Untitled

mail@pastecode.io avatar
unknown
plain_text
2 months ago
6.0 kB
12
Indexable
Never
[GIN] 2024/04/19 - 18:39:16 | 200 |   91.548229ms |       127.0.0.1 | POST     "/api/embeddings"
{"function":"process_single_task","level":"INFO","line":1502,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":846570,"t
id":"140520165871616","timestamp":1713523156}
{"function":"log_server_request","level":"INFO","line":2730,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127
.0.0.1","remote_port":48860,"status":200,"tid":"140518059134976","timestamp":1713523156}
{"function":"process_single_task","level":"INFO","line":1502,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":846571,"t
id":"140520165871616","timestamp":1713523156}
{"function":"log_server_request","level":"INFO","line":2730,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127
.0.0.1","remote_port":48860,"status":200,"tid":"140518059134976","timestamp":1713523156}
{"function":"launch_slot_with_data","level":"INFO","line":826,"msg":"slot is processing task","slot_id":0,"task_id":846572,"tid":"14052016
5871616","timestamp":1713523156}
{"function":"update_slots","level":"INFO","line":1832,"msg":"kv cache rm [p0, end)","p0":0,"slot_id":0,"task_id":846572,"tid":"14052016587
1616","timestamp":1713523156}
{"function":"update_slots","level":"INFO","line":1636,"msg":"slot released","n_cache_tokens":303,"n_ctx":2048,"n_past":303,"n_system_token
s":0,"slot_id":0,"task_id":846572,"tid":"140520165871616","timestamp":1713523157,"truncated":false}
{"function":"log_server_request","level":"INFO","line":2730,"method":"POST","msg":"request","params":{},"path":"/embedding","remote_addr":
"127.0.0.1","remote_port":48862,"status":200,"tid":"140517966864384","timestamp":1713523157}
[GIN] 2024/04/19 - 18:39:17 | 200 |    49.42758ms |       127.0.0.1 | POST     "/api/embeddings"
{"function":"process_single_task","level":"INFO","line":1502,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":846575,"t
id":"140520165871616","timestamp":1713523157}
{"function":"log_server_request","level":"INFO","line":2730,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127
.0.0.1","remote_port":48862,"status":200,"tid":"140517966864384","timestamp":1713523157}
{"function":"process_single_task","level":"INFO","line":1502,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":846576,"t
id":"140520165871616","timestamp":1713523157}
{"function":"log_server_request","level":"INFO","line":2730,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127
.0.0.1","remote_port":48862,"status":200,"tid":"140517966864384","timestamp":1713523157}
{"function":"launch_slot_with_data","level":"INFO","line":826,"msg":"slot is processing task","slot_id":0,"task_id":846577,"tid":"14052016
5871616","timestamp":1713523157}
{"function":"update_slots","level":"INFO","line":1832,"msg":"kv cache rm [p0, end)","p0":0,"slot_id":0,"task_id":846577,"tid":"14052016587
1616","timestamp":1713523157}
{"function":"update_slots","level":"INFO","line":1636,"msg":"slot released","n_cache_tokens":16,"n_ctx":2048,"n_past":16,"n_system_tokens"
:0,"slot_id":0,"task_id":846577,"tid":"140520165871616","timestamp":1713523157,"truncated":false}
{"function":"log_server_request","level":"INFO","line":2730,"method":"POST","msg":"request","params":{},"path":"/embedding","remote_addr":
"127.0.0.1","remote_port":48862,"status":200,"tid":"140517966864384","timestamp":1713523157}
[GIN] 2024/04/19 - 18:39:17 | 200 |  127.422462ms |       127.0.0.1 | POST     "/api/embeddings"
time=2024-04-19T20:03:23.321+08:00 level=WARN source=server.go:51 msg="requested context length is greater than model max context length"
requested=8192 model=2048
time=2024-04-19T20:03:23.327+08:00 level=INFO source=gpu.go:121 msg="Detecting GPU type"
time=2024-04-19T20:03:23.328+08:00 level=INFO source=gpu.go:268 msg="Searching for GPU management library libcudart.so*"
time=2024-04-19T20:03:23.351+08:00 level=INFO source=gpu.go:314 msg="Discovered GPU libraries: [/usr/local/cuda/lib64/libcudart.so.12.4.12
7 /opt/cuda/lib64/libcudart.so.12.4.127]"
time=2024-04-19T20:03:24.029+08:00 level=INFO source=gpu.go:126 msg="Nvidia GPU detected via cudart"
time=2024-04-19T20:03:24.029+08:00 level=INFO source=cpu_common.go:11 msg="CPU has AVX2"
time=2024-04-19T20:03:24.030+08:00 level=INFO source=gpu.go:202 msg="[cudart] CUDART CUDA Compute Capability detected: 8.6"
time=2024-04-19T20:03:24.307+08:00 level=INFO source=gpu.go:121 msg="Detecting GPU type"
time=2024-04-19T20:03:24.307+08:00 level=INFO source=gpu.go:268 msg="Searching for GPU management library libcudart.so*"
time=2024-04-19T20:03:24.311+08:00 level=INFO source=gpu.go:314 msg="Discovered GPU libraries: [/usr/local/cuda/lib64/libcudart.so.12.4.12
7 /opt/cuda/lib64/libcudart.so.12.4.127]"
time=2024-04-19T20:03:24.919+08:00 level=INFO source=gpu.go:126 msg="Nvidia GPU detected via cudart"
time=2024-04-19T20:03:24.919+08:00 level=INFO source=cpu_common.go:11 msg="CPU has AVX2"
time=2024-04-19T20:03:24.920+08:00 level=INFO source=gpu.go:202 msg="[cudart] CUDART CUDA Compute Capability detected: 8.6"
time=2024-04-19T20:03:25.211+08:00 level=INFO source=server.go:120 msg="offload to gpu" reallayers=13 layers=13 required="691.1 MiB" used=
"691.1 MiB" available="8912.6 MiB" kv="6.0 MiB" fulloffload="12.0 MiB" partialoffload="12.0 MiB"
time=2024-04-19T20:03:25.212+08:00 level=INFO source=cpu_common.go:11 msg="CPU has AVX2"
time=2024-04-19T20:03:25.212+08:00 level=INFO source=server.go:257 msg="starting llama server" cmd="ollama_llama_server --model /home/ai/.
ollama/models/blobs/sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6 --ctx-size 2048 --batch-size 512 --embedding -
-log-disable --n-gpu-layers 13 --port 37791"
time=2024-04-19T20:03:25.212+08:00 level=ERROR source=server.go:278 msg="unable to load any llama server" error="error starting the extern
al llama server: exec: \"ollama_llama_server\": executable file not found in $PATH "
Leave a Comment