Created
February 4, 2024 08:35
-
-
Save alex4o/7809ed6597cb88c4f44fcbab03475d9e to your computer and use it in GitHub Desktop.
llama.cpp pixel6pro vulkan logs
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
./main -m ../phi-2-orange.Q4_K_M.gguf | |
Log start | |
main: build = 22 (277fad3) | |
main: built with clang version 17.0.6 for aarch64-unknown-linux-android24 | |
main: seed = 1707035493 | |
ggml_vk_init() | |
ggml_vk_find_queue_family_index() | |
ggml_vk_find_queue_family_index() | |
ggml_vulkan: Using Mali-G78 | uma: 1 | fp16: 1 | warp size: 16 | |
ggml_vk_load_shaders() | |
ggml_vk_create_pipeline(matmul_f32_l, main, 3, 56, (128,128,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(matmul_f32_m, main, 3, 56, (64,64,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(matmul_f32_s, main, 3, 56, (32,32,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(matmul_f32_aligned_l, main, 3, 56, (128,128,1), specialization_constants, 128) | |
ggml_vk_create_pipeline(matmul_f32_aligned_m, main, 3, 56, (64,64,1), specialization_constants, 64) | |
ggml_vk_create_pipeline(matmul_f32_aligned_s, main, 3, 56, (32,32,1), specialization_constants, 32) | |
ggml_vk_create_pipeline(matmul_f16_l, main, 3, 56, (128,128,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(matmul_f16_m, main, 3, 56, (64,64,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(matmul_f16_s, main, 3, 56, (32,32,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(matmul_f16_aligned_l, main, 3, 56, (128,128,1), specialization_constants, 128) | |
ggml_vk_create_pipeline(matmul_f16_aligned_m, main, 3, 56, (64,64,1), specialization_constants, 64) | |
ggml_vk_create_pipeline(matmul_f16_aligned_s, main, 3, 56, (32,32,1), specialization_constants, 32) | |
ggml_vk_create_pipeline(matmul_f16_f32_l, main, 3, 56, (128,128,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(matmul_f16_f32_m, main, 3, 56, (64,64,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(matmul_f16_f32_s, main, 3, 56, (32,32,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(matmul_f16_f32_aligned_l, main, 3, 56, (128,128,1), specialization_constants, 128) | |
ggml_vk_create_pipeline(matmul_f16_f32_aligned_m, main, 3, 56, (64,64,1), specialization_constants, 64) | |
ggml_vk_create_pipeline(matmul_f16_f32_aligned_s, main, 3, 56, (32,32,1), specialization_constants, 32) | |
ggml_vk_create_pipeline(mul_mat_vec_f16_f32, main, 3, 12, (1,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(mul_mat_vec_q4_0_f32, main, 3, 12, (1,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(mul_mat_vec_q4_1_f32, main, 3, 12, (1,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(mul_mat_vec_q5_0_f32, main, 3, 12, (1,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(mul_mat_vec_q5_1_f32, main, 3, 12, (1,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(mul_mat_vec_q8_0_f32, main, 3, 12, (1,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(mul_mat_vec_q2_K_f32, main, 3, 12, (1,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(mul_mat_vec_q3_K_f32, main, 3, 12, (1,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(mul_mat_vec_q4_K_f32, main, 3, 12, (1,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(mul_mat_vec_q5_K_f32, main, 3, 12, (1,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(mul_mat_vec_q6_K_f32, main, 3, 12, (1,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(f32_to_f16, main, 2, 16, (64,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(dequant_f16, main, 2, 16, (8192,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(dequant_q4_0, main, 2, 16, (8192,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(dequant_q4_1, main, 2, 16, (8192,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(dequant_q5_0, main, 2, 16, (8192,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(dequant_q5_1, main, 2, 16, (8192,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(dequant_q8_0, main, 2, 16, (8192,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(dequant_q2_K, main, 2, 16, (16384,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(dequant_q3_K, main, 2, 16, (16384,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(dequant_q4_K, main, 2, 16, (8192,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(dequant_q5_K, main, 2, 16, (16384,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(dequant_q6_K, main, 2, 16, (16384,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(get_rows_f16, main, 3, 16, (512,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(get_rows_q4_0, main, 3, 16, (512,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(get_rows_q4_1, main, 3, 16, (512,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(get_rows_q5_0, main, 3, 16, (512,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(get_rows_q5_1, main, 3, 16, (512,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(get_rows_q8_0, main, 3, 16, (512,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(get_rows_f16_f32, main, 3, 16, (512,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(get_rows_q4_0_f32, main, 3, 16, (512,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(get_rows_q4_1_f32, main, 3, 16, (512,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(get_rows_q5_0_f32, main, 3, 16, (512,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(get_rows_q5_1_f32, main, 3, 16, (512,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(get_rows_q8_0_f32, main, 3, 16, (512,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(split_k_reduce, main, 2, 8, (256,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(mul_mat_vec_p021_f16_f32, main, 3, 24, (1,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(mul_mat_vec_nc_f16_f32, main, 3, 28, (1,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(norm_f32, main, 2, 16, (1,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(rms_norm_f32, main, 2, 16, (1,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(cpy_f32_f32, main, 2, 48, (512,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(cpy_f32_f16, main, 2, 48, (512,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(cpy_f16_f16, main, 2, 48, (512,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(add_f32, main, 3, 16, (512,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(mul_f32, main, 3, 16, (512,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(scale_f32, main, 2, 16, (512,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(sqr_f32, main, 2, 16, (512,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(clamp_f32, main, 2, 16, (512,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(gelu_f32, main, 2, 16, (512,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(silu_f32, main, 2, 16, (512,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(relu_f32, main, 2, 16, (512,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(diag_mask_inf_f32, main, 2, 12, (512,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(soft_max_f32, main, 3, 16, (1,1,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(rope_f32, main, 3, 40, (1,512,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(rope_f16, main, 3, 40, (1,512,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(rope_neox_f32, main, 3, 52, (1,512,1), specialization_constants, 1) | |
ggml_vk_create_pipeline(rope_neox_f16, main, 3, 52, (1,512,1), specialization_constants, 1) | |
ggml_vk_create_queue() | |
ggml_vk_create_queue() | |
llama_model_loader: loaded meta data with 21 key-value pairs and 325 tensors from ../phi-2-orange.Q4_K_M.gguf (version GGUF V3 (latest)) | |
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. | |
llama_model_loader: - kv 0: general.architecture str = phi2 | |
llama_model_loader: - kv 1: general.name str = Phi2 | |
llama_model_loader: - kv 2: phi2.context_length u32 = 2048 | |
llama_model_loader: - kv 3: phi2.embedding_length u32 = 2560 | |
llama_model_loader: - kv 4: phi2.feed_forward_length u32 = 10240 | |
llama_model_loader: - kv 5: phi2.block_count u32 = 32 | |
llama_model_loader: - kv 6: phi2.attention.head_count u32 = 32 | |
llama_model_loader: - kv 7: phi2.attention.head_count_kv u32 = 32 | |
llama_model_loader: - kv 8: phi2.attention.layer_norm_epsilon f32 = 0.000010 | |
llama_model_loader: - kv 9: phi2.rope.dimension_count u32 = 32 | |
llama_model_loader: - kv 10: general.file_type u32 = 15 | |
llama_model_loader: - kv 11: tokenizer.ggml.add_bos_token bool = false | |
llama_model_loader: - kv 12: tokenizer.ggml.model str = gpt2 | |
llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,51200] = ["!", "\"", "#", "$", "%", "&", "'", ... | |
llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,51200] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... | |
llama_model_loader: - kv 15: tokenizer.ggml.merges arr[str,50000] = ["Ġ t", "Ġ a", "h e", "i n", "r e",... | |
llama_model_loader: - kv 16: tokenizer.ggml.bos_token_id u32 = 50256 | |
llama_model_loader: - kv 17: tokenizer.ggml.eos_token_id u32 = 50295 | |
llama_model_loader: - kv 18: tokenizer.ggml.unknown_token_id u32 = 50256 | |
llama_model_loader: - kv 19: tokenizer.ggml.padding_token_id u32 = 50256 | |
llama_model_loader: - kv 20: general.quantization_version u32 = 2 | |
llama_model_loader: - type f32: 195 tensors | |
llama_model_loader: - type q4_K: 81 tensors | |
llama_model_loader: - type q5_K: 32 tensors | |
llama_model_loader: - type q6_K: 17 tensors | |
llm_load_vocab: mismatch in special tokens definition ( 910/51200 vs 944/51200 ). | |
llm_load_print_meta: format = GGUF V3 (latest) | |
llm_load_print_meta: arch = phi2 | |
llm_load_print_meta: vocab type = BPE | |
llm_load_print_meta: n_vocab = 51200 | |
llm_load_print_meta: n_merges = 50000 | |
llm_load_print_meta: n_ctx_train = 2048 | |
llm_load_print_meta: n_embd = 2560 | |
llm_load_print_meta: n_head = 32 | |
llm_load_print_meta: n_head_kv = 32 | |
llm_load_print_meta: n_layer = 32 | |
llm_load_print_meta: n_rot = 32 | |
llm_load_print_meta: n_embd_head_k = 80 | |
llm_load_print_meta: n_embd_head_v = 80 | |
llm_load_print_meta: n_gqa = 1 | |
llm_load_print_meta: n_embd_k_gqa = 2560 | |
llm_load_print_meta: n_embd_v_gqa = 2560 | |
llm_load_print_meta: f_norm_eps = 1.0e-05 | |
llm_load_print_meta: f_norm_rms_eps = 0.0e+00 | |
llm_load_print_meta: f_clamp_kqv = 0.0e+00 | |
llm_load_print_meta: f_max_alibi_bias = 0.0e+00 | |
llm_load_print_meta: n_ff = 10240 | |
llm_load_print_meta: n_expert = 0 | |
llm_load_print_meta: n_expert_used = 0 | |
llm_load_print_meta: rope scaling = linear | |
llm_load_print_meta: freq_base_train = 10000.0 | |
llm_load_print_meta: freq_scale_train = 1 | |
llm_load_print_meta: n_yarn_orig_ctx = 2048 | |
llm_load_print_meta: rope_finetuned = unknown | |
llm_load_print_meta: model type = 3B | |
llm_load_print_meta: model ftype = Q4_K - Medium | |
llm_load_print_meta: model params = 2.78 B | |
llm_load_print_meta: model size = 1.66 GiB (5.14 BPW) | |
llm_load_print_meta: general.name = Phi2 | |
llm_load_print_meta: BOS token = 50256 '<|endoftext|>' | |
llm_load_print_meta: EOS token = 50295 '<|im_end|>' | |
llm_load_print_meta: UNK token = 50256 '<|endoftext|>' | |
llm_load_print_meta: PAD token = 50256 '<|endoftext|>' | |
llm_load_print_meta: LF token = 128 'Ä' | |
llm_load_tensors: ggml ctx size = 0.12 MiB | |
llm_load_tensors: offloading 0 repeating layers to GPU | |
llm_load_tensors: offloaded 0/33 layers to GPU | |
llm_load_tensors: CPU buffer size = 1704.63 MiB | |
.................................................................................. | |
llama_new_context_with_model: n_ctx = 512 | |
llama_new_context_with_model: freq_base = 10000.0 | |
llama_new_context_with_model: freq_scale = 1 | |
ggml_vk_host_malloc(167772160) | |
ggml_vk_create_buffer(167772160, { HostVisible | HostCoherent | HostCached }) | |
ggml_vulkan: Failed to allocate pinned memory. | |
ggml_vulkan: No suitable memory type found: ErrorOutOfDeviceMemory | |
llama_kv_cache_init: CPU KV buffer size = 160.00 MiB | |
llama_new_context_with_model: KV self size = 160.00 MiB, K (f16): 80.00 MiB, V (f16): 80.00 MiB | |
ggml_vk_host_malloc(6297600) | |
ggml_vk_create_buffer(6297600, { HostVisible | HostCoherent | HostCached }) | |
ggml_vulkan: Failed to allocate pinned memory. | |
ggml_vulkan: No suitable memory type found: ErrorOutOfDeviceMemory | |
llama_new_context_with_model: CPU input buffer size = 6.01 MiB | |
ggml_vk_host_malloc(1) | |
ggml_vk_create_buffer(1, { HostVisible | HostCoherent | HostCached }) | |
ggml_vulkan: Failed to allocate pinned memory. | |
ggml_vulkan: No suitable memory type found: ErrorOutOfDeviceMemory | |
ggml_vk_host_malloc(121110580) | |
ggml_vk_create_buffer(121110580, { HostVisible | HostCoherent | HostCached }) | |
ggml_vulkan: Failed to allocate pinned memory. | |
ggml_vulkan: No suitable memory type found: ErrorOutOfDeviceMemory | |
llama_new_context_with_model: CPU compute buffer size = 115.50 MiB | |
llama_new_context_with_model: graph splits (measure): 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd10e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd1270) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd1720) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd18b0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd1a40) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd1bd0) | |
ggml_vk_create_extra(0xb400007091fd1bd0 (wqkv-0, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_pool_malloc(61440) | |
ggml_vk_create_buffer(61440, { DeviceLocal }) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd1d60) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd1ef0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd2080) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd2850) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd1400) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd2b70) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd2d00) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd2210) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd23a0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd29e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd2e90) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd2530) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd26c0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd3340) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd3660) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd3020) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd31b0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd34d0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd37f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd3fc0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd3b10) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd3980) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd3ca0) | |
ggml_vk_create_extra(0xb400007091fd3ca0 (kq-0, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd1590) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd3e30) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd4150) | |
ggml_vk_create_extra(0xb400007091fd4150 (kqv-0, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd42e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd4470) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd4600) | |
ggml_vk_create_extra(0xb400007091fd4600 (kqv_wo-0, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd4790) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd4920) | |
ggml_vk_create_extra(0xb400007091fd4920 (ffn_up-0, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_pool_malloc(81920) | |
ggml_vk_create_buffer(81920, { DeviceLocal }) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd4ab0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd4c40) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd4dd0) | |
ggml_vk_create_extra(0xb400007091fd4dd0 (ffn_down-0, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd4f60) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd50f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd5280) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd5410) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd55a0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd5730) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd58c0) | |
ggml_vk_create_extra(0xb400007091fd58c0 (wqkv-1, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd5a50) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd5be0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd5d70) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd6540) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd6860) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd69f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd5f00) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd6090) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd66d0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd6b80) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd6220) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd63b0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd7030) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd7350) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd6d10) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd6ea0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd71c0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd74e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd7cb0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd7800) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd7670) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd7990) | |
ggml_vk_create_extra(0xb400007091fd7990 (kq-1, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd7b20) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd7e40) | |
ggml_vk_create_extra(0xb400007091fd7e40 (kqv-1, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd7fd0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd8160) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd82f0) | |
ggml_vk_create_extra(0xb400007091fd82f0 (kqv_wo-1, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd8480) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd8610) | |
ggml_vk_create_extra(0xb400007091fd8610 (ffn_up-1, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd87a0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd8930) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd8ac0) | |
ggml_vk_create_extra(0xb400007091fd8ac0 (ffn_down-1, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd8c50) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd8de0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd8f70) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd9100) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd9290) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd9420) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd95b0) | |
ggml_vk_create_extra(0xb400007091fd95b0 (wqkv-2, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd9740) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd98d0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd9a60) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fda230) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fda550) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fda6e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd9bf0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd9d80) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fda3c0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fda870) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fd9f10) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fda0a0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdad20) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdb040) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdaa00) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdab90) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdaeb0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdb1d0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdb9a0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdb4f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdb360) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdb680) | |
ggml_vk_create_extra(0xb400007091fdb680 (kq-2, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdb810) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdbb30) | |
ggml_vk_create_extra(0xb400007091fdbb30 (kqv-2, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdbcc0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdbe50) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdbfe0) | |
ggml_vk_create_extra(0xb400007091fdbfe0 (kqv_wo-2, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdc170) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdc300) | |
ggml_vk_create_extra(0xb400007091fdc300 (ffn_up-2, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdc490) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdc620) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdc7b0) | |
ggml_vk_create_extra(0xb400007091fdc7b0 (ffn_down-2, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdc940) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdcad0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdcc60) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdcdf0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdcf80) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdd110) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdd2a0) | |
ggml_vk_create_extra(0xb400007091fdd2a0 (wqkv-3, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdd430) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdd5c0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdd750) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fddf20) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fde240) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fde3d0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdd8e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdda70) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fde0b0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fde560) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fddc00) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fddd90) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdea10) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fded30) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fde6f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fde880) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdeba0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdeec0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdf690) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdf1e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdf050) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdf370) | |
ggml_vk_create_extra(0xb400007091fdf370 (kq-3, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdf500) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdf820) | |
ggml_vk_create_extra(0xb400007091fdf820 (kqv-3, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdf9b0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdfb40) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdfcd0) | |
ggml_vk_create_extra(0xb400007091fdfcd0 (kqv_wo-3, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdfe60) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fdfff0) | |
ggml_vk_create_extra(0xb400007091fdfff0 (ffn_up-3, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe0180) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe0310) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe04a0) | |
ggml_vk_create_extra(0xb400007091fe04a0 (ffn_down-3, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe0630) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe07c0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe0950) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe0ae0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe0c70) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe0e00) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe0f90) | |
ggml_vk_create_extra(0xb400007091fe0f90 (wqkv-4, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe1120) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe12b0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe1440) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe1c10) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe1f30) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe20c0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe15d0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe1760) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe1da0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe2250) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe18f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe1a80) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe2700) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe2a20) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe23e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe2570) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe2890) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe2bb0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe3380) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe2ed0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe2d40) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe3060) | |
ggml_vk_create_extra(0xb400007091fe3060 (kq-4, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe31f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe3510) | |
ggml_vk_create_extra(0xb400007091fe3510 (kqv-4, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe36a0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe3830) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe39c0) | |
ggml_vk_create_extra(0xb400007091fe39c0 (kqv_wo-4, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe3b50) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe3ce0) | |
ggml_vk_create_extra(0xb400007091fe3ce0 (ffn_up-4, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe3e70) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe4000) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe4190) | |
ggml_vk_create_extra(0xb400007091fe4190 (ffn_down-4, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe4320) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe44b0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe4640) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe47d0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe4960) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe4af0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe4c80) | |
ggml_vk_create_extra(0xb400007091fe4c80 (wqkv-5, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe4e10) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe4fa0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe5130) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe5900) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe5c20) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe5db0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe52c0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe5450) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe5a90) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe5f40) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe55e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe5770) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe63f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe6710) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe60d0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe6260) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe6580) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe68a0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe7070) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe6bc0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe6a30) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe6d50) | |
ggml_vk_create_extra(0xb400007091fe6d50 (kq-5, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe6ee0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe7200) | |
ggml_vk_create_extra(0xb400007091fe7200 (kqv-5, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe7390) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe7520) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe76b0) | |
ggml_vk_create_extra(0xb400007091fe76b0 (kqv_wo-5, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe7840) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe79d0) | |
ggml_vk_create_extra(0xb400007091fe79d0 (ffn_up-5, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe7b60) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe7cf0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe7e80) | |
ggml_vk_create_extra(0xb400007091fe7e80 (ffn_down-5, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe8010) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe81a0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe8330) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe84c0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe8650) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe87e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe8970) | |
ggml_vk_create_extra(0xb400007091fe8970 (wqkv-6, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe8b00) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe8c90) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe8e20) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe95f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe9910) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe9aa0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe8fb0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe9140) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe9780) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe9c30) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe92d0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe9460) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fea0e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fea400) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe9dc0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fe9f50) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fea270) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fea590) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fead60) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fea8b0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fea720) | |
ggml_vk_preallocate_buffers_graph(0xb400007091feaa40) | |
ggml_vk_create_extra(0xb400007091feaa40 (kq-6, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091feabd0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091feaef0) | |
ggml_vk_create_extra(0xb400007091feaef0 (kqv-6, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091feb080) | |
ggml_vk_preallocate_buffers_graph(0xb400007091feb210) | |
ggml_vk_preallocate_buffers_graph(0xb400007091feb3a0) | |
ggml_vk_create_extra(0xb400007091feb3a0 (kqv_wo-6, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091feb530) | |
ggml_vk_preallocate_buffers_graph(0xb400007091feb6c0) | |
ggml_vk_create_extra(0xb400007091feb6c0 (ffn_up-6, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091feb850) | |
ggml_vk_preallocate_buffers_graph(0xb400007091feb9e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091febb70) | |
ggml_vk_create_extra(0xb400007091febb70 (ffn_down-6, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091febd00) | |
ggml_vk_preallocate_buffers_graph(0xb400007091febe90) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fec020) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fec1b0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fec340) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fec4d0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fec660) | |
ggml_vk_create_extra(0xb400007091fec660 (wqkv-7, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fec7f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fec980) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fecb10) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fed2e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fed600) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fed790) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fecca0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fece30) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fed470) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fed920) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fecfc0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fed150) | |
ggml_vk_preallocate_buffers_graph(0xb400007091feddd0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fee0f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fedab0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fedc40) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fedf60) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fee280) | |
ggml_vk_preallocate_buffers_graph(0xb400007091feea50) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fee5a0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fee410) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fee730) | |
ggml_vk_create_extra(0xb400007091fee730 (kq-7, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fee8c0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091feebe0) | |
ggml_vk_create_extra(0xb400007091feebe0 (kqv-7, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091feed70) | |
ggml_vk_preallocate_buffers_graph(0xb400007091feef00) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fef090) | |
ggml_vk_create_extra(0xb400007091fef090 (kqv_wo-7, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fef220) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fef3b0) | |
ggml_vk_create_extra(0xb400007091fef3b0 (ffn_up-7, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fef540) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fef6d0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fef860) | |
ggml_vk_create_extra(0xb400007091fef860 (ffn_down-7, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fef9f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fefb80) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fefd10) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fefea0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff0030) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff01c0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff0350) | |
ggml_vk_create_extra(0xb400007091ff0350 (wqkv-8, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff04e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff0670) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff0800) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff0fd0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff12f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff1480) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff0990) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff0b20) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff1160) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff1610) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff0cb0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff0e40) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff1ac0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff1de0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff17a0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff1930) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff1c50) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff1f70) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff2740) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff2290) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff2100) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff2420) | |
ggml_vk_create_extra(0xb400007091ff2420 (kq-8, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff25b0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff28d0) | |
ggml_vk_create_extra(0xb400007091ff28d0 (kqv-8, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff2a60) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff2bf0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff2d80) | |
ggml_vk_create_extra(0xb400007091ff2d80 (kqv_wo-8, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff2f10) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff30a0) | |
ggml_vk_create_extra(0xb400007091ff30a0 (ffn_up-8, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff3230) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff33c0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff3550) | |
ggml_vk_create_extra(0xb400007091ff3550 (ffn_down-8, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff36e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff3870) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff3a00) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff3b90) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff3d20) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff3eb0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff4040) | |
ggml_vk_create_extra(0xb400007091ff4040 (wqkv-9, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff41d0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff4360) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff44f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff4cc0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff4fe0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff5170) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff4680) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff4810) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff4e50) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff5300) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff49a0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff4b30) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff57b0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff5ad0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff5490) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff5620) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff5940) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff5c60) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff6430) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff5f80) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff5df0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff6110) | |
ggml_vk_create_extra(0xb400007091ff6110 (kq-9, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff62a0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff65c0) | |
ggml_vk_create_extra(0xb400007091ff65c0 (kqv-9, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff6750) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff68e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff6a70) | |
ggml_vk_create_extra(0xb400007091ff6a70 (kqv_wo-9, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff6c00) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff6d90) | |
ggml_vk_create_extra(0xb400007091ff6d90 (ffn_up-9, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff6f20) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff70b0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff7240) | |
ggml_vk_create_extra(0xb400007091ff7240 (ffn_down-9, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff73d0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff7560) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff76f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff7880) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff7a10) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff7ba0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff7d30) | |
ggml_vk_create_extra(0xb400007091ff7d30 (wqkv-10, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff7ec0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff8050) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff81e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff89b0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff8cd0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff8e60) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff8370) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff8500) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff8b40) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff8ff0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff8690) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff8820) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff94a0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff97c0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff9180) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff9310) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff9630) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff9950) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffa120) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff9c70) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff9ae0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff9e00) | |
ggml_vk_create_extra(0xb400007091ff9e00 (kq-10, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091ff9f90) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffa2b0) | |
ggml_vk_create_extra(0xb400007091ffa2b0 (kqv-10, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffa440) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffa5d0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffa760) | |
ggml_vk_create_extra(0xb400007091ffa760 (kqv_wo-10, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffa8f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffaa80) | |
ggml_vk_create_extra(0xb400007091ffaa80 (ffn_up-10, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffac10) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffada0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffaf30) | |
ggml_vk_create_extra(0xb400007091ffaf30 (ffn_down-10, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffb0c0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffb250) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffb3e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffb570) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffb700) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffb890) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffba20) | |
ggml_vk_create_extra(0xb400007091ffba20 (wqkv-11, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffbbb0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffbd40) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffbed0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffc6a0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffc9c0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffcb50) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffc060) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffc1f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffc830) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffcce0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffc380) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffc510) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffd190) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffd4b0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffce70) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffd000) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffd320) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffd640) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffde10) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffd960) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffd7d0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffdaf0) | |
ggml_vk_create_extra(0xb400007091ffdaf0 (kq-11, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffdc80) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffdfa0) | |
ggml_vk_create_extra(0xb400007091ffdfa0 (kqv-11, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffe130) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffe2c0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffe450) | |
ggml_vk_create_extra(0xb400007091ffe450 (kqv_wo-11, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffe5e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffe770) | |
ggml_vk_create_extra(0xb400007091ffe770 (ffn_up-11, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffe900) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffea90) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffec20) | |
ggml_vk_create_extra(0xb400007091ffec20 (ffn_down-11, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffedb0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091ffef40) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fff0d0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fff260) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fff3f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fff580) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fff710) | |
ggml_vk_create_extra(0xb400007091fff710 (wqkv-12, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007091fff8a0) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fffa30) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fffbc0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092000390) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920006b0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092000840) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fffd50) | |
ggml_vk_preallocate_buffers_graph(0xb400007091fffee0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092000520) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920009d0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092000070) | |
ggml_vk_preallocate_buffers_graph(0xb400007092000200) | |
ggml_vk_preallocate_buffers_graph(0xb400007092000e80) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920011a0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092000b60) | |
ggml_vk_preallocate_buffers_graph(0xb400007092000cf0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092001010) | |
ggml_vk_preallocate_buffers_graph(0xb400007092001330) | |
ggml_vk_preallocate_buffers_graph(0xb400007092001b00) | |
ggml_vk_preallocate_buffers_graph(0xb400007092001650) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920014c0) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920017e0) | |
ggml_vk_create_extra(0xb4000070920017e0 (kq-12, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092001970) | |
ggml_vk_preallocate_buffers_graph(0xb400007092001c90) | |
ggml_vk_create_extra(0xb400007092001c90 (kqv-12, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092001e20) | |
ggml_vk_preallocate_buffers_graph(0xb400007092001fb0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092002140) | |
ggml_vk_create_extra(0xb400007092002140 (kqv_wo-12, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb4000070920022d0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092002460) | |
ggml_vk_create_extra(0xb400007092002460 (ffn_up-12, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb4000070920025f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092002780) | |
ggml_vk_preallocate_buffers_graph(0xb400007092002910) | |
ggml_vk_create_extra(0xb400007092002910 (ffn_down-12, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092002aa0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092002c30) | |
ggml_vk_preallocate_buffers_graph(0xb400007092002dc0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092002f50) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920030e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092003270) | |
ggml_vk_preallocate_buffers_graph(0xb400007092003400) | |
ggml_vk_create_extra(0xb400007092003400 (wqkv-13, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092003590) | |
ggml_vk_preallocate_buffers_graph(0xb400007092003720) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920038b0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092004080) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920043a0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092004530) | |
ggml_vk_preallocate_buffers_graph(0xb400007092003a40) | |
ggml_vk_preallocate_buffers_graph(0xb400007092003bd0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092004210) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920046c0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092003d60) | |
ggml_vk_preallocate_buffers_graph(0xb400007092003ef0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092004b70) | |
ggml_vk_preallocate_buffers_graph(0xb400007092004e90) | |
ggml_vk_preallocate_buffers_graph(0xb400007092004850) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920049e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092004d00) | |
ggml_vk_preallocate_buffers_graph(0xb400007092005020) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920057f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092005340) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920051b0) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920054d0) | |
ggml_vk_create_extra(0xb4000070920054d0 (kq-13, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092005660) | |
ggml_vk_preallocate_buffers_graph(0xb400007092005980) | |
ggml_vk_create_extra(0xb400007092005980 (kqv-13, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092005b10) | |
ggml_vk_preallocate_buffers_graph(0xb400007092005ca0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092005e30) | |
ggml_vk_create_extra(0xb400007092005e30 (kqv_wo-13, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092005fc0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092006150) | |
ggml_vk_create_extra(0xb400007092006150 (ffn_up-13, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb4000070920062e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092006470) | |
ggml_vk_preallocate_buffers_graph(0xb400007092006600) | |
ggml_vk_create_extra(0xb400007092006600 (ffn_down-13, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092006790) | |
ggml_vk_preallocate_buffers_graph(0xb400007092006920) | |
ggml_vk_preallocate_buffers_graph(0xb400007092006ab0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092006c40) | |
ggml_vk_preallocate_buffers_graph(0xb400007092006dd0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092006f60) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920070f0) | |
ggml_vk_create_extra(0xb4000070920070f0 (wqkv-14, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092007280) | |
ggml_vk_preallocate_buffers_graph(0xb400007092007410) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920075a0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092007d70) | |
ggml_vk_preallocate_buffers_graph(0xb400007092008090) | |
ggml_vk_preallocate_buffers_graph(0xb400007092008220) | |
ggml_vk_preallocate_buffers_graph(0xb400007092007730) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920078c0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092007f00) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920083b0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092007a50) | |
ggml_vk_preallocate_buffers_graph(0xb400007092007be0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092008860) | |
ggml_vk_preallocate_buffers_graph(0xb400007092008b80) | |
ggml_vk_preallocate_buffers_graph(0xb400007092008540) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920086d0) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920089f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092008d10) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920094e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092009030) | |
ggml_vk_preallocate_buffers_graph(0xb400007092008ea0) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920091c0) | |
ggml_vk_create_extra(0xb4000070920091c0 (kq-14, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092009350) | |
ggml_vk_preallocate_buffers_graph(0xb400007092009670) | |
ggml_vk_create_extra(0xb400007092009670 (kqv-14, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092009800) | |
ggml_vk_preallocate_buffers_graph(0xb400007092009990) | |
ggml_vk_preallocate_buffers_graph(0xb400007092009b20) | |
ggml_vk_create_extra(0xb400007092009b20 (kqv_wo-14, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092009cb0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092009e40) | |
ggml_vk_create_extra(0xb400007092009e40 (ffn_up-14, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092009fd0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200a160) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200a2f0) | |
ggml_vk_create_extra(0xb40000709200a2f0 (ffn_down-14, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709200a480) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200a610) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200a7a0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200a930) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200aac0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200ac50) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200ade0) | |
ggml_vk_create_extra(0xb40000709200ade0 (wqkv-15, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709200af70) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200b100) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200b290) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200ba60) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200bd80) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200bf10) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200b420) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200b5b0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200bbf0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200c0a0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200b740) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200b8d0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200c550) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200c870) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200c230) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200c3c0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200c6e0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200ca00) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200d1d0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200cd20) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200cb90) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200ceb0) | |
ggml_vk_create_extra(0xb40000709200ceb0 (kq-15, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709200d040) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200d360) | |
ggml_vk_create_extra(0xb40000709200d360 (kqv-15, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709200d4f0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200d680) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200d810) | |
ggml_vk_create_extra(0xb40000709200d810 (kqv_wo-15, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709200d9a0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200db30) | |
ggml_vk_create_extra(0xb40000709200db30 (ffn_up-15, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709200dcc0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200de50) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200dfe0) | |
ggml_vk_create_extra(0xb40000709200dfe0 (ffn_down-15, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709200e170) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200e300) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200e490) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200e620) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200e7b0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200e940) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200ead0) | |
ggml_vk_create_extra(0xb40000709200ead0 (wqkv-16, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709200ec60) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200edf0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200ef80) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200f750) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200fa70) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200fc00) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200f110) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200f2a0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200f8e0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200fd90) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200f430) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200f5c0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092010240) | |
ggml_vk_preallocate_buffers_graph(0xb400007092010560) | |
ggml_vk_preallocate_buffers_graph(0xb40000709200ff20) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920100b0) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920103d0) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920106f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092010ec0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092010a10) | |
ggml_vk_preallocate_buffers_graph(0xb400007092010880) | |
ggml_vk_preallocate_buffers_graph(0xb400007092010ba0) | |
ggml_vk_create_extra(0xb400007092010ba0 (kq-16, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092010d30) | |
ggml_vk_preallocate_buffers_graph(0xb400007092011050) | |
ggml_vk_create_extra(0xb400007092011050 (kqv-16, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb4000070920111e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092011370) | |
ggml_vk_preallocate_buffers_graph(0xb400007092011500) | |
ggml_vk_create_extra(0xb400007092011500 (kqv_wo-16, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092011690) | |
ggml_vk_preallocate_buffers_graph(0xb400007092011820) | |
ggml_vk_create_extra(0xb400007092011820 (ffn_up-16, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb4000070920119b0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092011b40) | |
ggml_vk_preallocate_buffers_graph(0xb400007092011cd0) | |
ggml_vk_create_extra(0xb400007092011cd0 (ffn_down-16, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092011e60) | |
ggml_vk_preallocate_buffers_graph(0xb400007092011ff0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092012180) | |
ggml_vk_preallocate_buffers_graph(0xb400007092012310) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920124a0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092012630) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920127c0) | |
ggml_vk_create_extra(0xb4000070920127c0 (wqkv-17, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092012950) | |
ggml_vk_preallocate_buffers_graph(0xb400007092012ae0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092012c70) | |
ggml_vk_preallocate_buffers_graph(0xb400007092013440) | |
ggml_vk_preallocate_buffers_graph(0xb400007092013760) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920138f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092012e00) | |
ggml_vk_preallocate_buffers_graph(0xb400007092012f90) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920135d0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092013a80) | |
ggml_vk_preallocate_buffers_graph(0xb400007092013120) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920132b0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092013f30) | |
ggml_vk_preallocate_buffers_graph(0xb400007092014250) | |
ggml_vk_preallocate_buffers_graph(0xb400007092013c10) | |
ggml_vk_preallocate_buffers_graph(0xb400007092013da0) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920140c0) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920143e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092014bb0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092014700) | |
ggml_vk_preallocate_buffers_graph(0xb400007092014570) | |
ggml_vk_preallocate_buffers_graph(0xb400007092014890) | |
ggml_vk_create_extra(0xb400007092014890 (kq-17, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092014a20) | |
ggml_vk_preallocate_buffers_graph(0xb400007092014d40) | |
ggml_vk_create_extra(0xb400007092014d40 (kqv-17, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092014ed0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092015060) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920151f0) | |
ggml_vk_create_extra(0xb4000070920151f0 (kqv_wo-17, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092015380) | |
ggml_vk_preallocate_buffers_graph(0xb400007092015510) | |
ggml_vk_create_extra(0xb400007092015510 (ffn_up-17, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb4000070920156a0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092015830) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920159c0) | |
ggml_vk_create_extra(0xb4000070920159c0 (ffn_down-17, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092015b50) | |
ggml_vk_preallocate_buffers_graph(0xb400007092015ce0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092015e70) | |
ggml_vk_preallocate_buffers_graph(0xb400007092016000) | |
ggml_vk_preallocate_buffers_graph(0xb400007092016190) | |
ggml_vk_preallocate_buffers_graph(0xb400007092016320) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920164b0) | |
ggml_vk_create_extra(0xb4000070920164b0 (wqkv-18, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092016640) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920167d0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092016960) | |
ggml_vk_preallocate_buffers_graph(0xb400007092017130) | |
ggml_vk_preallocate_buffers_graph(0xb400007092017450) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920175e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092016af0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092016c80) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920172c0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092017770) | |
ggml_vk_preallocate_buffers_graph(0xb400007092016e10) | |
ggml_vk_preallocate_buffers_graph(0xb400007092016fa0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092017c20) | |
ggml_vk_preallocate_buffers_graph(0xb400007092017f40) | |
ggml_vk_preallocate_buffers_graph(0xb400007092017900) | |
ggml_vk_preallocate_buffers_graph(0xb400007092017a90) | |
ggml_vk_preallocate_buffers_graph(0xb400007092017db0) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920180d0) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920188a0) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920183f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092018260) | |
ggml_vk_preallocate_buffers_graph(0xb400007092018580) | |
ggml_vk_create_extra(0xb400007092018580 (kq-18, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092018710) | |
ggml_vk_preallocate_buffers_graph(0xb400007092018a30) | |
ggml_vk_create_extra(0xb400007092018a30 (kqv-18, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092018bc0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092018d50) | |
ggml_vk_preallocate_buffers_graph(0xb400007092018ee0) | |
ggml_vk_create_extra(0xb400007092018ee0 (kqv_wo-18, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092019070) | |
ggml_vk_preallocate_buffers_graph(0xb400007092019200) | |
ggml_vk_create_extra(0xb400007092019200 (ffn_up-18, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092019390) | |
ggml_vk_preallocate_buffers_graph(0xb400007092019520) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920196b0) | |
ggml_vk_create_extra(0xb4000070920196b0 (ffn_down-18, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092019840) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920199d0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092019b60) | |
ggml_vk_preallocate_buffers_graph(0xb400007092019cf0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092019e80) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201a010) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201a1a0) | |
ggml_vk_create_extra(0xb40000709201a1a0 (wqkv-19, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709201a330) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201a4c0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201a650) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201ae20) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201b140) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201b2d0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201a7e0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201a970) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201afb0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201b460) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201ab00) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201ac90) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201b910) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201bc30) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201b5f0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201b780) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201baa0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201bdc0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201c590) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201c0e0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201bf50) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201c270) | |
ggml_vk_create_extra(0xb40000709201c270 (kq-19, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709201c400) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201c720) | |
ggml_vk_create_extra(0xb40000709201c720 (kqv-19, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709201c8b0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201ca40) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201cbd0) | |
ggml_vk_create_extra(0xb40000709201cbd0 (kqv_wo-19, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709201cd60) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201cef0) | |
ggml_vk_create_extra(0xb40000709201cef0 (ffn_up-19, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709201d080) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201d210) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201d3a0) | |
ggml_vk_create_extra(0xb40000709201d3a0 (ffn_down-19, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709201d530) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201d6c0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201d850) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201d9e0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201db70) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201dd00) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201de90) | |
ggml_vk_create_extra(0xb40000709201de90 (wqkv-20, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709201e020) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201e1b0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201e340) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201eb10) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201ee30) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201efc0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201e4d0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201e660) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201eca0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201f150) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201e7f0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201e980) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201f600) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201f920) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201f2e0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201f470) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201f790) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201fab0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092020280) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201fdd0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201fc40) | |
ggml_vk_preallocate_buffers_graph(0xb40000709201ff60) | |
ggml_vk_create_extra(0xb40000709201ff60 (kq-20, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb4000070920200f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092020410) | |
ggml_vk_create_extra(0xb400007092020410 (kqv-20, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb4000070920205a0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092020730) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920208c0) | |
ggml_vk_create_extra(0xb4000070920208c0 (kqv_wo-20, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092020a50) | |
ggml_vk_preallocate_buffers_graph(0xb400007092020be0) | |
ggml_vk_create_extra(0xb400007092020be0 (ffn_up-20, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092020d70) | |
ggml_vk_preallocate_buffers_graph(0xb400007092020f00) | |
ggml_vk_preallocate_buffers_graph(0xb400007092021090) | |
ggml_vk_create_extra(0xb400007092021090 (ffn_down-20, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092021220) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920213b0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092021540) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920216d0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092021860) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920219f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092021b80) | |
ggml_vk_create_extra(0xb400007092021b80 (wqkv-21, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092021d10) | |
ggml_vk_preallocate_buffers_graph(0xb400007092021ea0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092022030) | |
ggml_vk_preallocate_buffers_graph(0xb400007092022800) | |
ggml_vk_preallocate_buffers_graph(0xb400007092022b20) | |
ggml_vk_preallocate_buffers_graph(0xb400007092022cb0) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920221c0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092022350) | |
ggml_vk_preallocate_buffers_graph(0xb400007092022990) | |
ggml_vk_preallocate_buffers_graph(0xb400007092022e40) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920224e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092022670) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920232f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092023610) | |
ggml_vk_preallocate_buffers_graph(0xb400007092022fd0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092023160) | |
ggml_vk_preallocate_buffers_graph(0xb400007092023480) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920237a0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092023f70) | |
ggml_vk_preallocate_buffers_graph(0xb400007092023ac0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092023930) | |
ggml_vk_preallocate_buffers_graph(0xb400007092023c50) | |
ggml_vk_create_extra(0xb400007092023c50 (kq-21, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092023de0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092024100) | |
ggml_vk_create_extra(0xb400007092024100 (kqv-21, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092024290) | |
ggml_vk_preallocate_buffers_graph(0xb400007092024420) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920245b0) | |
ggml_vk_create_extra(0xb4000070920245b0 (kqv_wo-21, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092024740) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920248d0) | |
ggml_vk_create_extra(0xb4000070920248d0 (ffn_up-21, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092024a60) | |
ggml_vk_preallocate_buffers_graph(0xb400007092024bf0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092024d80) | |
ggml_vk_create_extra(0xb400007092024d80 (ffn_down-21, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092024f10) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920250a0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092025230) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920253c0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092025550) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920256e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092025870) | |
ggml_vk_create_extra(0xb400007092025870 (wqkv-22, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092025a00) | |
ggml_vk_preallocate_buffers_graph(0xb400007092025b90) | |
ggml_vk_preallocate_buffers_graph(0xb400007092025d20) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920264f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092026810) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920269a0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092025eb0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092026040) | |
ggml_vk_preallocate_buffers_graph(0xb400007092026680) | |
ggml_vk_preallocate_buffers_graph(0xb400007092026b30) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920261d0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092026360) | |
ggml_vk_preallocate_buffers_graph(0xb400007092026fe0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092027300) | |
ggml_vk_preallocate_buffers_graph(0xb400007092026cc0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092026e50) | |
ggml_vk_preallocate_buffers_graph(0xb400007092027170) | |
ggml_vk_preallocate_buffers_graph(0xb400007092027490) | |
ggml_vk_preallocate_buffers_graph(0xb400007092027c60) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920277b0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092027620) | |
ggml_vk_preallocate_buffers_graph(0xb400007092027940) | |
ggml_vk_create_extra(0xb400007092027940 (kq-22, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092027ad0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092027df0) | |
ggml_vk_create_extra(0xb400007092027df0 (kqv-22, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092027f80) | |
ggml_vk_preallocate_buffers_graph(0xb400007092028110) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920282a0) | |
ggml_vk_create_extra(0xb4000070920282a0 (kqv_wo-22, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092028430) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920285c0) | |
ggml_vk_create_extra(0xb4000070920285c0 (ffn_up-22, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092028750) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920288e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092028a70) | |
ggml_vk_create_extra(0xb400007092028a70 (ffn_down-22, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092028c00) | |
ggml_vk_preallocate_buffers_graph(0xb400007092028d90) | |
ggml_vk_preallocate_buffers_graph(0xb400007092028f20) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920290b0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092029240) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920293d0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092029560) | |
ggml_vk_create_extra(0xb400007092029560 (wqkv-23, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb4000070920296f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092029880) | |
ggml_vk_preallocate_buffers_graph(0xb400007092029a10) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202a1e0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202a500) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202a690) | |
ggml_vk_preallocate_buffers_graph(0xb400007092029ba0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092029d30) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202a370) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202a820) | |
ggml_vk_preallocate_buffers_graph(0xb400007092029ec0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202a050) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202acd0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202aff0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202a9b0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202ab40) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202ae60) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202b180) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202b950) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202b4a0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202b310) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202b630) | |
ggml_vk_create_extra(0xb40000709202b630 (kq-23, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709202b7c0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202bae0) | |
ggml_vk_create_extra(0xb40000709202bae0 (kqv-23, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709202bc70) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202be00) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202bf90) | |
ggml_vk_create_extra(0xb40000709202bf90 (kqv_wo-23, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709202c120) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202c2b0) | |
ggml_vk_create_extra(0xb40000709202c2b0 (ffn_up-23, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709202c440) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202c5d0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202c760) | |
ggml_vk_create_extra(0xb40000709202c760 (ffn_down-23, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709202c8f0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202ca80) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202cc10) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202cda0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202cf30) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202d0c0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202d250) | |
ggml_vk_create_extra(0xb40000709202d250 (wqkv-24, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709202d3e0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202d570) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202d700) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202ded0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202e1f0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202e380) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202d890) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202da20) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202e060) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202e510) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202dbb0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202dd40) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202e9c0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202ece0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202e6a0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202e830) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202eb50) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202ee70) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202f640) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202f190) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202f000) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202f320) | |
ggml_vk_create_extra(0xb40000709202f320 (kq-24, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709202f4b0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202f7d0) | |
ggml_vk_create_extra(0xb40000709202f7d0 (kqv-24, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709202f960) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202faf0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202fc80) | |
ggml_vk_create_extra(0xb40000709202fc80 (kqv_wo-24, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709202fe10) | |
ggml_vk_preallocate_buffers_graph(0xb40000709202ffa0) | |
ggml_vk_create_extra(0xb40000709202ffa0 (ffn_up-24, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092030130) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920302c0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092030450) | |
ggml_vk_create_extra(0xb400007092030450 (ffn_down-24, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb4000070920305e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092030770) | |
ggml_vk_preallocate_buffers_graph(0xb400007092030900) | |
ggml_vk_preallocate_buffers_graph(0xb400007092030a90) | |
ggml_vk_preallocate_buffers_graph(0xb400007092030c20) | |
ggml_vk_preallocate_buffers_graph(0xb400007092030db0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092030f40) | |
ggml_vk_create_extra(0xb400007092030f40 (wqkv-25, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb4000070920310d0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092031260) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920313f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092031bc0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092031ee0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092032070) | |
ggml_vk_preallocate_buffers_graph(0xb400007092031580) | |
ggml_vk_preallocate_buffers_graph(0xb400007092031710) | |
ggml_vk_preallocate_buffers_graph(0xb400007092031d50) | |
ggml_vk_preallocate_buffers_graph(0xb400007092032200) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920318a0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092031a30) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920326b0) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920329d0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092032390) | |
ggml_vk_preallocate_buffers_graph(0xb400007092032520) | |
ggml_vk_preallocate_buffers_graph(0xb400007092032840) | |
ggml_vk_preallocate_buffers_graph(0xb400007092032b60) | |
ggml_vk_preallocate_buffers_graph(0xb400007092033330) | |
ggml_vk_preallocate_buffers_graph(0xb400007092032e80) | |
ggml_vk_preallocate_buffers_graph(0xb400007092032cf0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092033010) | |
ggml_vk_create_extra(0xb400007092033010 (kq-25, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb4000070920331a0) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920334c0) | |
ggml_vk_create_extra(0xb4000070920334c0 (kqv-25, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092033650) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920337e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092033970) | |
ggml_vk_create_extra(0xb400007092033970 (kqv_wo-25, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092033b00) | |
ggml_vk_preallocate_buffers_graph(0xb400007092033c90) | |
ggml_vk_create_extra(0xb400007092033c90 (ffn_up-25, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092033e20) | |
ggml_vk_preallocate_buffers_graph(0xb400007092033fb0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092034140) | |
ggml_vk_create_extra(0xb400007092034140 (ffn_down-25, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb4000070920342d0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092034460) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920345f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092034780) | |
ggml_vk_preallocate_buffers_graph(0xb400007092034910) | |
ggml_vk_preallocate_buffers_graph(0xb400007092034aa0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092034c30) | |
ggml_vk_create_extra(0xb400007092034c30 (wqkv-26, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092034dc0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092034f50) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920350e0) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920358b0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092035bd0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092035d60) | |
ggml_vk_preallocate_buffers_graph(0xb400007092035270) | |
ggml_vk_preallocate_buffers_graph(0xb400007092035400) | |
ggml_vk_preallocate_buffers_graph(0xb400007092035a40) | |
ggml_vk_preallocate_buffers_graph(0xb400007092035ef0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092035590) | |
ggml_vk_preallocate_buffers_graph(0xb400007092035720) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920363a0) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920366c0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092036080) | |
ggml_vk_preallocate_buffers_graph(0xb400007092036210) | |
ggml_vk_preallocate_buffers_graph(0xb400007092036530) | |
ggml_vk_preallocate_buffers_graph(0xb400007092036850) | |
ggml_vk_preallocate_buffers_graph(0xb400007092037020) | |
ggml_vk_preallocate_buffers_graph(0xb400007092036b70) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920369e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092036d00) | |
ggml_vk_create_extra(0xb400007092036d00 (kq-26, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092036e90) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920371b0) | |
ggml_vk_create_extra(0xb4000070920371b0 (kqv-26, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092037340) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920374d0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092037660) | |
ggml_vk_create_extra(0xb400007092037660 (kqv_wo-26, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb4000070920377f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092037980) | |
ggml_vk_create_extra(0xb400007092037980 (ffn_up-26, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092037b10) | |
ggml_vk_preallocate_buffers_graph(0xb400007092037ca0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092037e30) | |
ggml_vk_create_extra(0xb400007092037e30 (ffn_down-26, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092037fc0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092038150) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920382e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092038470) | |
ggml_vk_preallocate_buffers_graph(0xb400007092038600) | |
ggml_vk_preallocate_buffers_graph(0xb400007092038790) | |
ggml_vk_preallocate_buffers_graph(0xb400007092038920) | |
ggml_vk_create_extra(0xb400007092038920 (wqkv-27, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092038ab0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092038c40) | |
ggml_vk_preallocate_buffers_graph(0xb400007092038dd0) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920395a0) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920398c0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092039a50) | |
ggml_vk_preallocate_buffers_graph(0xb400007092038f60) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920390f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092039730) | |
ggml_vk_preallocate_buffers_graph(0xb400007092039be0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092039280) | |
ggml_vk_preallocate_buffers_graph(0xb400007092039410) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203a090) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203a3b0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092039d70) | |
ggml_vk_preallocate_buffers_graph(0xb400007092039f00) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203a220) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203a540) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203ad10) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203a860) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203a6d0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203a9f0) | |
ggml_vk_create_extra(0xb40000709203a9f0 (kq-27, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709203ab80) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203aea0) | |
ggml_vk_create_extra(0xb40000709203aea0 (kqv-27, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709203b030) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203b1c0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203b350) | |
ggml_vk_create_extra(0xb40000709203b350 (kqv_wo-27, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709203b4e0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203b670) | |
ggml_vk_create_extra(0xb40000709203b670 (ffn_up-27, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709203b800) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203b990) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203bb20) | |
ggml_vk_create_extra(0xb40000709203bb20 (ffn_down-27, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709203bcb0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203be40) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203bfd0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203c160) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203c2f0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203c480) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203c610) | |
ggml_vk_create_extra(0xb40000709203c610 (wqkv-28, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709203c7a0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203c930) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203cac0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203d290) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203d5b0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203d740) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203cc50) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203cde0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203d420) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203d8d0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203cf70) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203d100) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203dd80) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203e0a0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203da60) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203dbf0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203df10) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203e230) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203ea00) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203e550) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203e3c0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203e6e0) | |
ggml_vk_create_extra(0xb40000709203e6e0 (kq-28, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709203e870) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203eb90) | |
ggml_vk_create_extra(0xb40000709203eb90 (kqv-28, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709203ed20) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203eeb0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203f040) | |
ggml_vk_create_extra(0xb40000709203f040 (kqv_wo-28, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709203f1d0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203f360) | |
ggml_vk_create_extra(0xb40000709203f360 (ffn_up-28, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709203f4f0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203f680) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203f810) | |
ggml_vk_create_extra(0xb40000709203f810 (ffn_down-28, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709203f9a0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203fb30) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203fcc0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203fe50) | |
ggml_vk_preallocate_buffers_graph(0xb40000709203ffe0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092040170) | |
ggml_vk_preallocate_buffers_graph(0xb400007092040300) | |
ggml_vk_create_extra(0xb400007092040300 (wqkv-29, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092040490) | |
ggml_vk_preallocate_buffers_graph(0xb400007092040620) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920407b0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092040f80) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920412a0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092041430) | |
ggml_vk_preallocate_buffers_graph(0xb400007092040940) | |
ggml_vk_preallocate_buffers_graph(0xb400007092040ad0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092041110) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920415c0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092040c60) | |
ggml_vk_preallocate_buffers_graph(0xb400007092040df0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092041a70) | |
ggml_vk_preallocate_buffers_graph(0xb400007092041d90) | |
ggml_vk_preallocate_buffers_graph(0xb400007092041750) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920418e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092041c00) | |
ggml_vk_preallocate_buffers_graph(0xb400007092041f20) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920426f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092042240) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920420b0) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920423d0) | |
ggml_vk_create_extra(0xb4000070920423d0 (kq-29, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092042560) | |
ggml_vk_preallocate_buffers_graph(0xb400007092042880) | |
ggml_vk_create_extra(0xb400007092042880 (kqv-29, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092042a10) | |
ggml_vk_preallocate_buffers_graph(0xb400007092042ba0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092042d30) | |
ggml_vk_create_extra(0xb400007092042d30 (kqv_wo-29, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092042ec0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092043050) | |
ggml_vk_create_extra(0xb400007092043050 (ffn_up-29, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb4000070920431e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092043370) | |
ggml_vk_preallocate_buffers_graph(0xb400007092043500) | |
ggml_vk_create_extra(0xb400007092043500 (ffn_down-29, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092043690) | |
ggml_vk_preallocate_buffers_graph(0xb400007092043820) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920439b0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092043b40) | |
ggml_vk_preallocate_buffers_graph(0xb400007092043cd0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092043e60) | |
ggml_vk_preallocate_buffers_graph(0xb400007092043ff0) | |
ggml_vk_create_extra(0xb400007092043ff0 (wqkv-30, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092044180) | |
ggml_vk_preallocate_buffers_graph(0xb400007092044310) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920444a0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092044c70) | |
ggml_vk_preallocate_buffers_graph(0xb400007092044f90) | |
ggml_vk_preallocate_buffers_graph(0xb400007092045120) | |
ggml_vk_preallocate_buffers_graph(0xb400007092044630) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920447c0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092044e00) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920452b0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092044950) | |
ggml_vk_preallocate_buffers_graph(0xb400007092044ae0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092045760) | |
ggml_vk_preallocate_buffers_graph(0xb400007092045a80) | |
ggml_vk_preallocate_buffers_graph(0xb400007092045440) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920455d0) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920458f0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092045c10) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920463e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092045f30) | |
ggml_vk_preallocate_buffers_graph(0xb400007092045da0) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920460c0) | |
ggml_vk_create_extra(0xb4000070920460c0 (kq-30, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092046250) | |
ggml_vk_preallocate_buffers_graph(0xb400007092046570) | |
ggml_vk_create_extra(0xb400007092046570 (kqv-30, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092046700) | |
ggml_vk_preallocate_buffers_graph(0xb400007092046890) | |
ggml_vk_preallocate_buffers_graph(0xb400007092046a20) | |
ggml_vk_create_extra(0xb400007092046a20 (kqv_wo-30, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092046bb0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092046d40) | |
ggml_vk_create_extra(0xb400007092046d40 (ffn_up-30, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092046ed0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092047060) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920471f0) | |
ggml_vk_create_extra(0xb4000070920471f0 (ffn_down-30, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092047380) | |
ggml_vk_preallocate_buffers_graph(0xb400007092047510) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920476a0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092047830) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920479c0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092047b50) | |
ggml_vk_preallocate_buffers_graph(0xb400007092047ce0) | |
ggml_vk_create_extra(0xb400007092047ce0 (wqkv-31, MUL_MAT)) | |
ggml_vk_guess_split_k(7680, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092047e70) | |
ggml_vk_preallocate_buffers_graph(0xb400007092048000) | |
ggml_vk_preallocate_buffers_graph(0xb400007092048190) | |
ggml_vk_preallocate_buffers_graph(0xb400007092048960) | |
ggml_vk_preallocate_buffers_graph(0xb400007092048c80) | |
ggml_vk_preallocate_buffers_graph(0xb400007092048e10) | |
ggml_vk_preallocate_buffers_graph(0xb400007092048320) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920484b0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092048af0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092048fa0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092048640) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920487d0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092049450) | |
ggml_vk_preallocate_buffers_graph(0xb400007092049770) | |
ggml_vk_preallocate_buffers_graph(0xb400007092049130) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920492c0) | |
ggml_vk_preallocate_buffers_graph(0xb4000070920495e0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092049900) | |
ggml_vk_preallocate_buffers_graph(0xb40000709204a0d0) | |
ggml_vk_preallocate_buffers_graph(0xb400007092049c20) | |
ggml_vk_preallocate_buffers_graph(0xb400007092049a90) | |
ggml_vk_preallocate_buffers_graph(0xb400007092049db0) | |
ggml_vk_create_extra(0xb400007092049db0 (kq-31, MUL_MAT)) | |
ggml_vk_guess_split_k(32, 2, 80) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb400007092049f40) | |
ggml_vk_preallocate_buffers_graph(0xb40000709204a260) | |
ggml_vk_create_extra(0xb40000709204a260 (kqv-31, MUL_MAT)) | |
ggml_vk_guess_split_k(80, 2, 32) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709204a3f0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709204a580) | |
ggml_vk_preallocate_buffers_graph(0xb40000709204a710) | |
ggml_vk_create_extra(0xb40000709204a710 (kqv_wo-31, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709204a8a0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709204aa30) | |
ggml_vk_create_extra(0xb40000709204aa30 (ffn_up-31, MUL_MAT)) | |
ggml_vk_guess_split_k(10240, 2, 2560) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709204abc0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709204ad50) | |
ggml_vk_preallocate_buffers_graph(0xb40000709204aee0) | |
ggml_vk_create_extra(0xb40000709204aee0 (ffn_down-31, MUL_MAT)) | |
ggml_vk_guess_split_k(2560, 2, 10240) = 1 | |
ggml_vk_preallocate_buffers_graph(0xb40000709204b070) | |
ggml_vk_preallocate_buffers_graph(0xb40000709204b200) | |
ggml_vk_preallocate_buffers_graph(0xb40000709204b390) | |
ggml_vk_preallocate_buffers_graph(0xb40000709204b520) | |
ggml_vk_preallocate_buffers_graph(0xb40000709204b6b0) | |
ggml_vk_preallocate_buffers_graph(0xb40000709204b840) | |
ggml_vk_preallocate_buffers_graph(0xb40000709204b9d0) | |
ggml_vk_create_extra(0xb40000709204b9d0 (result_output_no_bias, MUL_MAT)) | |
ggml_vk_guess_split_k(51200, 2, 2560) = 1 | |
ggml_vk_pool_malloc(409600) | |
ggml_vk_create_buffer(409600, { DeviceLocal }) | |
ggml_vk_preallocate_buffers_graph(0xb40000709204bb60) | |
ggml_vk_preallocate_buffers() | |
qx_size: 107520000 qy_size: 81920 x_size: 262144000 y_size: 81920 split_k_size: 0 | |
ggml_vk_create_buffer(104857600, { HostVisible | HostCoherent | HostCached }) | |
ggml_vulkan: Memory allocation of size 104857600 failed. | |
ggml_vulkan: No suitable memory type found: ErrorOutOfDeviceMemory | |
libc++abi: terminating due to uncaught exception of type vk::SystemError: No suitable memory type found: ErrorOutOfDeviceMemory |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment