Skip to content

Instantly share code, notes, and snippets.

@galleon
Created February 11, 2024 07:13
Show Gist options
  • Save galleon/d538c6d7df7f276bf93861422eb71605 to your computer and use it in GitHub Desktop.
Save galleon/d538c6d7df7f276bf93861422eb71605 to your computer and use it in GitHub Desktop.
ollama log
llama_new_context_with_model: n_ctx = 2048
llama_new_context_with_model: freq_base = 1000000.0
llama_new_context_with_model: freq_scale = 1
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M3 Max
ggml_metal_init: picking default device: Apple M3 Max
ggml_metal_init: default.metallib not found, loading from source
ggml_metal_init: GGML_METAL_PATH_RESOURCES = /var/folders/vd/flj90b5128xfgcsxgjf4_r7m0000gn/T/ollama2312987543
ggml_metal_init: loading '/var/folders/vd/flj90b5128xfgcsxgjf4_r7m0000gn/T/ollama2312987543/ggml-metal.metal'
ggml_metal_init: GPU name: Apple M3 Max
ggml_metal_init: GPU family: MTLGPUFamilyApple9 (1009)
ggml_metal_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_init: GPU family: MTLGPUFamilyMetal3 (5001)
ggml_metal_init: simdgroup reduction support = true
ggml_metal_init: simdgroup matrix mul. support = true
ggml_metal_init: hasUnifiedMemory = true
ggml_metal_init: recommendedMaxWorkingSetSize = 103079.22 MB
ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 256.00 MiB, (25407.53 / 98304.00)
llama_kv_cache_init: Metal KV buffer size = 256.00 MiB
llama_new_context_with_model: KV self size = 256.00 MiB, K (f16): 128.00 MiB, V (f16): 128.00 MiB
llama_new_context_with_model: CPU input buffer size = 12.01 MiB
ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 0.02 MiB, (25407.55 / 98304.00)
ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 202.44 MiB, (25609.97 / 98304.00)
llama_new_context_with_model: Metal compute buffer size = 202.44 MiB
llama_new_context_with_model: CPU compute buffer size = 8.80 MiB
llama_new_context_with_model: graph splits (measure): 3
time=2024-02-10T22:32:19.475+01:00 level=INFO source=dyn_ext_server.go:156 msg="Starting llama main loop"
[GIN] 2024/02/10 - 22:32:25 | 200 | 7.155776459s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/10 - 22:32:41 | 200 | 16.020701209s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/10 - 22:32:52 | 200 | 10.74335s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/10 - 22:33:04 | 200 | 12.378235041s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/10 - 22:33:22 | 200 | 17.442970541s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/10 - 22:33:40 | 200 | 18.145414125s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/10 - 22:33:51 | 200 | 11.366535125s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/10 - 22:34:10 | 200 | 18.876767334s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/10 - 22:34:26 | 200 | 16.155763s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/10 - 22:34:46 | 200 | 20.1503715s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/10 - 22:35:03 | 200 | 16.98645975s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/10 - 22:35:21 | 200 | 17.73278075s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/10 - 22:35:28 | 200 | 7.155519375s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/10 - 22:35:43 | 200 | 15.097013417s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/10 - 22:35:56 | 200 | 12.512163625s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/10 - 22:36:07 | 200 | 11.014607333s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/10 - 22:36:21 | 200 | 14.09642225s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/10 - 22:36:36 | 200 | 15.44790075s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/10 - 22:36:51 | 200 | 14.5270445s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/10 - 22:37:18 | 200 | 27.31977325s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/10 - 22:37:35 | 200 | 16.468427042s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/10 - 22:37:51 | 200 | 16.166390167s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/10 - 22:38:07 | 200 | 16.426113792s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/10 - 22:38:27 | 200 | 19.625774292s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/10 - 22:38:34 | 200 | 7.113926917s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/10 - 22:38:55 | 200 | 21.133472916s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/10 - 22:39:04 | 200 | 8.67121775s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/10 - 22:39:16 | 200 | 12.218877125s | 127.0.0.1 | POST "/api/generate"
...
[GIN] 2024/02/11 - 03:26:02 | 200 | 22.472924s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/11 - 03:26:17 | 200 | 15.002093042s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/11 - 03:26:47 | 200 | 30.561350583s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/11 - 03:26:56 | 200 | 9.028346708s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/11 - 03:27:46 | 200 | 49.35295825s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/11 - 03:27:55 | 200 | 8.954917625s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/11 - 03:28:23 | 200 | 27.809346084s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/11 - 03:28:36 | 200 | 13.962246959s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/11 - 03:28:50 | 200 | 13.984092334s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/11 - 03:29:16 | 200 | 25.07985425s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/11 - 03:29:39 | 200 | 23.048378792s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/11 - 03:29:52 | 200 | 13.028750042s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/11 - 03:30:16 | 200 | 24.189961666s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/11 - 03:30:40 | 200 | 24.058164292s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/11 - 03:30:55 | 200 | 15.567912375s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/11 - 03:31:17 | 200 | 21.809681958s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/11 - 03:31:42 | 200 | 24.915271791s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/11 - 03:32:19 | 200 | 36.597789667s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/11 - 03:32:48 | 200 | 29.205049125s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/11 - 03:32:57 | 200 | 9.397129333s | 127.0.0.1 | POST "/api/generate"
[GIN] 2024/02/11 - 07:54:36 | 200 | 110.5µs | 127.0.0.1 | HEAD "/"
[GIN] 2024/02/11 - 07:54:36 | 200 | 5.948ms | 127.0.0.1 | GET "/api/tags"
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment