421875 25.109375 ..
CCV_NNC_SOFTMAX_FORWARD [1446]: [1] -> [1] (0)
|-> 1. 0x14390be50 (0x285da5a40:0) [4096x4096] 25.000000 25.421875 25.109375 ..
|<- 1. 0x14390be50 (0x285da5a40:0) [4096x4096] 0.002108 0.003214 0.002352 ..
CCV_NNC_GEMM_FORWARD [1447]: [2] -> [1] (0)
|-> 1. 0x14390bf70 (0x285da5a40:0) [1x4096x4096] 0.002108 0.003214 0.002352 ..
|-> 2. 0x14390bec0 (0x285da5980:0) [1x4096x40] 0.375488 -0.056519 -0.926270 ..
|<- 1. 0x14390d2f0 (0x285da5680:0) [1x4096x40] 0.068542 0.187622 -0.021896 ..
CCV_NNC_GEMM_FORWARD [1448]: [2] -> [1] (0)
|-> 1. 0x14390c090 (0x285da5a80:0) [1x4096x40] 0.672852 0.210571 -0.129028 ..
|-> 2. 0x14390bfe0 (0x285da59c0:0) [1x4096x40] 5.898438 -0.648438 -2.865234 ..
|<- 1. 0x1438bab00 (0x285da5a40:0) [1x4096x4096] 22.218750 20.984375 20.765625 ..
CCV_NNC_SOFTMAX_FORWARD [1449]: [1] -> [1] (0)
|-> 1. 0x14390c140 (0x285da5a40:0) [4096x4096] 22.218750 20.984375 20.765625 ..
|<- 1. 0x14390c140 (0x285da5a40:0) [4096x4096] 0.019730 0.005745 0.004616 ..
CCV_NNC_GEMM_FORWARD [1450]: [2] -> [1] (0)
|-> 1. 0x14390c260 (0x285da5a40:0) [1x4096x4096] 0.019730 0.005745 0.004616 ..
|-> 2. 0x14390c1b0 (0x285da5980:0) [1x4096x40] 0.184204 -0.037384 -0.142334 ..
|<- 1. 0x14390d3a0 (0x285da5680:0) [1x4096x40] -0.032288 0.130981 0.124146 ..
CCV_NNC_GEMM_FORWARD [1451]: [2] -> [1] (0)
|-> 1. 0x14390c380 (0x285da5a80:0) [1x4096x40] -0.448242 -0.437500 0.084229 ..
|-> 2. 0x14390c2d0 (0x285da59c0:0) [1x4096x40] -3.394531 -4.011719 0.787109 ..
|<- 1. 0x1438bab70 (0x285da5a40:0) [1x4096x4096] 18.625000 17.968750 18.046875 ..
CCV_NNC_SOFTMAX_FORWARD [1452]: [1] -> [1] (0)
|-> 1. 0x14390c430 (0x285da5a40:0) [4096x4096] 18.625000 17.968750 18.046875 ..
|<- 1. 0x14390c430 (0x285da5a40:0) [4096x4096] 0.006096 0.003162 0.003418 ..
CCV_NNC_GEMM_FORWARD [1453]: [2] -> [1] (0)
|-> 1. 0x14390c550 (0x285da5a40:0) [1x4096x4096] 0.006096 0.003162 0.003418 ..
|-> 2. 0x14390c4a0 (0x285da5980:0) [1x4096x40] -0.186035 -0.052948 0.116699 ..
|<- 1. 0x14390d450 (0x285da5680:0) [1x4096x40] 0.026459 -0.114990 -0.294922 ..
CCV_NNC_GEMM_FORWARD [1454]: [2] -> [1] (0)
|-> 1. 0x14390c670 (0x285da5a80:0) [1x4096x40] -0.193848 0.334961 0.038361 ..
|-> 2. 0x14390c5c0 (0x285da59c0:0) [1x4096x40] -1.271484 1.215820 0.925781 ..
|<- 1. 0x1438babe0 (0x285da5a40:0) [1x4096x4096] 21.125000 20.937500 20.781250 ..
CCV_NNC_SOFTMAX_FORWARD [1455]: [1] -> [1] (0)
|-> 1. 0x14390c720 (0x285da5a40:0) [4096x4096] 21.125000 20.937500 20.781250 ..
|<- 1. 0x14390c720 (0x285da5a40:0) [4096x4096] 0.003582 0.002970 0.002541 ..
CCV_NNC_GEMM_FORWARD [1456]: [2] -> [1] (0)
|-> 1. 0x14390c840 (0x285da5a40:0) [1x4096x4096] 0.003582 0.002970 0.002541 ..
|-> 2. 0x14390c790 (0x285da5980:0) [1x4096x40] 0.295410 0.205688 0.200317 ..
|<- 1. 0x14390d500 (0x285da5680:0) [1x4096x40] 0.061218 -0.064148 0.158691 ..
CCV_NNC_GEMM_FORWARD [1457]: [2] -> [1] (0)
|-> 1. 0x14390c960 (0x285da5a80:0) [1x4096x40] -0.159790 0.145386 0.116882 ..
|-> 2. 0x14390c8b0 (0x285da59c0:0) [1x4096x40] -0.148315 1.265625 -0.112671 ..
|<- 1. 0x1438bac50 (0x285da5a40:0) [1x4096x4096] 10.953125 10.312500 10.015625 ..
CCV_NNC_SOFTMAX_FORWARD [1458]: [1] -> [1] (0)
|-> 1. 0x14390ca10 (0x285da5a40:0) [4096x4096] 10.953125 10.312500 10.015625 ..
|<- 1. 0x14390ca10 (0x285da5a40:0) [4096x4096] 0.001497 0.000789 0.000587 ..
CCV_NNC_GEMM_FORWARD [1459]: [2] -> [1] (0)
|-> 1. 0x14390cb30 (0x285da5a40:0) [1x4096x4096] 0.001497 0.000789 0.000587 ..
|-> 2. 0x14390ca80 (0x285da5980:0) [1x4096x40] 0.254639 -0.479736 -0.680664 ..
|<- 1. 0x14390d5b0 (0x285da5680:0) [1x4096x40] -0.035034 0.397217 -0.361572 ..
CCV_NNC_TRANSPOSE_FORWARD [1460]: [1] -> [1] (0)
|-> 1. 0x14390d660 (0x285da5680:0) [2x8x4096x40] 0.403809 -0.681641 0.362061 ..
|<- 1. 0x1438bad30 (0x285da5940:0) [2x4096x8x40] 0.403809 -0.681641 0.362061 ..
CCV_NNC_GEMM_FORWARD [1461]: [3] -> [1] (0)
|-> 1. 0x14390d6d0 (0x285da5940:0) [2x4096x320] 0.403809 -0.681641 0.362061 ..
|-> 2. 0x1438cf400 (0x285d9d400:0) [320x320] -0.006226 -0.002787 -0.057770 ..
|-> 3. 0x1438cf470 (0x285d9d440:0) [320] -0.052582 0.042450 0.000213 ..
|<- 1. 0x1438bada0 (0x285da5ac0:0) [2x4096x320] -1.110352 0.015533 -0.390381 ..
CCV_NNC_ADD_FORWARD [1462]: [2] -> [1] (0)
|-> 1. 0x1438bada0 (0x285da5ac0:0) [2x4096x320] -1.110352 0.015533 -0.390381 ..
|-> 2. 0x143909ba0 (0x285da56c0:0) [2x4096x320] 0.386963 0.230591 0.273193 ..
|<- 1. 0x1438bada0 (0x285da5ac0:0) [2x4096x320] -0.723633 0.246094 -0.117188 ..
CCV_NNC_LAYER_NORM_FORWARD [1463]: [3] -> [3] (0)
|-> 1. 0x1438bada0 (0x285da5ac0:0) [2x4096x320] -0.723633 0.246094 -0.117188 ..
|-> 2. 0x1438cf4e0 (0x285d9d480:0) [1x1x320] 0.384766 0.144775 0.276367 ..
|-> 3. 0x1438cf550 (0x285d9d4c0:0) [1x1x320] 0.102844 -0.406982 -0.126953 ..
|<- 1. 0x1438bae10 (0x285da5940:0) [2x4096x320] -0.460205 -0.342285 -0.201294 ..
|<- 2. 0x1438bae80 (0x285da5b40:0) [2x4096x1] 0.019394 ..
|<- 3. 0x1438baef0 (0x285da5b00:0) [2x4096x1] 1.969727 ..
CCV_NNC_GEMM_FORWARD [1464]: [2] -> [1] (0)
|-> 1. 0x1438bae10 (0x285da5940:0) [2x4096x320] -0.460205 -0.342285 -0.201294 ..
|-> 2. 0x1438cf5c0 (0x285d9d500:0) [320x320] 0.029404 0.166260 0.031235 ..
|<- 1. 0x1438baf60 (0x285da5900:0) [2x4096x320] -0.324707 -0.035767 -0.345459 ..
CCV_NNC_SCALAR_MUL_FORWARD [1465]: [1] -> [1] (0)
|-> 1. 0x1438baf60 (0x285da5900:0) [2x4096x320] -0.324707 -0.035767 -0.345459 ..
|<- 1. 0x1438baf60 (0x285da5900:0) [2x4096x320] -0.051331 -0.005653 -0.054596 ..
CCV_NNC_TRANSPOSE_FORWARD [1466]: [1] -> [1] (0)
|-> 1. 0x14390d7b0 (0x285da5900:0) [2x4096x8x40] -0.051331 -0.005653 -0.054596 ..
|<- 1. 0x1438bb0b0 (0x285da56c0:0) [2x8x4096x40] -0.051331 -0.005653 -0.054596 ..
CCV_NNC_GEMM_FORWARD [1467]: [2] -> [1] (0)
Wait: (0, 150)
|-> 1. 0x1438bb0b0 (0x285da56c0:0) [2x8x4096x40] -0.051331 -0.005653 -0.054596 ..
|-> 2. 0x1438bb040 (0x285ef41c0:0) [2x8x133x40] -1.026367 0.949707 -6.625000 ..
|<- 1. 0x1438bb120 (0x285da5c00:0) [2x8x4096x133] 6.363281 0.032715 -0.275146 ..
CCV_NNC_SOFTMAX_FORWARD [1468]: [1] -> [1] (0)
|-> 1. 0x14390d820 (0x285da5c00:0) [65536x133] 6.363281 0.032715 -0.275146 ..
|<- 1. 0x14390d820 (0x285da5c00:0) [65536x133] 0.852051 0.001517 0.001116 ..
CCV_NNC_GEMM_FORWARD [1469]: [2] -> [1] (0)
Wait: (0, 151)
|-> 1. 0x14390d900 (0x285da5c00:0) [2x8x4096x133] 0.852051 0.001517 0.001116 ..
|-> 2. 0x1438bb200 (0x285ed54c0:0) [2x8x133x40] 0.047729 0.026077 0.020203 ..
|<- 1. 0x1438bb270 (0x285da56c0:0) [2x8x4096x40] 0.044861 -0.043243 0.010788 ..
CCV_NNC_TRANSPOSE_FORWARD [1470]: [1] -> [1] (0)
|-> 1. 0x14390d970 (0x285da56c0:0) [2x8x4096x40] 0.044861 -0.043243 0.010788 ..
|<- 1. 0x1438bb2e0 (0x285da5940:0) [2x4096x8x40] 0.044861 -0.043243 0.010788 ..
CCV_NNC_GEMM_FORWARD [1471]: [3] -> [1] (0)
|-> 1. 0x14390d9e0 (0x285da5940:0) [2x4096x320] 0.044861 -0.043243 0.010788 ..
|-> 2. 0x1438cf710 (0x285d9d5c0:0) [320x320] -0.005302 -0.015038 -0.013893 ..
|-> 3. 0x1438cf780 (0x285d9d600:0) [320] 0.037140 0.009109 -0.004398 ..
|<- 1. 0x1438bb350 (0x285da5a80:0) [2x4096x320] -0.045319 -0.009712 -0.032990 ..
CCV_NNC_ADD_FORWARD [1472]: [2] -> [1] (0)
|-> 1. 0x1438bb350 (0x285da5a80:0) [2x4096x320] -0.045319 -0.009712 -0.032990 ..
|-> 2. 0x1438bada0 (0x285da5ac0:0) [2x4096x320] -0.723633 0.246094 -0.117188 ..
|<- 1. 0x1438bb350 (0x285da5a80:0) [2x4096x320] -0.769043 0.236328 -0.150146 ..
CCV_NNC_LAYER_NORM_FORWARD [1473]: [3] -> [3] (0)
|-> 1. 0x1438bb350 (0x285da5a80:0) [2x4096x320] -0.769043 0.236328 -0.150146 ..
|-> 2. 0x1438cf7f0 (0x285d9d640:0) [1x1x320] 0.563477 0.693848 0.683105 ..
|-> 3. 0x1438cf860 (0x285d9d680:0) [1x1x320] 0.027481 -0.068298 -0.006428 ..
|<- 1. 0x1438bb3c0 (0x285da5ac0:0) [2x4096x320] -0.902832 0.253418 -0.244995 ..
|<- 2. 0x1438bb430 (0x285da5cc0:0) [2x4096x1] 0.015900 ..
|<- 3. 0x1438bb4a0 (0x285da5d00:0) [2x4096x1] 2.103516 ..
Emit: (0, 152)
CCV_NNC_GEMM_FORWARD [1474]: [3] -> [1] (0)
|-> 1. 0x1438bb3c0 (0x285da5ac0:0) [2x4096x320] -0.902832 0.253418 -0.244995 ..
|-> 2. 0x1438cf8d0 (0x285d9d6c0:0) [1280x320] -0.021347 0.072876 -0.072388 ..
|-> 3. 0x1438cf940 (0x285d9d700:0) [1280] -0.043152 0.044281 0.060944 ..
|<- 1. 0x1438bb510 (0x285da5d40:0) [2x4096x1280] 0.015205 0.159180 0.815918 ..
CCV_NNC_GELU_FORWARD [1475]: [1] -> [1] (0)
|-> 1. 0x1438bb510 (0x285da5d40:0) [2x4096x1280] 0.015205 0.159180 0.815918 ..
|<- 1. 0x1438bb510 (0x285da5d40:0) [2x4096x1280] 0.007694 0.089661 0.646973 ..
CCV_NNC_GEMM_FORWARD [1476]: [3] -> [1] (1)
Wait: (1, 152)
|-> 1. 0x1438bb3c0 (0x285da5ac0:0) [2x4096x320] -0.902832 0.253418 -0.244995 ..
|-> 2. 0x1438cf9b0 (0x285d9d740:0) [1280x320] -0.007217 -0.060333 -0.004696 ..
|-> 3. 0x1438cfa20 (0x285d9d780:0) [1280] -0.116943 -0.015251 0.032379 ..
|<- 1. 0x1438bb580 (0x285da5d80:0) [2x4096x1280] -0.147339 -0.221924 0.387939 ..
Emit: (1, 153)
CCV_NNC_MUL_FORWARD [1477]: [2] -> [1] (0)
Wait: (0, 153)
|-> 1. 0x1438bb580 (0x285da5d80:0) [2x4096x1280] -0.147339 -0.221924 0.387939 ..
|-> 2. 0x1438bb510 (0x285da5d40:0) [2x4096x1280] 0.007694 0.089661 0.646973 ..
|<- 1. 0x1438bb580 (0x285da5d80:0) [2x4096x1280] -0.001134 -0.019897 0.250977 ..
CCV_NNC_GEMM_FORWARD [1478]: [3] -> [1] (0)
|-> 1. 0x1438bb580 (0x285da5d80:0) [2x4096x1280] -0.001134 -0.019897 0.250977 ..
|-> 2. 0x1438cfa90 (0x285d9d7c0:0) [320x1280] -0.053497 0.012962 0.006279 ..
|-> 3. 0x1438cfb00 (0x285d9d800:0) [320] 0.025131 -0.035522 0.018524 ..
|<- 1. 0x1438bb5f0 (0x285da56c0:0) [2x4096x320] 1.109375 0.353271 0.677734 ..
CCV_NNC_ADD_FORWARD [1479]: [2] -> [1] (0)
|-> 1. 0x1438bb5f0 (0x285da56c0:0) [2x4096x320] 1.109375 0.353271 0.677734 ..
|-> 2. 0x1438bb350 (0x285da5a80:0) [2x4096x320] -0.769043 0.236328 -0.150146 ..
|<- 1. 0x1438bb5f0 (0x285da56c0:0) [2x4096x320] 0.340332 0.589844 0.527344 ..
CCV_NNC_CONVOLUTION_FORWARD [1480]: [3] -> [1] (0)
|-> 1. 0x14390da50 (0x285da56c0:0) [2x64x64x320] 0.340332 0.589844 0.527344 ..
|-> 2. 0x1438cfb70 (0x285d9d840:0) [320x320x1x1] 0.087952 ..
|-> 3. 0x1438cfbe0 (0x285d9d880:0) [320] 0.026993 -0.009033 0.013611 ..
|<- 1. 0x1438bb660 (0x285da5a80:0) [2x64x64x320] 0.049194 0.385742 0.315430 ..
CCV_NNC_ADD_FORWARD [1481]: [2] -> [1] (0)
|-> 1. 0x1438bb660 (0x285da5a80:0) [2x64x64x320] 0.049194 0.385742 0.315430 ..
|-> 2. 0x1438b9fa0 (0x285da5840:0) [2x64x64x320] -0.612305 0.469727 -0.276611 ..
|<- 1. 0x14390dac0 (0x285f78ac0:0) [2x64x64x320] -0.562988 0.855469 0.038818 ..
Emit: (0, 155)
CCV_NNC_GROUP_NORM_FORWARD [1482]: [3] -> [3] (0)
|-> 1. 0x1438bb6d0 (0x285f78ac0:0) [2x64x64x640] -0.562988 0.855469 0.038818 ..
|-> 2. 0x1438cfc50 (0x285d9d8c0:0) [1x1x1x640] 0.173950 0.157349 0.217163 ..
|-> 3. 0x1438cfcc0 (0x285d9d900:0) [1x1x1x640] -0.004253 -0.018677 -0.028885 ..
|<- 1. 0x1438bb740 (0x285e6b400:0) [2x64x64x640] -0.058197 0.136841 0.023422 ..
|<- 2. 0x1438bb7b0 (0x285da5700:0) [2x1x1x32] -0.224243 -0.161255 -0.112244 ..
|<- 3. 0x1438bb820 (0x285da5740:0) [2x1x1x32] 0.915527 1.054688 0.871582 ..
CCV_NNC_SWISH_FORWARD [1483]: [1] -> [1] (0)
|-> 1. 0x1438bb740 (0x285e6b400:0) [2x64x64x640] -0.058197 0.136841 0.023422 ..
|<- 1. 0x1438bb740 (0x285e6b400:0) [2x64x64x640] -0.028259 0.073120 0.011848 ..
CCV_NNC_CONVOLUTION_FORWARD [1484]: [3] -> [1] (0)
|-> 1. 0x1438bb740 (0x285e6b400:0) [2x64x64x640] -0.028259 0.073120 0.011848 ..
|-> 2. 0x1438cfe10 (0x285d9d9c0:0) [320x640x3x3] -0.033051 0.034088 0.006004 ..
|-> 3. 0x1438cfe80 (0x285d9da00:0) [320] -0.010132 -0.052979 0.049622 ..
|<- 1. 0x1438bb900 (0x285da56c0:0) [2x64x64x320] 0.709473 -0.756836 0.607910 ..
CCV_NNC_ADD_FORWARD [1485]: [2] -> [1] (0)
Wait: (0, 154)
|-> 1. 0x1438bb900 (0x285da56c0:0) [2x64x64x320] 0.709473 -0.756836 0.607910 ..
|-> 2. 0x14390dc20 (0x285f65e80:0) [2x1x1x320] -0.972656 0.468994 0.141357 ..
|<- 1. 0x1438bb900 (0x285da56c0:0) [2x64x64x320] -0.263184 -0.287842 0.749023 ..
CCV_NNC_GROUP_NORM_FORWARD [1486]: [3] -> [3] (0)
|-> 1. 0x1438bb900 (0x285da56c0:0) [2x64x64x320] -0.263184 -0.287842 0.749023 ..
|-> 2. 0x1438cfef0 (0x285d9da40:0) [1x1x1x320] 0.465332 0.802734 0.416016 ..
|-> 3. 0x1438cff60 (0x285d9da80:0) [1x1x1x320] -0.057037 0.114380 -0.037567 ..
|<- 1. 0x1438bb970 (0x285da5940:0) [2x64x64x320] 0.074646 0.325195 0.425781 ..
|<- 2. 0x1438bb9e0 (0x285e6b3c0:0) [2x1x1x32] -0.607910 -0.021637 0.203613 ..
|<- 3. 0x1438bba50 (0x285e6b480:0) [2x1x1x32] 0.820801 0.756836 0.814941 ..
CCV_NNC_SWISH_FORWARD [1487]: [1] -> [1] (0)
|-> 1. 0x1438bb970 (0x285da5940:0) [2x64x64x320] 0.074646 0.325195 0.425781 ..
|<- 1. 0x1438bb970 (0x285da5940:0) [2x64x64x320] 0.038727 0.188843 0.257568 ..
CCV_NNC_CONVOLUTION_FORWARD [1488]: [3] -> [1] (0)
|-> 1. 0x1438bb970 (0x285da5940:0) [2x64x64x320] 0.038727 0.188843 0.257568 ..
|-> 2. 0x1438cffd0 (0x285d9dac0:0) [320x320x3x3] -0.063843 0.050476 0.026642 ..
|-> 3. 0x1438d0040 (0x285d9db00:0) [320] -0.010399 0.022095 0.006435 ..
|<- 1. 0x1438bbac0 (0x285da56c0:0) [2x64x64x320] 0.234375 -0.245728 0.107788 ..
CCV_NNC_CONVOLUTION_FORWARD [1489]: [3] -> [1] (1)
Wait: (1, 155)
|-> 1. 0x1438bb6d0 (0x285f78ac0:0) [2x64x64x640] -0.562988 0.855469 0.038818 ..
|-> 2. 0x1438d00b0 (0x285d9db40:0) [320x640x1x1] -0.010422 ..
|-> 3. 0x1438d0120 (0x285d9db80:0) [320] 0.002766 0.012024 0.005032 ..
|<- 1. 0x1438bbb30 (0x285da5a80:0) [2x64x64x320] 0.437500 0.459473 -0.276855 ..
Emit: (1, 156)
CCV_NNC_ADD_FORWARD [1490]: [2] -> [1] (0)
Wait: (0, 156)
|-> 1. 0x1438bbb30 (0x285da5a80:0) [2x64x64x320] 0.437500 0.459473 -0.276855 ..
|-> 2. 0x1438bbac0 (0x285da56c0:0) [2x64x64x320] 0.234375 -0.245728 0.107788 ..
|<- 1. 0x1438bbb30 (0x285da5a80:0) [2x64x64x320] 0.671875 0.213745 -0.169067 ..
CCV_NNC_GROUP_NORM_FORWARD [1491]: [3] -> [3] (0)
|-> 1. 0x1438bbb30 (0x285da5a80:0) [2x64x64x320] 0.671875 0.213745 -0.169067 ..
|-> 2. 0x1438d0190 (0x285d9dbc0:0) [1x1x1x320] 0.544922 0.628418 0.439941 ..
|-> 3. 0x1438d0200 (0x285d9dc00:0) [1x1x1x320] 0.044312 -0.046997 0.011879 ..
|<- 1. 0x1438bbba0 (0x285da5940:0) [2x64x64x320] 0.458740 0.294678 0.171387 ..
|<- 2. 0x1438bbc10 (0x285da5740:0) [2x1x1x32] -0.935059 -2.093750 -1.262695 ..
|<- 3. 0x1438bbc80 (0x285da5700:0) [2x1x1x32] 0.473389 0.402100 0.434814 ..
CCV_NNC_CONVOLUTION_FORWARD [1492]: [3] -> [1] (0)
|-> 1. 0x1438bbba0 (0x285da5940:0) [2x64x64x320] 0.458740 0.294678 0.171387 ..
|-> 2. 0x1438d0270 (0x285d9dc40:0) [320x320x1x1] 0.044617 ..
|-> 3. 0x1438d02e0 (0x285d9dc80:0) [320] 0.010094 -0.008141 0.044525 ..
|<- 1. 0x1438bbcf0 (0x285da56c0:0) [2x64x64x320] 0.101257 0.121521 -0.043365 ..
CCV_NNC_LAYER_NORM_FORWARD [1493]: [3] -> [3] (0)
|-> 1. 0x14390dc90 (0x285da56c0:0) [2x4096x320] 0.101257 0.121521 -0.043365 ..
|-> 2. 0x1438d0350 (0x285d9dcc0:0) [1x1x320] 0.546387 0.779785 0.564941 ..
|-> 3. 0x1438d03c0 (0x285d9dd00:0) [1x1x320] 0.120911 0.073181 -0.085449 ..
|<- 1. 0x1438bbd60 (0x285da5680:0) [2x4096x320] 0.210571 0.253662 -0.264648 ..
|<- 2. 0x1438bbdd0 (0x285da5d00:0) [2x4096x1] 0.051941 ..
|<- 3. 0x1438bbe40 (0x285da5cc0:0) [2x4096x1] 3.328125 ..
Emit: (0, 157)
CCV_NNC_GEMM_FORWARD [1494]: [2] -> [1] (0)
|-> 1. 0x1438bbd60 (0x285da5680:0) [2x4096x320] 0.210571 0.253662 -0.264648 ..
|-> 2. 0x1438d0430 (0x285d9dd40:0) [320x320] -0.133423 -0.037476 0.125732 ..
|<- 1. 0x1438bbeb0 (0x285da5900:0) [2x4096x320] 0.474365 1.914062 -0.207642 ..
CCV_NNC_SCALAR_MUL_FORWARD [1495]: [1] -> [1] (0)
|-> 1. 0x1438bbeb0 (0x285da5900:0) [2x4096x320] 0.474365 1.914062 -0.207642 ..
|<- 1. 0x1438bbeb0 (0x285da5900:0) [2x4096x320] 0.075012 0.302490 -0.032837 ..
CCV_NNC_TRANSPOSE_FORWARD [1496]: [1] -> [1] (0)
|-> 1. 0x14390dd70 (0x285da5900:0) [2x4096x8x40] 0.075012 0.302490 -0.032837 ..
|<- 1. 0x1438bc000 (0x285da59c0:0) [2x8x4096x40] 0.075012 0.302490 -0.032837 ..
CCV_NNC_GEMM_FORWARD [1497]: [2] -> [1] (1)
Wait: (1, 157)
|-> 1. 0x1438bbd60 (0x285da5680:0) [2x4096x320] 0.210571 0.253662 -0.264648 ..
|-> 2. 0x1438d04a0 (0x285d9dd80:0) [320x320] -0.221436 -0.070740 0.112061 ..
|<- 1. 0x1438bbf20 (0x285da5940:0) [2x4096x320] 1.587891 3.517578 -2.062500 ..
CCV_NNC_TRANSPOSE_FORWARD [1498]: [1] -> [1] (1)
|-> 1. 0x14390dd00 (0x285da5940:0) [2x4096x8x40] 1.587891 3.517578 -2.062500 ..
|<- 1. 0x1438bbf90 (0x285da5980:0) [2x8x4096x40] 1.587891 3.517578 -2.062500 ..
Emit: (1, 158)
CCV_NNC_GEMM_FORWARD [1499]: [2] -> [1] (2)
Wait: (2, 157)
|-> 1. 0x1438bbd60 (0x285da5680:0) [2x4096x320] 0.210571 0.253662 -0.264648 ..
|-> 2. 0x1438d0510 (0x285d9ddc0:0) [320x320] 0.039948 0.039490 0.065857 ..
|<- 1. 0x1438bc070 (0x285f658c0:0) [2x4096x320] -0.410400 0.139282 0.224121 ..
CCV_NNC_TRANSPOSE_FORWARD [1500]: [1] -> [1] (2)
|-> 1. 0x14390dec0 (0x285f658c0:0) [2x4096x8x40] -0.410400 0.139282 0.224121 ..
|<- 1. 0x1438bc150 (0x285f6d340:0) [2x8x4096x40] -0.410400 0.139282 0.224121 ..
Emit: (2, 159)
CCV_NNC_GEMM_FORWARD [1501]: [2] -> [1] (0)
Wait: (0, 158)
|-> 1. 0x14390de50 (0x285da59c0:0) [1x4096x40] 0.075012 0.302490 -0.032837 ..
|-> 2. 0x14390dde0 (0x285da5980:0) [1x4096x40] 1.587891 3.517578 -2.062500 ..
|<- 1. 0x1438bc0e0 (0x285da5a40:0) [1x4096x4096] 13.304688 12.656250 12.304688 ..
CCV_NNC_SOFTMAX_FORWARD [1502]: [1] -> [1] (0)
|-> 1. 0x14390df30 (0x285da5a40:0) [4096x4096] 13.304688 12.656250 12.304688 ..
|<- 1. 0x14390df30 (0x285da5a40:0) [4096x4096] 0.002821 0.001474 0.001038 ..
CCV_NNC_GEMM_FORWARD [1503]: [2] -> [1] (0)
Wait: (0, 159)
|-> 1. 0x14390e010 (0x285da5a40:0) [1x4096x4096] 0.002821 0.001474 0.001038 ..
|-> 2. 0x14390dfa0 (0x285f6d340:0) [1x4096x40] -0.410400 0.139282 0.224121 ..
|<- 1. 0x143910c90 (0x285da5680:0) [1x4096x40] 0.014565 -0.032043 -0.056061 ..
CCV_NNC_GEMM_FORWARD [1504]: [2] -> [1] (0)
|-> 1. 0x14390e130 (0x285da59c0:0) [1x4096x40] 0.073303 -0.375244 -0.231567 ..
|-> 2. 0x14390e080 (0x285da5980:0) [1x4096x40] 0.216064 -3.785156 -2.847656 ..
|<- 1. 0x1438bc1c0 (0x285da5a40:0) [1x4096x4096] 15.796875 15.867188 15.117188 ..
CCV_NNC_SOFTMAX_FORWARD [1505]: [1] -> [1] (0)
|-> 1. 0x14390e1e0 (0x285da5a40:0) [4096x4096] 15.796875 15.867188 15.117188 ..
|<- 1. 0x14390e1e0 (0x285da5a40:0) [4096x4096] 0.003546 0.003803 0.001797 ..
CCV_NNC_GEMM_FORWARD [1506]: [2] -> [1] (0)
|-> 1. 0x14390e300 (0x285da5a40:0) [1x4096x4096] 0.003546 0.003803 0.001797 ..
|-> 2. 0x14390e250 (0x285f6d340:0) [1x4096x40] 0.057251 -0.523926 -0.039368 ..
|<- 1. 0x143910d00 (0x285da5680:0) [1x4096x40] 0.074158 -0.196289 -0.095703 ..
CCV_NNC_GEMM_FORWARD [1507]: [2] -> [1] (0)
|-> 1. 0x14390e420 (0x285da59c0:0) [1x4096x40] 0.036377 0.070068 -0.075500 ..
|-> 2. 0x14390e370 (0x285da5980:0) [1x4096x40] 0.115234 0.381104 -2.968750 ..
|<- 1. 0x1438bc230 (0x285da5a40:0) [1x4096x4096] 10.953125 10.023438 9.945312 ..
CCV_NNC_SOFTMAX_FORWARD [1508]: [1] -> [1] (0)
|-> 1. 0x14390e4d0 (0x285da5a40:0) [4096x4096] 10.953125 10.023438 9.945312 ..
|<- 1. 0x14390e4d0 (0x285da5a40:0) [4096x4096] 0.016708 0.006596 0.006100 ..
CCV_NNC_GEMM_FORWARD [1509]: [2] -> [1] (0)
|-> 1. 0x14390e5f0 (0x285da5a40:0) [1x4096x4096] 0.016708 0.006596 0.006100 ..
|-> 2. 0x14390e540 (0x285f6d340:0) [1x4096x40] -0.450928 0.094421 -0.409180 ..
|<- 1. 0x143910db0 (0x285da5680:0) [1x4096x40] -0.052734 0.083374 -0.024231 ..
CCV_NNC_GEMM_FORWARD [1510]: [2] -> [1] (0)
|-> 1. 0x14390e710 (0x285da59c0:0) [1x4096x40] -0.040100 0.101013 0.049103 ..
|-> 2. 0x14390e660 (0x285da5980:0) [1x4096x40] -0.525391 0.914551 2.027344 ..
|<- 1. 0x1438bc2a0 (0x285da5a40:0) [1x4096x4096] 7.718750 7.164062 6.792969 ..
CCV_NNC_SOFTMAX_FORWARD [1511]: [1] -> [1] (0)
|-> 1. 0x14390e7c0 (0x285da5a40:0) [4096x4096] 7.718750 7.164062 6.792969 ..
|<- 1. 0x14390e7c0 (0x285da5a40:0) [4096x4096] 0.001666 0.000957 0.000660 ..
CCV_NNC_GEMM_FORWARD [1512]: [2] -> [1] (0)
|-> 1. 0x14390e8e0 (0x285da5a40:0) [1x4096x4096] 0.001666 0.000957 0.000660 ..
|-> 2. 0x14390e830 (0x285f6d340:0) [1x4096x40] 0.729492 -0.497070 0.112183 ..
|<- 1. 0x143910e60 (0x285da5680:0) [1x4096x40] -0.020248 -0.126709 0.016861 ..
CCV_NNC_GEMM_FORWARD [1513]: [2] -> [1] (0)
|-> 1. 0x14390ea00 (0x285da59c0:0) [1x4096x40] -0.145264 0.027298 0.154175 ..
|-> 2. 0x14390e950 (0x285da5980:0) [1x4096x40] -0.714355 0.052582 1.906250 ..
|<- 1. 0x1438bc310 (0x285da5a40:0) [1x4096x4096] 3.669922 3.679688 3.212891 ..
CCV_NNC_SOFTMAX_FORWARD [1514]: [1] -> [1] (0)
|-> 1. 0x14390eab0 (0x285da5a40:0) [4096x4096] 3.669922 3.679688 3.212891 ..
|<- 1. 0x14390eab0 (0x285da5a40:0) [4096x4096] 0.001215 0.001227 0.000770 ..
CCV_NNC_GEMM_FORWARD [1515]: [2] -> [1] (0)
|-> 1. 0x14390ebd0 (0x285da5a40:0) [1x4096x4096] 0.001215 0.001227 0.000770 ..
|-> 2. 0x14390eb20 (0x285f6d340:0) [1x4096x40] 0.615234 -0.522949 0.786133 ..
|<- 1. 0x143910f10 (0x285da5680:0) [1x4096x40] 0.058929 -0.234497 0.027527 ..
CCV_NNC_GEMM_FORWARD [1516]: [2] -> [1] (0)
|-> 1. 0x14390ecf0 (0x285da59c0:0) [1x4096x40] -0.141479 -0.198364 -0.058197 ..
|-> 2. 0x14390ec40 (0x285da5980:0) [1x4096x40] -0.486084 -1.357422 -0.666992 ..
|<- 1. 0x1438bc380 (0x285da5a40:0) [1x4096x4096] 12.367188 10.898438 10.265625 ..
CCV_NNC_SOFTMAX_FORWARD [1517]: [1] -> [1] (0)
|-> 1. 0x14390eda0 (0x285da5a40:0) [4096x4096] 12.367188 10.898438 10.265625 ..
|<- 1. 0x14390eda0 (0x285da5a40:0) [4096x4096] 0.009628 0.002216 0.001177 ..
CCV_NNC_GEMM_FORWARD [1518]: [2] -> [1] (0)
|-> 1. 0x14390eec0 (0x285da5a40:0) [1x4096x4096] 0.009628 0.002216 0.001177 ..
|-> 2. 0x14390ee10 (0x285f6d340:0) [1x4096x40] 0.043152 0.003998 -0.054565 ..
|<- 1. 0x143910fc0 (0x285da5680:0) [1x4096x40] -0.011017 0.001258 -0.053223 ..
CCV_NNC_GEMM_FORWARD [1519]: [2] -> [1] (0)
|-> 1. 0x14390efe0 (0x285da59c0:0) [1x4096x40] 0.316406 -0.018478 -0.227661 ..
|-> 2. 0x14390ef30 (0x285da5980:0) [1x4096x40] 2.085938 -0.916992 -3.335938 ..
|<- 1. 0x1438bc3f0 (0x285da5a40:0) [1x4096x4096] 17.062500 16.171875 15.828125 ..
CCV_NNC_SOFTMAX_FORWARD [1520]: [1] -> [1] (0)
|-> 1. 0x14390f090 (0x285da5a40:0) [4096x4096] 17.062500 16.171875 15.828125 ..
|<- 1. 0x14390f090 (0x285da5a40:0) [4096x4096] 0.010696 0.004391 0.003113 ..
CCV_NNC_GEMM_FORWARD [1521]: [2] -> [1] (0)
|-> 1. 0x14390f1b0 (0x285da5a40:0) [1x4096x4096] 0.010696 0.004391 0.003113 ..
|-> 2. 0x14390f100 (0x285f6d340:0) [1x4096x40] 0.336670 -0.176514 0.035461 ..
|<- 1. 0x143911070 (0x285da5680:0) [1x4096x40] -0.066467 -0.075928 0.016113 ..
CCV_NNC_GEMM_FORWARD [1522]: [2] -> [1] (0)
|-> 1. 0x14390f2d0 (0x285da59c0:0) [1x4096x40] 0.100403 0.143066 -0.197144 ..
|-> 2. 0x14390f220 (0x285da5980:0) [1x4096x40] 0.366699 1.572266 -1.167969 ..
|<- 1. 0x1438bc460 (0x285da5a40:0) [1x4096x4096] 8.234375 6.750000 7.378906 ..
CCV_NNC_SOFTMAX_FORWARD [1523]: [1] -> [1] (0)
|-> 1. 0x14390f380 (0x285da5a40:0) [4096x4096] 8.234375 6.750000 7.378906 ..
|<- 1. 0x14390f380 (0x285da5a40:0) [4096x4096] 0.004379 0.000993 0.001862 ..
CCV_NNC_GEMM_FORWARD [1524]: [2] -> [1] (0)
|-> 1. 0x14390f4a0 (0x285da5a40:0) [1x4096x4096] 0.004379 0.000993 0.001862 ..
|-> 2. 0x14390f3f0 (0x285f6d340:0) [1x4096x40] 0.254150 0.447754 0.177734 ..
|<- 1. 0x143911120 (0x285da5680:0) [1x4096x40] 0.020676 0.172119 0.010803 ..
CCV_NNC_GEMM_FORWARD [1525]: [2] -> [1] (0)
|-> 1. 0x14390f5c0 (0x285da59c0:0) [1x4096x40] 0.073730 0.350098 -0.051056 ..
|-> 2. 0x14390f510 (0x285da5980:0) [1x4096x40] 1.463867 4.253906 -2.408203 ..
|<- 1. 0x1438bc4d0 (0x285da5a40:0) [1x4096x4096] 13.039062 12.578125 12.320312 ..
CCV_NNC_SOFTMAX_FORWARD [1526]: [1] -> [1] (0)
|-> 1. 0x14390f670 (0x285da5a40:0) [4096x4096] 13.039062 12.578125 12.320312 ..
|<- 1. 0x14390f670 (0x285da5a40:0) [4096x4096] 0.001760 0.001110 0.000858 ..
CCV_NNC_GEMM_FORWARD [1527]: [2] -> [1] (0)
|-> 1. 0x14390f790 (0x285da5a40:0) [1x4096x4096] 0.001760 0.001110 0.000858 ..
|-> 2. 0x14390f6e0 (0x285f6d340:0) [1x4096x40] -0.367676 -0.033813 0.138794 ..
|<- 1. 0x1439111d0 (0x285da5680:0) [1x4096x40] 0.020889 -0.079285 -0.108093 ..
CCV_NNC_GEMM_FORWARD [1528]: [2] -> [1] (0)
|-> 1. 0x14390f8b0 (0x285da59c0:0) [1x4096x40] 0.073853 -0.346436 -0.193481 ..
|-> 2. 0x14390f800 (0x285da5980:0) [1x4096x40] 0.326660 -3.671875 -2.486328 ..
|<- 1. 0x1438bc540 (0x285da5a40:0) [1x4096x4096] 15.804688 16.078125 15.335938 ..
CCV_NNC_SOFTMAX_FORWARD [1529]: [1] -> [1] (0)
|-> 1. 0x14390f960 (0x285da5a40:0) [4096x4096] 15.804688 16.078125 15.335938 ..
|<- 1. 0x14390f960 (0x285da5a40:0) [4096x4096] 0.001839 0.002417 0.001151 ..
CCV_NNC_GEMM_FORWARD [1530]: [2] -> [1] (0)
|-> 1. 0x14390fa80 (0x285da5a40:0) [1x4096x4096] 0.001839 0.002417 0.001151 ..
|-> 2. 0x14390f9d0 (0x285f6d340:0) [1x4096x40] 0.152588 -0.344971 -0.054565 ..
|<- 1. 0x143911280 (0x285da5680:0) [1x4096x40] 0.078613 -0.163330 -0.108765 ..
CCV_NNC_GEMM_FORWARD [1531]: [2] -> [1] (0)
|-> 1. 0x14390fba0 (0x285da59c0:0) [1x4096x40] 0.027802 0.129761 -0.147339 ..
|-> 2. 0x14390faf0 (0x285da5980:0) [1x4096x40] 0.040680 0.741699 -3.396484 ..
|<- 1. 0x1438bc5b0 (0x285da5a40:0) [1x4096x4096] 10.718750 9.796875 9.796875 ..
CCV_NNC_SOFTMAX_FORWARD [1532]: [1] -> [1] (0)
|-> 1. 0x14390fc50 (0x285da5a40:0) [4096x4096] 10.718750 9.796875 9.796875 ..
|<- 1. 0x14390fc50 (0x285da5a40:0) [4096x4096] 0.009308 0.003704 0.003704 ..
CCV_NNC_GEMM_FORWARD [1533]: [2] -> [1] (0)
|-> 1. 0x14390fd70 (0x285da5a40:0) [1x4096x4096] 0.009308 0.003704 0.003704 ..
|-> 2. 0x14390fcc0 (0x285f6d340:0) [1x4096x40] -0.499268 0.182373 -0.402344 ..
|<- 1. 0x143911330 (0x285da5680:0) [1x4096x40] -0.034515 0.173096 -0.047089 ..
CCV_NNC_GEMM_FORWARD [1534]: [2] -> [1] (0)
|-> 1. 0x14390fe90 (0x285da59c0:0) [1x4096x40] -0.010681 0.090759 0.065247 ..
|-> 2. 0x14390fde0 (0x285da5980:0) [1x4096x40] -0.263428 0.887207 2.308594 ..
|<- 1. 0x1438bc620 (0x285da5a40:0) [1x4096x4096] 7.687500 7.386719 7.042969 ..
CCV_NNC_SOFTMAX_FORWARD [1535]: [1] -> [1] (0)
|-> 1. 0x14390ff40 (0x285da5a40:0) [4096x4096] 7.687500 7.386719 7.042969 ..
|<- 1. 0x14390ff40 (0x285da5a40:0) [4096x4096] 0.001120 0.000829 0.000587 ..
CCV_NNC_GEMM_FORWARD [1536]: [2] -> [1] (0)
|-> 1. 0x143910060 (0x285da5a40:0) [1x4096x4096] 0.001120 0.000829 0.000587 ..
|-> 2. 0x14390ffb0 (0x285f6d340:0) [1x4096x40] 0.577148 -0.546387 0.201782 ..
|<- 1. 0x1439113e0 (0x285da5680:0) [1x4096x40] -0.061859 -0.159790 0.132935 ..
CCV_NNC_GEMM_FORWARD [1537]: [2] -> [1] (0)
|-> 1. 0x143910180 (0x285da59c0:0) [1x4096x40] -0.140259 0.029617 0.164917 ..
|-> 2. 0x1439100d0 (0x285da5980:0) [1x4096x40] -0.562988 0.169312 2.080078 ..
|<- 1. 0x1438bc690 (0x285da5a40:0) [1x4096x4096] 3.753906 3.751953 3.302734 ..
CCV_NNC_SOFTMAX_FORWARD [1538]: [1] -> [1] (0)
|-> 1. 0x143910230 (0x285da5a40:0) [4096x4096] 3.753906 3.751953 3.302734 ..
|<- 1. 0x143910230 (0x285da5a40:0) [4096x4096] 0.000846 0.000844 0.000539 ..
CCV_NNC_GEMM_FORWARD [1539]: [2] -> [1] (0)
|-> 1. 0x143910350 (0x285da5a40:0) [1x4096x4096] 0.000846 0.000844 0.000539 ..
|-> 2. 0x1439102a0 (0x285f6d340:0) [1x4096x40] 0.550781 -0.262695 0.690430 ..
|<- 1. 0x143911490 (0x285da5680:0) [1x4096x40] -0.039856 -0.094177 -0.030167 ..
CCV_NNC_GEMM_FORWARD [1540]: [2] -> [1] (0)
|-> 1. 0x143910470 (0x285da59c0:0) [1x4096x40] -0.177856 -0.174438 -0.067322 ..
|-> 2. 0x1439103c0 (0x285da5980:0) [1x4096x40] -0.517090 -1.398438 -0.969727 ..
|<- 1. 0x1438bc700 (0x285da5a40:0) [1x4096x4096] 12.140625 11.015625 10.734375 ..
CCV_NNC_SOFTMAX_FORWARD [1541]: [1] -> [1] (0)
|-> 1. 0x143910520 (0x285da5a40:0) [4096x4096] 12.140625 11.015625 10.734375 ..
|<- 1. 0x143910520 (0x285da5a40:0) [4096x4096] 0.004230 0.001374 0.001038 ..
CCV_NNC_GEMM_FORWARD [1542]: [2] -> [1] (0)
|-> 1. 0x143910640 (0x285da5a40:0) [1x4096x4096] 0.004230 0.001374 0.001038 ..
|-> 2. 0x143910590 (0x285f6d340:0) [1x4096x40] 0.020096 -0.064209 -0.155518 ..
|<- 1. 0x143911540 (0x285da5680:0) [1x4096x40] -0.073730 -0.058319 -0.058624 ..
CCV_NNC_GEMM_FORWARD [1543]: [2] -> [1] (0)
|-> 1. 0x143910760 (0x285da59c0:0) [1x4096x40] 0.281494 -0.023331 -0.281738 ..
|-> 2. 0x1439106b0 (0x285da5980:0) [1x4096x40] 2.035156 -0.937012 -3.859375 ..
|<- 1. 0x1438bc770 (0x285da5a40:0) [1x4096x4096] 16.140625 15.359375 15.140625 ..
CCV_NNC_SOFTMAX_FORWARD [1544]: [1] -> [1] (0)
|-> 1. 0x143910810 (0x285da5a40:0) [4096x4096] 16.140625 15.359375 15.140625 ..
|<- 1. 0x143910810 (0x285da5a40:0) [4096x4096] 0.004459 0.002043 0.001640 ..
CCV_NNC_GEMM_FORWARD [1545]: [2] -> [1] (0)
|-> 1. 0x143910930 (0x285da5a40:0) [1x4096x4096] 0.004459 0.002043 0.001640 ..
|-> 2. 0x143910880 (0x285f6d340:0) [1x4096x40] 0.231323 -0.122314 0.057495 ..
|<- 1. 0x1439115f0 (0x285da5680:0) [1x4096x40] -0.059784 -0.031403 0.006596 ..
CCV_NNC_GEMM_FORWARD [1546]: [2] -> [1] (0)
|-> 1. 0x143910a50 (0x285da59c0:0) [1x4096x40] 0.098022 0.112366 -0.198975 ..
|-> 2. 0x1439109a0 (0x285da5980:0) [1x4096x40] 0.451172 1.490234 -1.266602 ..
|<- 1. 0x1438bc7e0 (0x285da5a40:0) [1x4096x4096] 8.078125 7.000000 7.562500 ..
CCV_NNC_SOFTMAX_FORWARD [1547]: [1] -> [1] (0)
|-> 1. 0x143910b00 (0x285da5a40:0) [4096x4096] 8.078125 7.000000 7.562500 ..
|<- 1. 0x143910b00 (0x285da5a40:0) [4096x4096] 0.002388 0.000813 0.001426 ..
CCV_NNC_GEMM_FORWARD [1548]: [2] -> [1] (0)
|-> 1. 0x143910c20 (0x285da5a40:0) [1x4096x4096] 0.002388 0.000813 0.001426 ..
|-> 2. 0x143910b70 (0x285f6d340:0) [1x4096x40] 0.256836 0.457275 0.091003 ..
|<- 1. 0x1439116a0 (0x285da5680:0) [1x4096x40] 0.075378 0.195312 -0.004940 ..
CCV_NNC_TRANSPOSE_FORWARD [1549]: [1] -> [1] (0)
|-> 1. 0x143911750 (0x285da5680:0) [2x8x4096x40] 0.014565 -0.032043 -0.056061 ..
|<- 1. 0x1438bc8c0 (0x285da5940:0) [2x4096x8x40] 0.014565 -0.032043 -0.056061 ..
CCV_NNC_GEMM_FORWARD [1550]: [3] -> [1] (0)
|-> 1. 0x1439117c0 (0x285da5940:0) [2x4096x320] 0.014565 -0.032043 -0.056061 ..
|-> 2. 0x1438d0580 (0x285d9de00:0) [320x320] -0.036713 0.011360 -0.035004 ..
|-> 3. 0x1438d05f0 (0x285d9de40:0) [320] -0.039581 -0.020538 0.034393 ..
|<- 1. 0x1438bc930 (0x285da5680:0) [2x4096x320] -0.155762 0.089050 0.000238 ..
CCV_NNC_ADD_FORWARD [1551]: [2] -> [1] (0)
|-> 1. 0x1438bc930 (0x285da5680:0) [2x4096x320] -0.155762 0.089050 0.000238 ..
|-> 2. 0x14390dc90 (0x285da56c0:0) [2x4096x320] 0.101257 0.121521 -0.043365 ..
|<- 1. 0x1438bc930 (0x285da5680:0) [2x4096x320] -0.054504 0.210571 -0.043121 ..
CCV_NNC_LAYER_NORM_FORWARD [1552]: [3] -> [3] (0)
|-> 1. 0x1438bc930 (0x285da5680:0) [2x4096x320] -0.054504 0.210571 -0.043121 ..
|-> 2. 0x1438d0660 (0x285d9de80:0) [1x1x320] 0.322754 0.343994 0.381836 ..
|-> 3. 0x1438d06d0 (0x285d9dec0:0) [1x1x320] 0.033569 -0.047516 0.016083 ..
|<- 1. 0x1438bc9a0 (0x285da5940:0) [2x4096x320] -0.073486 0.112122 -0.097473 ..
|<- 2. 0x1438bca10 (0x285da5b00:0) [2x4096x1] 0.055969 ..
|<- 3. 0x1438bca80 (0x285da5b40:0) [2x4096x1] 3.001953 ..
CCV_NNC_GEMM_FORWARD [1553]: [2] -> [1] (0)
|-> 1. 0x1438bc9a0 (0x285da5940:0) [2x4096x320] -0.073486 0.112122 -0.097473 ..
|-> 2. 0x1438d0740 (0x285d9df00:0) [320x320] 0.015457 -0.008194 0.033844 ..
|<- 1. 0x1438bcaf0 (0x285da5900:0) [2x4096x320] -0.113159 0.283936 -0.128052 ..
CCV_NNC_SCALAR_MUL_FORWARD [1554]: [1] -> [1] (0)
|-> 1. 0x1438bcaf0 (0x285da5900:0) [2x4096x320] -0.113159 0.283936 -0.128052 ..
|<- 1. 0x1438bcaf0 (0x285da5900:0) [2x4096x320] -0.017883 0.044891 -0.020248 ..
CCV_NNC_TRANSPOSE_FORWARD [1555]: [1] -> [1] (0)
|-> 1. 0x1439118a0 (0x285da5900:0) [2x4096x8x40] -0.017883 0.044891 -0.020248 ..
|<- 1. 0x1438bcc40 (0x285da56c0:0) [2x8x4096x40] -0.017883 0.044891 -0.020248 ..
CCV_NNC_GEMM_FORWARD [1556]: [2] -> [1] (0)
Wait: (0, 160)
|-> 1. 0x1438bcc40 (0x285da56c0:0) [2x8x4096x40] -0.017883 0.044891 -0.020248 ..
|-> 2. 0x1438bcbd0 (0x285f6d400:0) [2x8x133x40] 0.226440 -0.880859 -0.376221 ..
|<- 1. 0x1438bccb0 (0x285da5c00:0) [2x8x4096x133] 4.042969 0.310059 -0.188599 ..
CCV_NNC_SOFTMAX_FORWARD [1557]: [1] -> [1] (0)
|-> 1. 0x143911910 (0x285da5c00:0) [65536x133] 4.042969 0.310059 -0.188599 ..
|<- 1. 0x143911910 (0x285da5c00:0) [65536x133] 0.507812 0.012154 0.007378 ..
CCV_NNC_GEMM_FORWARD [1558]: [2] -> [1] (0)
Wait: (0, 161)
|-> 1. 0x1439119f0 (0x285da5c00:0) [2x8x4096x133] 0.507812 0.012154 0.007378 ..
|-> 2. 0x1438bcd90 (0x285da6ec0:0) [2x8x133x40] -0.004234 0.009697 0.024551 ..
|<- 1. 0x1438bce00 (0x285da56c0:0) [2x8x4096x40] -0.067078 -0.248535 -0.083862 ..
CCV_NNC_TRANSPOSE_FORWARD [1559]: [1] -> [1] (0)
|-> 1. 0x143911a60 (0x285da56c0:0) [2x8x4096x40] -0.067078 -0.248535 -0.083862 ..
|<- 1. 0x1438bce70 (0x285da5940:0) [2x4096x8x40] -0.067078 -0.248535 -0.083862 ..
CCV_NNC_GEMM_FORWARD [1560]: [3] -> [1] (0)
|-> 1. 0x143911ad0 (0x285da5940:0) [2x4096x320] -0.067078 -0.248535 -0.083862 ..
|-> 2. 0x1438d0890 (0x285d9dfc0:0) [320x320] -0.008354 0.008049 0.005302 ..
|-> 3. 0x1438d0900 (0x285d9e000:0) [320] -0.005112 0.018448 -0.011581 ..
|<- 1. 0x1438bcee0 (0x285f6d340:0) [2x4096x320] 0.014107 -0.007706 -0.002991 ..
CCV_NNC_ADD_FORWARD [1561]: [2] -> [1] (0)
|-> 1. 0x1438bcee0 (0x285f6d340:0) [2x4096x320] 0.014107 -0.007706 -0.002991 ..
|-> 2. 0x1438bc930 (0x285da5680:0) [2x4096x320] -0.054504 0.210571 -0.043121 ..
|<- 1. 0x1438bcee0 (0x285f6d340:0) [2x4096x320] -0.040405 0.202881 -0.046112 ..
CCV_NNC_LAYER_NORM_FORWARD [1562]: [3] -> [3] (0)
|-> 1. 0x1438bcee0 (0x285f6d340:0) [2x4096x320] -0.040405 0.202881 -0.046112 ..
|-> 2. 0x1438d0970 (0x285d9e040:0) [1x1x320] 0.592773 0.669434 0.659180 ..
|-> 3. 0x1438d09e0 (0x285d9e080:0) [1x1x320] 0.072693 -0.046417 0.035919 ..
|<- 1. 0x1438bcf50 (0x285da5ac0:0) [2x4096x320] -0.103638 0.270020 -0.172119 ..
|<- 2. 0x1438bcfc0 (0x285da6080:0) [2x4096x1] 0.053558 ..
|<- 3. 0x1438bd030 (0x285da6040:0) [2x4096x1] 3.166016 ..
Emit: (0, 162)
CCV_NNC_GEMM_FORWARD [1563]: [3] -> [1] (0)
|-> 1. 0x1438bcf50 (0x285da5ac0:0) [2x4096x320] -0.103638 0.270020 -0.172119 ..
|-> 2. 0x1438d0a50 (0x285d9e0c0:0) [1280x320] 0.008713 0.129395 0.108459 ..
|-> 3. 0x1438d0ac0 (0x285d9e100:0) [1280] 0.025085 -0.045135 0.039398 ..
|<- 1. 0x1438bd0a0 (0x285da5d40:0) [2x4096x1280] -0.195190 -0.578125 -0.047485 ..
CCV_NNC_GELU_FORWARD [1564]: [1] -> [1] (0)
|-> 1. 0x1438bd0a0 (0x285da5d40:0) [2x4096x1280] -0.195190 -0.578125 -0.047485 ..
|<- 1. 0x1438bd0a0 (0x285da5d40:0) [2x4096x1280] -0.082520 -0.162842 -0.022842 ..
CCV_NNC_GEMM_FORWARD [1565]: [3] -> [1] (1)
Wait: (1, 162)
|-> 1. 0x1438bcf50 (0x285da5ac0:0) [2x4096x320] -0.103638 0.270020 -0.172119 ..
|-> 2. 0x1438d0b30 (0x285d9e140:0) [1280x320] -0.097290 -0.045166 -0.010414 ..
|-> 3. 0x1438d0ba0 (0x285d9e180:0) [1280] 0.030746 -0.038635 -0.005798 ..
|<- 1. 0x1438bd110 (0x285da5d80:0) [2x4096x1280] -0.293457 -0.233398 0.446777 ..
Emit: (1, 163)
CCV_NNC_MUL_FORWARD [1566]: [2] -> [1] (0)
Wait: (0, 163)
|-> 1. 0x1438bd110 (0x285da5d80:0) [2x4096x1280] -0.293457 -0.233398 0.446777 ..
|-> 2. 0x1438bd0a0 (0x285da5d40:0) [2x4096x1280] -0.082520 -0.162842 -0.022842 ..
|<- 1. 0x1438bd110 (0x285da5d80:0) [2x4096x1280] 0.024216 0.037994 -0.010208 ..
CCV_NNC_GEMM_FORWARD [1567]: [3] -> [1] (0)
|-> 1. 0x1438bd110 (0x285da5d80:0) [2x4096x1280] 0.024216 0.037994 -0.010208 ..
|-> 2. 0x1438d0c10 (0x285d9e1c0:0) [320x1280] 0.014885 0.043793 -0.168457 ..
|-> 3. 0x1438d0c80 (0x285d9e200:0) [320] -0.006794 -0.044647 0.048462 ..
|<- 1. 0x1438bd180 (0x285da56c0:0) [2x4096x320] 0.440674 0.840820 -0.444092 ..
CCV_NNC_ADD_FORWARD [1568]: [2] -> [1] (0)
|-> 1. 0x1438bd180 (0x285da56c0:0) [2x4096x320] 0.440674 0.840820 -0.444092 ..
|-> 2. 0x1438bcee0 (0x285f6d340:0) [2x4096x320] -0.040405 0.202881 -0.046112 ..
|<- 1. 0x1438bd180 (0x285da56c0:0) [2x4096x320] 0.400391 1.043945 -0.490234 ..
CCV_NNC_CONVOLUTION_FORWARD [1569]: [3] -> [1] (0)
|-> 1. 0x143911b40 (0x285da56c0:0) [2x64x64x320] 0.400391 1.043945 -0.490234 ..
|-> 2. 0x1438d0cf0 (0x285d9e240:0) [320x320x1x1] -0.049561 ..
|-> 3. 0x1438d0d60 (0x285d9e280:0) [320] 0.078247 -0.009094 -0.025848 ..
|<- 1. 0x1438bd1f0 (0x285f6d340:0) [2x64x64x320] 1.304688 -0.415527 0.661621 ..
CCV_NNC_ADD_FORWARD [1570]: [2] -> [1] (0)
|-> 1. 0x1438bd1f0 (0x285f6d340:0) [2x64x64x320] 1.304688 -0.415527 0.661621 ..
|-> 2. 0x1438bbb30 (0x285da5a80:0) [2x64x64x320] 0.671875 0.213745 -0.169067 ..
|<- 1. 0x1438bd1f0 (0x285f6d340:0) [2x64x64x320] 1.976562 -0.201782 0.492676 ..
CCV_NNC_GROUP_NORM_FORWARD [1571]: [3] -> [3] (0)
|-> 1. 0x1438bd1f0 (0x285f6d340:0) [2x64x64x320] 1.976562 -0.201782 0.492676 ..
|-> 2. 0x1438d0dd0 (0x285d9e2c0:0) [1x1x1x320] 0.281738 0.262451 0.284912 ..
|-> 3. 0x1438d0e40 (0x285d9e300:0) [1x1x1x320] -0.032379 -0.048981 -0.016617 ..
|<- 1. 0x1438bd260 (0x285da5a80:0) [2x64x64x320] 0.294189 0.042389 0.156250 ..
|<- 2. 0x1438bd2d0 (0x285da5700:0) [2x1x1x32] -1.136719 -2.496094 -1.416016 ..
|<- 3. 0x1438bd340 (0x285da5740:0) [2x1x1x32] 0.372314 0.236938 0.305420 ..
CCV_NNC_SWISH_FORWARD [1572]: [1] -> [1] (0)
|-> 1. 0x1438bd260 (0x285da5a80:0) [2x64x64x320] 0.294189 0.042389 0.156250 ..
|<- 1. 0x1438bd260 (0x285da5a80:0) [2x64x64x320] 0.168579 0.021637 0.084229 ..
CCV_NNC_CONVOLUTION_FORWARD [1573]: [3] -> [1] (0)
|-> 1. 0x1438bd260 (0x285da5a80:0) [2x64x64x320] 0.168579 0.021637 0.084229 ..
|-> 2. 0x1438d0eb0 (0x285d9e340:0) [4x320x3x3] -0.020233 0.010170 0.011658 ..
|-> 3. 0x1438d0f20 (0x285d9e380:0) [4] -0.001718 -0.001582 0.000219 ..
|<- 1. 0x1438bd500 (0x28148e640:0) [2x64x64x4] 1.330078 0.557617 0.386230 ..
Graph Stream 0 End
|<- 1. 0x282ac2450 (0x28148e640:0) [2x64x64x4] 1.330078 0.557617 0.386230 ..
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment