github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-09 01:59:50 -05:00
Code Issues 14.7k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #3949] Inconsistent 500 errors when generating #48960

New Issue
Closed
opened 2026-04-28 10:18:08 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-28 10:18:08 -05:00
Owner
Copy Link

Originally created by @ronangaillard on GitHub (Apr 26, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3949

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

EDIT : I tried with 0.1.29 and I don't have the issue

Hello,

I'm using docker image, tag latest without any GPU.

I downloaded mistral model, and I'm trying to generate answers using the promt from the doc (I have the same issue with llama model) :

curl http://localhost:11434/api/generate -d '{
  "model": "llama2",
  "prompt": "Why is the sky blue?"
}'

But often (not always) I get an error 500 even though tokens have been generated. I know tokens have been generated because I see them in the API response.

API response :

{"model":"mistral","created_at":"2024-04-26T16:07:28.07709035Z","response":" The","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:28.631254126Z","response":" color","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:29.18215074Z","response":" of","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:29.664237413Z","response":" the","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:30.273469909Z","response":" sky","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:30.781810227Z","response":" appears","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:31.40826255Z","response":" blue","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:31.989479606Z","response":" due","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:32.525336503Z","response":" to","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:33.026269498Z","response":" a","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:33.549170938Z","response":" process","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:34.081219456Z","response":" called","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:34.619630847Z","response":" Ray","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:35.137036869Z","response":"le","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:35.704325551Z","response":"igh","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:36.267680082Z","response":" scattering","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:36.793143541Z","response":".","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:37.282849465Z","response":" As","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:37.842596991Z","response":" sunlight","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:38.38296667Z","response":" reaches","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:38.903363958Z","response":" Earth","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:39.726083579Z","response":"'","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:40.494767417Z","response":"s","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:41.06925115Z","response":" atmosphere","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:41.613843427Z","response":",","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:42.128205209Z","response":" it","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:42.667473181Z","response":" inter","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:43.173160182Z","response":"acts","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:43.716459779Z","response":" with","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:44.268444653Z","response":" different","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:44.817945821Z","response":" g","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:45.426567347Z","response":"ases","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:45.932192978Z","response":" and","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:46.498713045Z","response":" particles","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:47.052741443Z","response":" in","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:47.580913744Z","response":" the","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:48.090460265Z","response":" air","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:48.596333364Z","response":".","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:49.115045502Z","response":" Blue","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:49.642993369Z","response":" light","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:50.18264068Z","response":" has","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:50.685417256Z","response":" a","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:51.19918961Z","response":" shorter","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:51.836339325Z","response":" w","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:52.320055654Z","response":"avelength","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:52.947997012Z","response":" and","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:53.441787158Z","response":" gets","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:53.990117921Z","response":" scattered","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:54.46448626Z","response":" more","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:55.003384218Z","response":" easily","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:55.475699829Z","response":" than","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:56.062239913Z","response":" other","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:56.576008126Z","response":" colors","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:57.275554243Z","response":",","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:57.874225128Z","response":" such","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:58.451544809Z","response":" as","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:58.937056211Z","response":" red","done":false}
{"model":"mistral","created_at":"2024-04-26T16:07:59.49227394Z","response":" or","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:00.030899371Z","response":" yellow","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:00.573231159Z","response":".","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:01.060011721Z","response":" As","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:01.59222445Z","response":" a","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:02.25517787Z","response":" result","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:02.741180311Z","response":",","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:03.243095355Z","response":" when","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:03.759198116Z","response":" we","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:04.293691209Z","response":" look","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:04.830839629Z","response":" up","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:05.34726204Z","response":" at","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:05.871421624Z","response":" the","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:06.423681143Z","response":" sky","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:06.931967006Z","response":",","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:07.473513959Z","response":" we","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:07.989916516Z","response":" predomin","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:08.595876379Z","response":"antly","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:09.109355685Z","response":" see","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:09.616627341Z","response":" the","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:10.167182816Z","response":" scattered","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:10.697195496Z","response":" blue","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:11.227974595Z","response":" light","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:11.722090129Z","response":".","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:12.25041971Z","response":" This","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:12.829180966Z","response":" is","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:13.343747729Z","response":" why","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:13.849074334Z","response":" we","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:14.428382283Z","response":" typically","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:14.975249303Z","response":" per","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:15.557414171Z","response":"ceive","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:16.179399225Z","response":" the","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:16.713970612Z","response":" sky","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:17.279799166Z","response":" as","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:17.749814713Z","response":" having","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:18.349225178Z","response":" a","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:18.874442601Z","response":" blue","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:19.385743625Z","response":" h","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:19.856165748Z","response":"ue","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:20.434154839Z","response":".","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:20.959613693Z","response":" However","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:21.477155944Z","response":",","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:21.948582002Z","response":" during","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:22.510912787Z","response":" sun","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:23.124877491Z","response":"rise","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:23.703203542Z","response":" or","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:24.197086988Z","response":" sun","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:24.731125053Z","response":"set","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:25.260788753Z","response":",","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:25.784992149Z","response":" the","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:26.29265038Z","response":" sky","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:26.838179737Z","response":" can","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:27.363118194Z","response":" take","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:28.101355293Z","response":" on","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:28.667340507Z","response":" various","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:29.197801841Z","response":" sh","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:29.757229536Z","response":"ades","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:30.283713028Z","response":" of","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:30.791915363Z","response":" red","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:31.309829303Z","response":",","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:31.842367364Z","response":" pink","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:32.371649431Z","response":",","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:32.900765864Z","response":" orange","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:33.422518694Z","response":",","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:34.002004535Z","response":" and","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:34.50465466Z","response":" purple","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:35.020001089Z","response":" due","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:35.552555833Z","response":" to","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:36.100933033Z","response":" the","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:36.624066249Z","response":" scattering","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:37.127360511Z","response":" of","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:37.645663874Z","response":" sunlight","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:38.188634483Z","response":" in","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:38.726616954Z","response":" the","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:39.478114703Z","response":" Earth","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:40.205710019Z","response":"'","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:40.717148082Z","response":"s","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:41.214359608Z","response":" atmosphere","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:41.753657558Z","response":" at","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:42.293513538Z","response":" those","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:42.831315764Z","response":" specific","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:43.325317833Z","response":" angles","done":false}
{"model":"mistral","created_at":"2024-04-26T16:08:43.851507537Z","response":".","done":false}
{"error":"unexpected server status: 1"}

Here are the logs from the docker container (I see no errors) :

text  error  warn  system  array  login  

{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":52940,"status":200,"tid":"23175901271616","timestamp":1714146582}
{"function":"launch_slot_with_data","level":"INFO","line":830,"msg":"slot is processing task","slot_id":0,"task_id":787,"tid":"23180484790144","timestamp":1714146582}
{"function":"update_slots","ga_i":0,"level":"INFO","line":1809,"msg":"slot progression","n_past":72,"n_past_se":0,"n_prompt_tokens_processed":22,"slot_id":0,"task_id":787,"tid":"23180484790144","timestamp":1714146582}
{"function":"update_slots","level":"INFO","line":1836,"msg":"kv cache rm [p0, end)","p0":72,"slot_id":0,"task_id":787,"tid":"23180484790144","timestamp":1714146582}
[GIN] 2024/04/26 - 15:50:19 | 200 | 36.865107759s |   192.168.1.167 | POST     "/api/generate"
{"function":"log_server_request","level":"INFO","line":2734,"method":"POST","msg":"request","params":{},"path":"/completion","remote_addr":"127.0.0.1","remote_port":52940,"status":200,"tid":"23175901271616","timestamp":1714146620}
{"function":"update_slots","level":"INFO","line":1640,"msg":"slot released","n_cache_tokens":152,"n_ctx":2048,"n_past":151,"n_system_tokens":0,"slot_id":0,"task_id":787,"tid":"23180484790144","timestamp":1714146620,"truncated":false}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":848,"tid":"23180484790144","timestamp":1714146654}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":41324,"status":200,"tid":"23175903372864","timestamp":1714146654}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":849,"tid":"23180484790144","timestamp":1714146654}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":41324,"status":200,"tid":"23175903372864","timestamp":1714146654}
{"function":"launch_slot_with_data","level":"INFO","line":830,"msg":"slot is processing task","slot_id":0,"task_id":850,"tid":"23180484790144","timestamp":1714146654}
{"function":"update_slots","ga_i":0,"level":"INFO","line":1809,"msg":"slot progression","n_past":72,"n_past_se":0,"n_prompt_tokens_processed":11,"slot_id":0,"task_id":850,"tid":"23180484790144","timestamp":1714146654}
{"function":"update_slots","level":"INFO","line":1836,"msg":"kv cache rm [p0, end)","p0":72,"slot_id":0,"task_id":850,"tid":"23180484790144","timestamp":1714146654}
{"function":"print_timings","level":"INFO","line":269,"msg":"prompt eval time     =    4190.76 ms /    11 tokens (  380.98 ms per token,     2.62 tokens per second)","n_prompt_tokens_processed":11,"n_tokens_second":2.624825359630902,"slot_id":0,"t_prompt_processing":4190.755,"t_token":380.9777272727273,"task_id":850,"tid":"23180484790144","timestamp":1714146690}
{"function":"print_timings","level":"INFO","line":283,"msg":"generation eval time =   31807.07 ms /    64 runs   (  496.99 ms per token,     2.01 tokens per second)","n_decoded":64,"n_tokens_second":2.0121314549373572,"slot_id":0,"t_token":496.985421875,"t_token_generation":31807.067,"task_id":850,"tid":"23180484790144","timestamp":1714146690}
{"function":"print_timings","level":"INFO","line":293,"msg":"          total time =   35997.82 ms","slot_id":0,"t_prompt_processing":4190.755,"t_token_generation":31807.067,"t_total":35997.822,"task_id":850,"tid":"23180484790144","timestamp":1714146690}
{"function":"log_server_request","level":"INFO","line":2734,"method":"POST","msg":"request","params":{},"path":"/completion","remote_addr":"127.0.0.1","remote_port":41324,"status":200,"tid":"23175903372864","timestamp":1714146690}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":0,"n_processing_slots":1,"task_id":916,"tid":"23180484790144","timestamp":1714146690}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":41324,"status":200,"tid":"23175903372864","timestamp":1714146690}
{"function":"update_slots","level":"INFO","line":1640,"msg":"slot released","n_cache_tokens":147,"n_ctx":2048,"n_past":146,"n_system_tokens":0,"slot_id":0,"task_id":850,"tid":"23180484790144","timestamp":1714146690,"truncated":false}
[GIN] 2024/04/26 - 15:51:30 | 500 | 36.085232311s |   192.168.1.167 | POST     "/api/generate"
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":918,"tid":"23180484790144","timestamp":1714146702}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":52920,"status":200,"tid":"23175899170368","timestamp":1714146702}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":919,"tid":"23180484790144","timestamp":1714146702}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":52920,"status":200,"tid":"23175899170368","timestamp":1714146702}
{"function":"launch_slot_with_data","level":"INFO","line":830,"msg":"slot is processing task","slot_id":0,"task_id":920,"tid":"23180484790144","timestamp":1714146702}
{"function":"update_slots","ga_i":0,"level":"INFO","line":1809,"msg":"slot progression","n_past":83,"n_past_se":0,"n_prompt_tokens_processed":0,"slot_id":0,"task_id":920,"tid":"23180484790144","timestamp":1714146702}
{"function":"update_slots","level":"INFO","line":1824,"msg":"we have to evaluate at least 1 token to generate logits","slot_id":0,"task_id":920,"tid":"23180484790144","timestamp":1714146702}
{"function":"update_slots","level":"INFO","line":1836,"msg":"kv cache rm [p0, end)","p0":82,"slot_id":0,"task_id":920,"tid":"23180484790144","timestamp":1714146702}
[GIN] 2024/04/26 - 15:52:19 | 200 | 37.126512884s |   192.168.1.167 | POST     "/api/generate"
{"function":"log_server_request","level":"INFO","line":2734,"method":"POST","msg":"request","params":{},"path":"/completion","remote_addr":"127.0.0.1","remote_port":52920,"status":200,"tid":"23175899170368","timestamp":1714146740}
{"function":"update_slots","level":"INFO","line":1640,"msg":"slot released","n_cache_tokens":157,"n_ctx":2048,"n_past":156,"n_system_tokens":0,"slot_id":0,"task_id":920,"tid":"23180484790144","timestamp":1714146740,"truncated":false}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":997,"tid":"23180484790144","timestamp":1714146772}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":60708,"status":200,"tid":"23175901271616","timestamp":1714146772}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":998,"tid":"23180484790144","timestamp":1714146772}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":60708,"status":200,"tid":"23175901271616","timestamp":1714146772}
{"function":"launch_slot_with_data","level":"INFO","line":830,"msg":"slot is processing task","slot_id":0,"task_id":999,"tid":"23180484790144","timestamp":1714146772}
{"function":"update_slots","ga_i":0,"level":"INFO","line":1809,"msg":"slot progression","n_past":59,"n_past_se":0,"n_prompt_tokens_processed":26,"slot_id":0,"task_id":999,"tid":"23180484790144","timestamp":1714146772}
{"function":"update_slots","level":"INFO","line":1836,"msg":"kv cache rm [p0, end)","p0":59,"slot_id":0,"task_id":999,"tid":"23180484790144","timestamp":1714146772}
{"function":"print_timings","level":"INFO","line":269,"msg":"prompt eval time     =    9954.13 ms /    26 tokens (  382.85 ms per token,     2.61 tokens per second)","n_prompt_tokens_processed":26,"n_tokens_second":2.611980632766373,"slot_id":0,"t_prompt_processing":9954.132,"t_token":382.85123076923077,"task_id":999,"tid":"23180484790144","timestamp":1714146816}
{"function":"print_timings","level":"INFO","line":283,"msg":"generation eval time =   34261.63 ms /    69 runs   (  496.55 ms per token,     2.01 tokens per second)","n_decoded":69,"n_tokens_second":2.0139148087183716,"slot_id":0,"t_token":496.5453333333333,"t_token_generation":34261.628,"task_id":999,"tid":"23180484790144","timestamp":1714146816}
{"function":"print_timings","level":"INFO","line":293,"msg":"          total time =   44215.76 ms","slot_id":0,"t_prompt_processing":9954.132,"t_token_generation":34261.628,"t_total":44215.759999999995,"task_id":999,"tid":"23180484790144","timestamp":1714146816}
{"function":"log_server_request","level":"INFO","line":2734,"method":"POST","msg":"request","params":{},"path":"/completion","remote_addr":"127.0.0.1","remote_port":60708,"status":200,"tid":"23175901271616","timestamp":1714146816}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":0,"n_processing_slots":1,"task_id":1070,"tid":"23180484790144","timestamp":1714146816}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":60708,"status":200,"tid":"23175901271616","timestamp":1714146816}
{"function":"update_slots","level":"INFO","line":1640,"msg":"slot released","n_cache_tokens":154,"n_ctx":2048,"n_past":153,"n_system_tokens":0,"slot_id":0,"task_id":999,"tid":"23180484790144","timestamp":1714146816,"truncated":false}
[GIN] 2024/04/26 - 15:53:36 | 500 | 44.303565407s |   192.168.1.167 | POST     "/api/generate"
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":1072,"tid":"23180484790144","timestamp":1714146826}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":43070,"status":200,"tid":"23175903372864","timestamp":1714146826}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":1073,"tid":"23180484790144","timestamp":1714146826}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":43070,"status":200,"tid":"23175903372864","timestamp":1714146826}
{"function":"launch_slot_with_data","level":"INFO","line":830,"msg":"slot is processing task","slot_id":0,"task_id":1074,"tid":"23180484790144","timestamp":1714146826}
{"function":"update_slots","ga_i":0,"level":"INFO","line":1809,"msg":"slot progression","n_past":85,"n_past_se":0,"n_prompt_tokens_processed":0,"slot_id":0,"task_id":1074,"tid":"23180484790144","timestamp":1714146826}
{"function":"update_slots","level":"INFO","line":1824,"msg":"we have to evaluate at least 1 token to generate logits","slot_id":0,"task_id":1074,"tid":"23180484790144","timestamp":1714146826}
{"function":"update_slots","level":"INFO","line":1836,"msg":"kv cache rm [p0, end)","p0":84,"slot_id":0,"task_id":1074,"tid":"23180484790144","timestamp":1714146826}
{"function":"print_timings","level":"INFO","line":269,"msg":"prompt eval time     =     517.12 ms /     0 tokens (     inf ms per token,     0.00 tokens per second)","n_prompt_tokens_processed":0,"n_tokens_second":0.0,"slot_id":0,"t_prompt_processing":517.12,"t_token":null,"task_id":1074,"tid":"23180484790144","timestamp":1714146893}
{"function":"print_timings","level":"INFO","line":283,"msg":"generation eval time =   66105.63 ms /   119 runs   (  555.51 ms per token,     1.80 tokens per second)","n_decoded":119,"n_tokens_second":1.8001493549126968,"slot_id":0,"t_token":555.509462184874,"t_token_generation":66105.626,"task_id":1074,"tid":"23180484790144","timestamp":1714146893}
{"function":"print_timings","level":"INFO","line":293,"msg":"          total time =   66622.75 ms","slot_id":0,"t_prompt_processing":517.12,"t_token_generation":66105.626,"t_total":66622.746,"task_id":1074,"tid":"23180484790144","timestamp":1714146893}
{"function":"log_server_request","level":"INFO","line":2734,"method":"POST","msg":"request","params":{},"path":"/completion","remote_addr":"127.0.0.1","remote_port":43070,"status":200,"tid":"23175903372864","timestamp":1714146893}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":0,"n_processing_slots":1,"task_id":1195,"tid":"23180484790144","timestamp":1714146893}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":43070,"status":200,"tid":"23175903372864","timestamp":1714146893}
{"function":"update_slots","level":"INFO","line":1640,"msg":"slot released","n_cache_tokens":204,"n_ctx":2048,"n_past":203,"n_system_tokens":0,"slot_id":0,"task_id":1074,"tid":"23180484790144","timestamp":1714146893,"truncated":false}
[GIN] 2024/04/26 - 15:54:53 | 500 |          1m6s |   192.168.1.167 | POST     "/api/generate"
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":1197,"tid":"23180484790144","timestamp":1714146898}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":57848,"status":200,"tid":"23175899170368","timestamp":1714146898}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":1198,"tid":"23180484790144","timestamp":1714146898}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":57848,"status":200,"tid":"23175899170368","timestamp":1714146898}
{"function":"launch_slot_with_data","level":"INFO","line":830,"msg":"slot is processing task","slot_id":0,"task_id":1199,"tid":"23180484790144","timestamp":1714146898}
{"function":"update_slots","ga_i":0,"level":"INFO","line":1809,"msg":"slot progression","n_past":85,"n_past_se":0,"n_prompt_tokens_processed":0,"slot_id":0,"task_id":1199,"tid":"23180484790144","timestamp":1714146898}
{"function":"update_slots","level":"INFO","line":1824,"msg":"we have to evaluate at least 1 token to generate logits","slot_id":0,"task_id":1199,"tid":"23180484790144","timestamp":1714146898}
{"function":"update_slots","level":"INFO","line":1836,"msg":"kv cache rm [p0, end)","p0":84,"slot_id":0,"task_id":1199,"tid":"23180484790144","timestamp":1714146898}
[GIN] 2024/04/26 - 15:56:21 | 200 |         1m23s |   192.168.1.167 | POST     "/api/generate"
{"function":"log_server_request","level":"INFO","line":2734,"method":"POST","msg":"request","params":{},"path":"/completion","remote_addr":"127.0.0.1","remote_port":57848,"status":200,"tid":"23175899170368","timestamp":1714146982}
{"function":"update_slots","level":"INFO","line":1640,"msg":"slot released","n_cache_tokens":235,"n_ctx":2048,"n_past":234,"n_system_tokens":0,"slot_id":0,"task_id":1199,"tid":"23180484790144","timestamp":1714146982,"truncated":false}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":1352,"tid":"23180484790144","timestamp":1714147011}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":53832,"status":200,"tid":"23175901271616","timestamp":1714147011}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":1353,"tid":"23180484790144","timestamp":1714147011}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":53832,"status":200,"tid":"23175901271616","timestamp":1714147011}
{"function":"launch_slot_with_data","level":"INFO","line":830,"msg":"slot is processing task","slot_id":0,"task_id":1354,"tid":"23180484790144","timestamp":1714147011}
{"function":"update_slots","ga_i":0,"level":"INFO","line":1809,"msg":"slot progression","n_past":74,"n_past_se":0,"n_prompt_tokens_processed":4,"slot_id":0,"task_id":1354,"tid":"23180484790144","timestamp":1714147011}
{"function":"update_slots","level":"INFO","line":1836,"msg":"kv cache rm [p0, end)","p0":74,"slot_id":0,"task_id":1354,"tid":"23180484790144","timestamp":1714147011}
{"function":"print_timings","level":"INFO","line":269,"msg":"prompt eval time     =    1759.11 ms /     4 tokens (  439.78 ms per token,     2.27 tokens per second)","n_prompt_tokens_processed":4,"n_tokens_second":2.2738797163107667,"slot_id":0,"t_prompt_processing":1759.108,"t_token":439.777,"task_id":1354,"tid":"23180484790144","timestamp":1714147065}
{"function":"print_timings","level":"INFO","line":283,"msg":"generation eval time =   52489.85 ms /    98 runs   (  535.61 ms per token,     1.87 tokens per second)","n_decoded":98,"n_tokens_second":1.867027589771592,"slot_id":0,"t_token":535.610724489796,"t_token_generation":52489.851,"task_id":1354,"tid":"23180484790144","timestamp":1714147065}
{"function":"print_timings","level":"INFO","line":293,"msg":"          total time =   54248.96 ms","slot_id":0,"t_prompt_processing":1759.108,"t_token_generation":52489.851,"t_total":54248.959,"task_id":1354,"tid":"23180484790144","timestamp":1714147065}
{"function":"log_server_request","level":"INFO","line":2734,"method":"POST","msg":"request","params":{},"path":"/completion","remote_addr":"127.0.0.1","remote_port":53832,"status":200,"tid":"23175901271616","timestamp":1714147065}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":0,"n_processing_slots":1,"task_id":1454,"tid":"23180484790144","timestamp":1714147065}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":34160,"status":200,"tid":"23175903372864","timestamp":1714147065}
[GIN] 2024/04/26 - 15:57:45 | 500 |  54.29739368s |   192.168.1.167 | POST     "/api/generate"
{"function":"update_slots","level":"INFO","line":1640,"msg":"slot released","n_cache_tokens":176,"n_ctx":2048,"n_past":175,"n_system_tokens":0,"slot_id":0,"task_id":1354,"tid":"23180484790144","timestamp":1714147065,"truncated":false}
time=2024-04-26T16:06:50.536Z level=INFO source=gpu.go:121 msg="Detecting GPU type"
time=2024-04-26T16:06:50.536Z level=INFO source=gpu.go:268 msg="Searching for GPU management library libcudart.so*"
time=2024-04-26T16:06:50.537Z level=INFO source=gpu.go:314 msg="Discovered GPU libraries: [/tmp/ollama3539318188/runners/cuda_v11/libcudart.so.11.0]"
time=2024-04-26T16:06:50.579Z level=INFO source=gpu.go:343 msg="Unable to load cudart CUDA management library /tmp/ollama3539318188/runners/cuda_v11/libcudart.so.11.0: your nvidia driver is too old or missing, please upgrade to run ollama"
time=2024-04-26T16:06:50.579Z level=INFO source=gpu.go:268 msg="Searching for GPU management library libnvidia-ml.so"
time=2024-04-26T16:06:50.580Z level=INFO source=gpu.go:314 msg="Discovered GPU libraries: []"
time=2024-04-26T16:06:50.580Z level=INFO source=cpu_common.go:11 msg="CPU has AVX2"
time=2024-04-26T16:06:50.580Z level=INFO source=gpu.go:121 msg="Detecting GPU type"
time=2024-04-26T16:06:50.580Z level=INFO source=gpu.go:268 msg="Searching for GPU management library libcudart.so*"
time=2024-04-26T16:06:50.581Z level=INFO source=gpu.go:314 msg="Discovered GPU libraries: [/tmp/ollama3539318188/runners/cuda_v11/libcudart.so.11.0]"
time=2024-04-26T16:06:50.581Z level=INFO source=gpu.go:343 msg="Unable to load cudart CUDA management library /tmp/ollama3539318188/runners/cuda_v11/libcudart.so.11.0: your nvidia driver is too old or missing, please upgrade to run ollama"
time=2024-04-26T16:06:50.582Z level=INFO source=gpu.go:268 msg="Searching for GPU management library libnvidia-ml.so"
time=2024-04-26T16:06:50.582Z level=INFO source=gpu.go:314 msg="Discovered GPU libraries: []"
time=2024-04-26T16:06:50.583Z level=INFO source=cpu_common.go:11 msg="CPU has AVX2"
time=2024-04-26T16:06:50.583Z level=INFO source=server.go:127 msg="offload to gpu" reallayers=0 layers=0 required="4267.5 MiB" used="181.0 MiB" available="0 B" kv="256.0 MiB" fulloffload="164.0 MiB" partialoffload="181.0 MiB"
time=2024-04-26T16:06:50.584Z level=INFO source=server.go:264 msg="starting llama server" cmd="/tmp/ollama3539318188/runners/cpu_avx2/ollama_llama_server --model /root/.ollama/models/blobs/sha256-e8a35b5937a5e6d5c35d1f2a15f161e07eefe5e5bb0a3cdd42998ee79b057730 --ctx-size 2048 --batch-size 512 --embedding --log-disable --n-gpu-layers 0 --port 39645"
time=2024-04-26T16:06:50.585Z level=INFO source=server.go:389 msg="waiting for llama runner to start responding"
{"function":"server_params_parse","level":"INFO","line":2603,"msg":"logging to file is disabled.","tid":"22658407044992","timestamp":1714147610}
{"function":"server_params_parse","level":"WARN","line":2380,"msg":"Not compiled with GPU offload support, --n-gpu-layers option will be ignored. See main README.md for information on enabling GPU BLAS support","n_gpu_layers":-1,"tid":"22658407044992","timestamp":1714147610}
{"build":1,"commit":"7593639","function":"main","level":"INFO","line":2819,"msg":"build info","tid":"22658407044992","timestamp":1714147610}
{"function":"main","level":"INFO","line":2822,"msg":"system info","n_threads":1,"n_threads_batch":-1,"system_info":"AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | ","tid":"22658407044992","timestamp":1714147610,"total_threads":1}
llama_model_loader: loaded meta data with 24 key-value pairs and 291 tensors from /root/.ollama/models/blobs/sha256-e8a35b5937a5e6d5c35d1f2a15f161e07eefe5e5bb0a3cdd42998ee79b057730 (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              = llama
llama_model_loader: - kv   1:                               general.name str              = mistralai
llama_model_loader: - kv   2:                       llama.context_length u32              = 32768
llama_model_loader: - kv   3:                     llama.embedding_length u32              = 4096
llama_model_loader: - kv   4:                          llama.block_count u32              = 32
llama_model_loader: - kv   5:                  llama.feed_forward_length u32              = 14336
llama_model_loader: - kv   6:                 llama.rope.dimension_count u32              = 128
llama_model_loader: - kv   7:                 llama.attention.head_count u32              = 32
llama_model_loader: - kv   8:              llama.attention.head_count_kv u32              = 8
llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  10:                       llama.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  11:                          general.file_type u32              = 2
llama_model_loader: - kv  12:                       tokenizer.ggml.model str              = llama
llama_model_loader: - kv  13:                      tokenizer.ggml.tokens arr[str,32000]   = ["<unk>", "<s>", "</s>", "<0x00>", "<...
llama_model_loader: - kv  14:                      tokenizer.ggml.scores arr[f32,32000]   = [0.000000, 0.000000, 0.000000, 0.0000...
llama_model_loader: - kv  15:                  tokenizer.ggml.token_type arr[i32,32000]   = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
llama_model_loader: - kv  16:                      tokenizer.ggml.merges arr[str,58980]   = ["▁ t", "i n", "e r", "▁ a", "h e...
llama_model_loader: - kv  17:                tokenizer.ggml.bos_token_id u32              = 1
llama_model_loader: - kv  18:                tokenizer.ggml.eos_token_id u32              = 2
llama_model_loader: - kv  19:            tokenizer.ggml.unknown_token_id u32              = 0
llama_model_loader: - kv  20:               tokenizer.ggml.add_bos_token bool             = true
llama_model_loader: - kv  21:               tokenizer.ggml.add_eos_token bool             = false
llama_model_loader: - kv  22:                    tokenizer.chat_template str              = {{ bos_token }}{% for message in mess...
llama_model_loader: - kv  23:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:   65 tensors
llama_model_loader: - type q4_0:  225 tensors
llama_model_loader: - type q6_K:    1 tensors
llm_load_vocab: special tokens definition check successful ( 259/32000 ).
llm_load_print_meta: format           = GGUF V3 (latest)
llm_load_print_meta: arch             = llama
llm_load_print_meta: vocab type       = SPM
llm_load_print_meta: n_vocab          = 32000
llm_load_print_meta: n_merges         = 0
llm_load_print_meta: n_ctx_train      = 32768
llm_load_print_meta: n_embd           = 4096
llm_load_print_meta: n_head           = 32
llm_load_print_meta: n_head_kv        = 8
llm_load_print_meta: n_layer          = 32
llm_load_print_meta: n_rot            = 128
llm_load_print_meta: n_embd_head_k    = 128
llm_load_print_meta: n_embd_head_v    = 128
llm_load_print_meta: n_gqa            = 4
llm_load_print_meta: n_embd_k_gqa     = 1024
llm_load_print_meta: n_embd_v_gqa     = 1024
llm_load_print_meta: f_norm_eps       = 0.0e+00
llm_load_print_meta: f_norm_rms_eps   = 1.0e-05
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: f_logit_scale    = 0.0e+00
llm_load_print_meta: n_ff             = 14336
llm_load_print_meta: n_expert         = 0
llm_load_print_meta: n_expert_used    = 0
llm_load_print_meta: causal attn      = 1
llm_load_print_meta: pooling type     = 0
llm_load_print_meta: rope type        = 0
llm_load_print_meta: rope scaling     = linear
llm_load_print_meta: freq_base_train  = 1000000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_yarn_orig_ctx  = 32768
llm_load_print_meta: rope_finetuned   = unknown
llm_load_print_meta: ssm_d_conv       = 0
llm_load_print_meta: ssm_d_inner      = 0
llm_load_print_meta: ssm_d_state      = 0
llm_load_print_meta: ssm_dt_rank      = 0
llm_load_print_meta: model type       = 7B
llm_load_print_meta: model ftype      = Q4_0
llm_load_print_meta: model params     = 7.24 B
llm_load_print_meta: model size       = 3.83 GiB (4.54 BPW) 
llm_load_print_meta: general.name     = mistralai
llm_load_print_meta: BOS token        = 1 '<s>'
llm_load_print_meta: EOS token        = 2 '</s>'
llm_load_print_meta: UNK token        = 0 '<unk>'
llm_load_print_meta: LF token         = 13 '<0x0A>'
llm_load_tensors: ggml ctx size =    0.11 MiB
llm_load_tensors:        CPU buffer size =  3917.87 MiB
..................................................................................................
llama_new_context_with_model: n_ctx      = 2048
llama_new_context_with_model: n_batch    = 512
llama_new_context_with_model: n_ubatch   = 512
llama_new_context_with_model: freq_base  = 1000000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init:        CPU 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  output buffer size =     0.14 MiB
llama_new_context_with_model:        CPU compute buffer size =   164.01 MiB
llama_new_context_with_model: graph nodes  = 1030
llama_new_context_with_model: graph splits = 1
{"function":"initialize","level":"INFO","line":448,"msg":"initializing slots","n_slots":1,"tid":"22658407044992","timestamp":1714147640}
{"function":"initialize","level":"INFO","line":457,"msg":"new slot","n_ctx_slot":2048,"slot_id":0,"tid":"22658407044992","timestamp":1714147640}
{"function":"main","level":"INFO","line":3064,"msg":"model loaded","tid":"22658407044992","timestamp":1714147640}
{"function":"main","hostname":"127.0.0.1","level":"INFO","line":3267,"msg":"HTTP server listening","n_threads_http":"3","port":"39645","tid":"22658407044992","timestamp":1714147640}
{"function":"update_slots","level":"INFO","line":1578,"msg":"all slots are idle and system prompt is empty, clear the KV cache","tid":"22658407044992","timestamp":1714147640}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":0,"tid":"22658407044992","timestamp":1714147640}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":44072,"status":200,"tid":"22653821568576","timestamp":1714147640}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":1,"tid":"22658407044992","timestamp":1714147640}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":44078,"status":200,"tid":"22653821568576","timestamp":1714147640}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":2,"tid":"22658407044992","timestamp":1714147640}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":44094,"status":200,"tid":"22653821568576","timestamp":1714147640}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":3,"tid":"22658407044992","timestamp":1714147640}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":44102,"status":200,"tid":"22653821568576","timestamp":1714147640}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":4,"tid":"22658407044992","timestamp":1714147640}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":44120,"status":200,"tid":"22653821568576","timestamp":1714147640}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":5,"tid":"22658407044992","timestamp":1714147640}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":44116,"status":200,"tid":"22653823669824","timestamp":1714147640}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":6,"tid":"22658407044992","timestamp":1714147641}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":44942,"status":200,"tid":"22653823669824","timestamp":1714147641}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":7,"tid":"22658407044992","timestamp":1714147641}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":44942,"status":200,"tid":"22653823669824","timestamp":1714147641}
{"function":"launch_slot_with_data","level":"INFO","line":830,"msg":"slot is processing task","slot_id":0,"task_id":8,"tid":"22658407044992","timestamp":1714147641}
{"function":"update_slots","ga_i":0,"level":"INFO","line":1809,"msg":"slot progression","n_past":0,"n_past_se":0,"n_prompt_tokens_processed":15,"slot_id":0,"task_id":8,"tid":"22658407044992","timestamp":1714147641}
{"function":"update_slots","level":"INFO","line":1836,"msg":"kv cache rm [p0, end)","p0":0,"slot_id":0,"task_id":8,"tid":"22658407044992","timestamp":1714147641}
[GIN] 2024/04/26 - 16:07:21 | 200 |      66.373µs |       127.0.0.1 | GET      "/api/version"
{"function":"print_timings","level":"INFO","line":269,"msg":"prompt eval time     =    6808.76 ms /    15 tokens (  453.92 ms per token,     2.20 tokens per second)","n_prompt_tokens_processed":15,"n_tokens_second":2.2030430192616457,"slot_id":0,"t_prompt_processing":6808.764,"t_token":453.9176,"task_id":8,"tid":"22658407044992","timestamp":1714147724}
{"function":"print_timings","level":"INFO","line":283,"msg":"generation eval time =   76398.96 ms /   141 runs   (  541.84 ms per token,     1.85 tokens per second)","n_decoded":141,"n_tokens_second":1.845574957856754,"slot_id":0,"t_token":541.8365673758866,"t_token_generation":76398.956,"task_id":8,"tid":"22658407044992","timestamp":1714147724}
{"function":"print_timings","level":"INFO","line":293,"msg":"          total time =   83207.72 ms","slot_id":0,"t_prompt_processing":6808.764,"t_token_generation":76398.956,"t_total":83207.72,"task_id":8,"tid":"22658407044992","timestamp":1714147724}
{"function":"log_server_request","level":"INFO","line":2734,"method":"POST","msg":"request","params":{},"path":"/completion","remote_addr":"127.0.0.1","remote_port":44942,"status":200,"tid":"22653823669824","timestamp":1714147724}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":0,"n_processing_slots":1,"task_id":151,"tid":"22658407044992","timestamp":1714147724}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":44942,"status":200,"tid":"22653823669824","timestamp":1714147724}
{"function":"update_slots","level":"INFO","line":1640,"msg":"slot released","n_cache_tokens":156,"n_ctx":2048,"n_past":155,"n_system_tokens":0,"slot_id":0,"task_id":8,"tid":"22658407044992","timestamp":1714147724,"truncated":false}
[GIN] 2024/04/26 - 16:08:44 | 200 |         1m57s |   192.168.1.167 | POST     "/api/generate"

OS

Linux

GPU

Other

CPU

Intel

Ollama version

0.1.32

Originally created by @ronangaillard on GitHub (Apr 26, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3949 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? EDIT : I tried with `0.1.29` and I don't have the issue Hello, I'm using docker image, tag latest without any GPU. I downloaded mistral model, and I'm trying to generate answers using the promt from the doc (I have the same issue with llama model) : ``` curl http://localhost:11434/api/generate -d '{ "model": "llama2", "prompt": "Why is the sky blue?" }' ``` But often (not always) I get an error 500 even though tokens have been generated. I know tokens have been generated because I see them in the API response. API response : ``` {"model":"mistral","created_at":"2024-04-26T16:07:28.07709035Z","response":" The","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:28.631254126Z","response":" color","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:29.18215074Z","response":" of","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:29.664237413Z","response":" the","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:30.273469909Z","response":" sky","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:30.781810227Z","response":" appears","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:31.40826255Z","response":" blue","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:31.989479606Z","response":" due","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:32.525336503Z","response":" to","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:33.026269498Z","response":" a","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:33.549170938Z","response":" process","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:34.081219456Z","response":" called","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:34.619630847Z","response":" Ray","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:35.137036869Z","response":"le","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:35.704325551Z","response":"igh","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:36.267680082Z","response":" scattering","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:36.793143541Z","response":".","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:37.282849465Z","response":" As","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:37.842596991Z","response":" sunlight","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:38.38296667Z","response":" reaches","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:38.903363958Z","response":" Earth","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:39.726083579Z","response":"'","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:40.494767417Z","response":"s","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:41.06925115Z","response":" atmosphere","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:41.613843427Z","response":",","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:42.128205209Z","response":" it","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:42.667473181Z","response":" inter","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:43.173160182Z","response":"acts","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:43.716459779Z","response":" with","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:44.268444653Z","response":" different","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:44.817945821Z","response":" g","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:45.426567347Z","response":"ases","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:45.932192978Z","response":" and","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:46.498713045Z","response":" particles","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:47.052741443Z","response":" in","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:47.580913744Z","response":" the","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:48.090460265Z","response":" air","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:48.596333364Z","response":".","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:49.115045502Z","response":" Blue","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:49.642993369Z","response":" light","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:50.18264068Z","response":" has","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:50.685417256Z","response":" a","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:51.19918961Z","response":" shorter","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:51.836339325Z","response":" w","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:52.320055654Z","response":"avelength","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:52.947997012Z","response":" and","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:53.441787158Z","response":" gets","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:53.990117921Z","response":" scattered","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:54.46448626Z","response":" more","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:55.003384218Z","response":" easily","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:55.475699829Z","response":" than","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:56.062239913Z","response":" other","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:56.576008126Z","response":" colors","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:57.275554243Z","response":",","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:57.874225128Z","response":" such","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:58.451544809Z","response":" as","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:58.937056211Z","response":" red","done":false} {"model":"mistral","created_at":"2024-04-26T16:07:59.49227394Z","response":" or","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:00.030899371Z","response":" yellow","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:00.573231159Z","response":".","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:01.060011721Z","response":" As","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:01.59222445Z","response":" a","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:02.25517787Z","response":" result","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:02.741180311Z","response":",","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:03.243095355Z","response":" when","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:03.759198116Z","response":" we","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:04.293691209Z","response":" look","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:04.830839629Z","response":" up","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:05.34726204Z","response":" at","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:05.871421624Z","response":" the","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:06.423681143Z","response":" sky","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:06.931967006Z","response":",","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:07.473513959Z","response":" we","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:07.989916516Z","response":" predomin","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:08.595876379Z","response":"antly","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:09.109355685Z","response":" see","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:09.616627341Z","response":" the","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:10.167182816Z","response":" scattered","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:10.697195496Z","response":" blue","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:11.227974595Z","response":" light","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:11.722090129Z","response":".","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:12.25041971Z","response":" This","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:12.829180966Z","response":" is","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:13.343747729Z","response":" why","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:13.849074334Z","response":" we","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:14.428382283Z","response":" typically","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:14.975249303Z","response":" per","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:15.557414171Z","response":"ceive","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:16.179399225Z","response":" the","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:16.713970612Z","response":" sky","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:17.279799166Z","response":" as","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:17.749814713Z","response":" having","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:18.349225178Z","response":" a","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:18.874442601Z","response":" blue","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:19.385743625Z","response":" h","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:19.856165748Z","response":"ue","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:20.434154839Z","response":".","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:20.959613693Z","response":" However","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:21.477155944Z","response":",","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:21.948582002Z","response":" during","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:22.510912787Z","response":" sun","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:23.124877491Z","response":"rise","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:23.703203542Z","response":" or","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:24.197086988Z","response":" sun","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:24.731125053Z","response":"set","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:25.260788753Z","response":",","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:25.784992149Z","response":" the","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:26.29265038Z","response":" sky","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:26.838179737Z","response":" can","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:27.363118194Z","response":" take","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:28.101355293Z","response":" on","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:28.667340507Z","response":" various","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:29.197801841Z","response":" sh","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:29.757229536Z","response":"ades","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:30.283713028Z","response":" of","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:30.791915363Z","response":" red","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:31.309829303Z","response":",","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:31.842367364Z","response":" pink","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:32.371649431Z","response":",","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:32.900765864Z","response":" orange","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:33.422518694Z","response":",","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:34.002004535Z","response":" and","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:34.50465466Z","response":" purple","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:35.020001089Z","response":" due","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:35.552555833Z","response":" to","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:36.100933033Z","response":" the","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:36.624066249Z","response":" scattering","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:37.127360511Z","response":" of","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:37.645663874Z","response":" sunlight","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:38.188634483Z","response":" in","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:38.726616954Z","response":" the","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:39.478114703Z","response":" Earth","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:40.205710019Z","response":"'","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:40.717148082Z","response":"s","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:41.214359608Z","response":" atmosphere","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:41.753657558Z","response":" at","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:42.293513538Z","response":" those","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:42.831315764Z","response":" specific","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:43.325317833Z","response":" angles","done":false} {"model":"mistral","created_at":"2024-04-26T16:08:43.851507537Z","response":".","done":false} {"error":"unexpected server status: 1"} ``` Here are the logs from the docker container (I see no errors) : ``` text error warn system array login {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":52940,"status":200,"tid":"23175901271616","timestamp":1714146582} {"function":"launch_slot_with_data","level":"INFO","line":830,"msg":"slot is processing task","slot_id":0,"task_id":787,"tid":"23180484790144","timestamp":1714146582} {"function":"update_slots","ga_i":0,"level":"INFO","line":1809,"msg":"slot progression","n_past":72,"n_past_se":0,"n_prompt_tokens_processed":22,"slot_id":0,"task_id":787,"tid":"23180484790144","timestamp":1714146582} {"function":"update_slots","level":"INFO","line":1836,"msg":"kv cache rm [p0, end)","p0":72,"slot_id":0,"task_id":787,"tid":"23180484790144","timestamp":1714146582} [GIN] 2024/04/26 - 15:50:19 | 200 | 36.865107759s | 192.168.1.167 | POST "/api/generate" {"function":"log_server_request","level":"INFO","line":2734,"method":"POST","msg":"request","params":{},"path":"/completion","remote_addr":"127.0.0.1","remote_port":52940,"status":200,"tid":"23175901271616","timestamp":1714146620} {"function":"update_slots","level":"INFO","line":1640,"msg":"slot released","n_cache_tokens":152,"n_ctx":2048,"n_past":151,"n_system_tokens":0,"slot_id":0,"task_id":787,"tid":"23180484790144","timestamp":1714146620,"truncated":false} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":848,"tid":"23180484790144","timestamp":1714146654} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":41324,"status":200,"tid":"23175903372864","timestamp":1714146654} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":849,"tid":"23180484790144","timestamp":1714146654} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":41324,"status":200,"tid":"23175903372864","timestamp":1714146654} {"function":"launch_slot_with_data","level":"INFO","line":830,"msg":"slot is processing task","slot_id":0,"task_id":850,"tid":"23180484790144","timestamp":1714146654} {"function":"update_slots","ga_i":0,"level":"INFO","line":1809,"msg":"slot progression","n_past":72,"n_past_se":0,"n_prompt_tokens_processed":11,"slot_id":0,"task_id":850,"tid":"23180484790144","timestamp":1714146654} {"function":"update_slots","level":"INFO","line":1836,"msg":"kv cache rm [p0, end)","p0":72,"slot_id":0,"task_id":850,"tid":"23180484790144","timestamp":1714146654} {"function":"print_timings","level":"INFO","line":269,"msg":"prompt eval time = 4190.76 ms / 11 tokens ( 380.98 ms per token, 2.62 tokens per second)","n_prompt_tokens_processed":11,"n_tokens_second":2.624825359630902,"slot_id":0,"t_prompt_processing":4190.755,"t_token":380.9777272727273,"task_id":850,"tid":"23180484790144","timestamp":1714146690} {"function":"print_timings","level":"INFO","line":283,"msg":"generation eval time = 31807.07 ms / 64 runs ( 496.99 ms per token, 2.01 tokens per second)","n_decoded":64,"n_tokens_second":2.0121314549373572,"slot_id":0,"t_token":496.985421875,"t_token_generation":31807.067,"task_id":850,"tid":"23180484790144","timestamp":1714146690} {"function":"print_timings","level":"INFO","line":293,"msg":" total time = 35997.82 ms","slot_id":0,"t_prompt_processing":4190.755,"t_token_generation":31807.067,"t_total":35997.822,"task_id":850,"tid":"23180484790144","timestamp":1714146690} {"function":"log_server_request","level":"INFO","line":2734,"method":"POST","msg":"request","params":{},"path":"/completion","remote_addr":"127.0.0.1","remote_port":41324,"status":200,"tid":"23175903372864","timestamp":1714146690} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":0,"n_processing_slots":1,"task_id":916,"tid":"23180484790144","timestamp":1714146690} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":41324,"status":200,"tid":"23175903372864","timestamp":1714146690} {"function":"update_slots","level":"INFO","line":1640,"msg":"slot released","n_cache_tokens":147,"n_ctx":2048,"n_past":146,"n_system_tokens":0,"slot_id":0,"task_id":850,"tid":"23180484790144","timestamp":1714146690,"truncated":false} [GIN] 2024/04/26 - 15:51:30 | 500 | 36.085232311s | 192.168.1.167 | POST "/api/generate" {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":918,"tid":"23180484790144","timestamp":1714146702} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":52920,"status":200,"tid":"23175899170368","timestamp":1714146702} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":919,"tid":"23180484790144","timestamp":1714146702} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":52920,"status":200,"tid":"23175899170368","timestamp":1714146702} {"function":"launch_slot_with_data","level":"INFO","line":830,"msg":"slot is processing task","slot_id":0,"task_id":920,"tid":"23180484790144","timestamp":1714146702} {"function":"update_slots","ga_i":0,"level":"INFO","line":1809,"msg":"slot progression","n_past":83,"n_past_se":0,"n_prompt_tokens_processed":0,"slot_id":0,"task_id":920,"tid":"23180484790144","timestamp":1714146702} {"function":"update_slots","level":"INFO","line":1824,"msg":"we have to evaluate at least 1 token to generate logits","slot_id":0,"task_id":920,"tid":"23180484790144","timestamp":1714146702} {"function":"update_slots","level":"INFO","line":1836,"msg":"kv cache rm [p0, end)","p0":82,"slot_id":0,"task_id":920,"tid":"23180484790144","timestamp":1714146702} [GIN] 2024/04/26 - 15:52:19 | 200 | 37.126512884s | 192.168.1.167 | POST "/api/generate" {"function":"log_server_request","level":"INFO","line":2734,"method":"POST","msg":"request","params":{},"path":"/completion","remote_addr":"127.0.0.1","remote_port":52920,"status":200,"tid":"23175899170368","timestamp":1714146740} {"function":"update_slots","level":"INFO","line":1640,"msg":"slot released","n_cache_tokens":157,"n_ctx":2048,"n_past":156,"n_system_tokens":0,"slot_id":0,"task_id":920,"tid":"23180484790144","timestamp":1714146740,"truncated":false} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":997,"tid":"23180484790144","timestamp":1714146772} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":60708,"status":200,"tid":"23175901271616","timestamp":1714146772} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":998,"tid":"23180484790144","timestamp":1714146772} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":60708,"status":200,"tid":"23175901271616","timestamp":1714146772} {"function":"launch_slot_with_data","level":"INFO","line":830,"msg":"slot is processing task","slot_id":0,"task_id":999,"tid":"23180484790144","timestamp":1714146772} {"function":"update_slots","ga_i":0,"level":"INFO","line":1809,"msg":"slot progression","n_past":59,"n_past_se":0,"n_prompt_tokens_processed":26,"slot_id":0,"task_id":999,"tid":"23180484790144","timestamp":1714146772} {"function":"update_slots","level":"INFO","line":1836,"msg":"kv cache rm [p0, end)","p0":59,"slot_id":0,"task_id":999,"tid":"23180484790144","timestamp":1714146772} {"function":"print_timings","level":"INFO","line":269,"msg":"prompt eval time = 9954.13 ms / 26 tokens ( 382.85 ms per token, 2.61 tokens per second)","n_prompt_tokens_processed":26,"n_tokens_second":2.611980632766373,"slot_id":0,"t_prompt_processing":9954.132,"t_token":382.85123076923077,"task_id":999,"tid":"23180484790144","timestamp":1714146816} {"function":"print_timings","level":"INFO","line":283,"msg":"generation eval time = 34261.63 ms / 69 runs ( 496.55 ms per token, 2.01 tokens per second)","n_decoded":69,"n_tokens_second":2.0139148087183716,"slot_id":0,"t_token":496.5453333333333,"t_token_generation":34261.628,"task_id":999,"tid":"23180484790144","timestamp":1714146816} {"function":"print_timings","level":"INFO","line":293,"msg":" total time = 44215.76 ms","slot_id":0,"t_prompt_processing":9954.132,"t_token_generation":34261.628,"t_total":44215.759999999995,"task_id":999,"tid":"23180484790144","timestamp":1714146816} {"function":"log_server_request","level":"INFO","line":2734,"method":"POST","msg":"request","params":{},"path":"/completion","remote_addr":"127.0.0.1","remote_port":60708,"status":200,"tid":"23175901271616","timestamp":1714146816} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":0,"n_processing_slots":1,"task_id":1070,"tid":"23180484790144","timestamp":1714146816} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":60708,"status":200,"tid":"23175901271616","timestamp":1714146816} {"function":"update_slots","level":"INFO","line":1640,"msg":"slot released","n_cache_tokens":154,"n_ctx":2048,"n_past":153,"n_system_tokens":0,"slot_id":0,"task_id":999,"tid":"23180484790144","timestamp":1714146816,"truncated":false} [GIN] 2024/04/26 - 15:53:36 | 500 | 44.303565407s | 192.168.1.167 | POST "/api/generate" {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":1072,"tid":"23180484790144","timestamp":1714146826} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":43070,"status":200,"tid":"23175903372864","timestamp":1714146826} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":1073,"tid":"23180484790144","timestamp":1714146826} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":43070,"status":200,"tid":"23175903372864","timestamp":1714146826} {"function":"launch_slot_with_data","level":"INFO","line":830,"msg":"slot is processing task","slot_id":0,"task_id":1074,"tid":"23180484790144","timestamp":1714146826} {"function":"update_slots","ga_i":0,"level":"INFO","line":1809,"msg":"slot progression","n_past":85,"n_past_se":0,"n_prompt_tokens_processed":0,"slot_id":0,"task_id":1074,"tid":"23180484790144","timestamp":1714146826} {"function":"update_slots","level":"INFO","line":1824,"msg":"we have to evaluate at least 1 token to generate logits","slot_id":0,"task_id":1074,"tid":"23180484790144","timestamp":1714146826} {"function":"update_slots","level":"INFO","line":1836,"msg":"kv cache rm [p0, end)","p0":84,"slot_id":0,"task_id":1074,"tid":"23180484790144","timestamp":1714146826} {"function":"print_timings","level":"INFO","line":269,"msg":"prompt eval time = 517.12 ms / 0 tokens ( inf ms per token, 0.00 tokens per second)","n_prompt_tokens_processed":0,"n_tokens_second":0.0,"slot_id":0,"t_prompt_processing":517.12,"t_token":null,"task_id":1074,"tid":"23180484790144","timestamp":1714146893} {"function":"print_timings","level":"INFO","line":283,"msg":"generation eval time = 66105.63 ms / 119 runs ( 555.51 ms per token, 1.80 tokens per second)","n_decoded":119,"n_tokens_second":1.8001493549126968,"slot_id":0,"t_token":555.509462184874,"t_token_generation":66105.626,"task_id":1074,"tid":"23180484790144","timestamp":1714146893} {"function":"print_timings","level":"INFO","line":293,"msg":" total time = 66622.75 ms","slot_id":0,"t_prompt_processing":517.12,"t_token_generation":66105.626,"t_total":66622.746,"task_id":1074,"tid":"23180484790144","timestamp":1714146893} {"function":"log_server_request","level":"INFO","line":2734,"method":"POST","msg":"request","params":{},"path":"/completion","remote_addr":"127.0.0.1","remote_port":43070,"status":200,"tid":"23175903372864","timestamp":1714146893} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":0,"n_processing_slots":1,"task_id":1195,"tid":"23180484790144","timestamp":1714146893} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":43070,"status":200,"tid":"23175903372864","timestamp":1714146893} {"function":"update_slots","level":"INFO","line":1640,"msg":"slot released","n_cache_tokens":204,"n_ctx":2048,"n_past":203,"n_system_tokens":0,"slot_id":0,"task_id":1074,"tid":"23180484790144","timestamp":1714146893,"truncated":false} [GIN] 2024/04/26 - 15:54:53 | 500 | 1m6s | 192.168.1.167 | POST "/api/generate" {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":1197,"tid":"23180484790144","timestamp":1714146898} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":57848,"status":200,"tid":"23175899170368","timestamp":1714146898} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":1198,"tid":"23180484790144","timestamp":1714146898} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":57848,"status":200,"tid":"23175899170368","timestamp":1714146898} {"function":"launch_slot_with_data","level":"INFO","line":830,"msg":"slot is processing task","slot_id":0,"task_id":1199,"tid":"23180484790144","timestamp":1714146898} {"function":"update_slots","ga_i":0,"level":"INFO","line":1809,"msg":"slot progression","n_past":85,"n_past_se":0,"n_prompt_tokens_processed":0,"slot_id":0,"task_id":1199,"tid":"23180484790144","timestamp":1714146898} {"function":"update_slots","level":"INFO","line":1824,"msg":"we have to evaluate at least 1 token to generate logits","slot_id":0,"task_id":1199,"tid":"23180484790144","timestamp":1714146898} {"function":"update_slots","level":"INFO","line":1836,"msg":"kv cache rm [p0, end)","p0":84,"slot_id":0,"task_id":1199,"tid":"23180484790144","timestamp":1714146898} [GIN] 2024/04/26 - 15:56:21 | 200 | 1m23s | 192.168.1.167 | POST "/api/generate" {"function":"log_server_request","level":"INFO","line":2734,"method":"POST","msg":"request","params":{},"path":"/completion","remote_addr":"127.0.0.1","remote_port":57848,"status":200,"tid":"23175899170368","timestamp":1714146982} {"function":"update_slots","level":"INFO","line":1640,"msg":"slot released","n_cache_tokens":235,"n_ctx":2048,"n_past":234,"n_system_tokens":0,"slot_id":0,"task_id":1199,"tid":"23180484790144","timestamp":1714146982,"truncated":false} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":1352,"tid":"23180484790144","timestamp":1714147011} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":53832,"status":200,"tid":"23175901271616","timestamp":1714147011} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":1353,"tid":"23180484790144","timestamp":1714147011} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":53832,"status":200,"tid":"23175901271616","timestamp":1714147011} {"function":"launch_slot_with_data","level":"INFO","line":830,"msg":"slot is processing task","slot_id":0,"task_id":1354,"tid":"23180484790144","timestamp":1714147011} {"function":"update_slots","ga_i":0,"level":"INFO","line":1809,"msg":"slot progression","n_past":74,"n_past_se":0,"n_prompt_tokens_processed":4,"slot_id":0,"task_id":1354,"tid":"23180484790144","timestamp":1714147011} {"function":"update_slots","level":"INFO","line":1836,"msg":"kv cache rm [p0, end)","p0":74,"slot_id":0,"task_id":1354,"tid":"23180484790144","timestamp":1714147011} {"function":"print_timings","level":"INFO","line":269,"msg":"prompt eval time = 1759.11 ms / 4 tokens ( 439.78 ms per token, 2.27 tokens per second)","n_prompt_tokens_processed":4,"n_tokens_second":2.2738797163107667,"slot_id":0,"t_prompt_processing":1759.108,"t_token":439.777,"task_id":1354,"tid":"23180484790144","timestamp":1714147065} {"function":"print_timings","level":"INFO","line":283,"msg":"generation eval time = 52489.85 ms / 98 runs ( 535.61 ms per token, 1.87 tokens per second)","n_decoded":98,"n_tokens_second":1.867027589771592,"slot_id":0,"t_token":535.610724489796,"t_token_generation":52489.851,"task_id":1354,"tid":"23180484790144","timestamp":1714147065} {"function":"print_timings","level":"INFO","line":293,"msg":" total time = 54248.96 ms","slot_id":0,"t_prompt_processing":1759.108,"t_token_generation":52489.851,"t_total":54248.959,"task_id":1354,"tid":"23180484790144","timestamp":1714147065} {"function":"log_server_request","level":"INFO","line":2734,"method":"POST","msg":"request","params":{},"path":"/completion","remote_addr":"127.0.0.1","remote_port":53832,"status":200,"tid":"23175901271616","timestamp":1714147065} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":0,"n_processing_slots":1,"task_id":1454,"tid":"23180484790144","timestamp":1714147065} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":34160,"status":200,"tid":"23175903372864","timestamp":1714147065} [GIN] 2024/04/26 - 15:57:45 | 500 | 54.29739368s | 192.168.1.167 | POST "/api/generate" {"function":"update_slots","level":"INFO","line":1640,"msg":"slot released","n_cache_tokens":176,"n_ctx":2048,"n_past":175,"n_system_tokens":0,"slot_id":0,"task_id":1354,"tid":"23180484790144","timestamp":1714147065,"truncated":false} time=2024-04-26T16:06:50.536Z level=INFO source=gpu.go:121 msg="Detecting GPU type" time=2024-04-26T16:06:50.536Z level=INFO source=gpu.go:268 msg="Searching for GPU management library libcudart.so*" time=2024-04-26T16:06:50.537Z level=INFO source=gpu.go:314 msg="Discovered GPU libraries: [/tmp/ollama3539318188/runners/cuda_v11/libcudart.so.11.0]" time=2024-04-26T16:06:50.579Z level=INFO source=gpu.go:343 msg="Unable to load cudart CUDA management library /tmp/ollama3539318188/runners/cuda_v11/libcudart.so.11.0: your nvidia driver is too old or missing, please upgrade to run ollama" time=2024-04-26T16:06:50.579Z level=INFO source=gpu.go:268 msg="Searching for GPU management library libnvidia-ml.so" time=2024-04-26T16:06:50.580Z level=INFO source=gpu.go:314 msg="Discovered GPU libraries: []" time=2024-04-26T16:06:50.580Z level=INFO source=cpu_common.go:11 msg="CPU has AVX2" time=2024-04-26T16:06:50.580Z level=INFO source=gpu.go:121 msg="Detecting GPU type" time=2024-04-26T16:06:50.580Z level=INFO source=gpu.go:268 msg="Searching for GPU management library libcudart.so*" time=2024-04-26T16:06:50.581Z level=INFO source=gpu.go:314 msg="Discovered GPU libraries: [/tmp/ollama3539318188/runners/cuda_v11/libcudart.so.11.0]" time=2024-04-26T16:06:50.581Z level=INFO source=gpu.go:343 msg="Unable to load cudart CUDA management library /tmp/ollama3539318188/runners/cuda_v11/libcudart.so.11.0: your nvidia driver is too old or missing, please upgrade to run ollama" time=2024-04-26T16:06:50.582Z level=INFO source=gpu.go:268 msg="Searching for GPU management library libnvidia-ml.so" time=2024-04-26T16:06:50.582Z level=INFO source=gpu.go:314 msg="Discovered GPU libraries: []" time=2024-04-26T16:06:50.583Z level=INFO source=cpu_common.go:11 msg="CPU has AVX2" time=2024-04-26T16:06:50.583Z level=INFO source=server.go:127 msg="offload to gpu" reallayers=0 layers=0 required="4267.5 MiB" used="181.0 MiB" available="0 B" kv="256.0 MiB" fulloffload="164.0 MiB" partialoffload="181.0 MiB" time=2024-04-26T16:06:50.584Z level=INFO source=server.go:264 msg="starting llama server" cmd="/tmp/ollama3539318188/runners/cpu_avx2/ollama_llama_server --model /root/.ollama/models/blobs/sha256-e8a35b5937a5e6d5c35d1f2a15f161e07eefe5e5bb0a3cdd42998ee79b057730 --ctx-size 2048 --batch-size 512 --embedding --log-disable --n-gpu-layers 0 --port 39645" time=2024-04-26T16:06:50.585Z level=INFO source=server.go:389 msg="waiting for llama runner to start responding" {"function":"server_params_parse","level":"INFO","line":2603,"msg":"logging to file is disabled.","tid":"22658407044992","timestamp":1714147610} {"function":"server_params_parse","level":"WARN","line":2380,"msg":"Not compiled with GPU offload support, --n-gpu-layers option will be ignored. See main README.md for information on enabling GPU BLAS support","n_gpu_layers":-1,"tid":"22658407044992","timestamp":1714147610} {"build":1,"commit":"7593639","function":"main","level":"INFO","line":2819,"msg":"build info","tid":"22658407044992","timestamp":1714147610} {"function":"main","level":"INFO","line":2822,"msg":"system info","n_threads":1,"n_threads_batch":-1,"system_info":"AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | ","tid":"22658407044992","timestamp":1714147610,"total_threads":1} llama_model_loader: loaded meta data with 24 key-value pairs and 291 tensors from /root/.ollama/models/blobs/sha256-e8a35b5937a5e6d5c35d1f2a15f161e07eefe5e5bb0a3cdd42998ee79b057730 (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 = llama llama_model_loader: - kv 1: general.name str = mistralai llama_model_loader: - kv 2: llama.context_length u32 = 32768 llama_model_loader: - kv 3: llama.embedding_length u32 = 4096 llama_model_loader: - kv 4: llama.block_count u32 = 32 llama_model_loader: - kv 5: llama.feed_forward_length u32 = 14336 llama_model_loader: - kv 6: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 7: llama.attention.head_count u32 = 32 llama_model_loader: - kv 8: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 10: llama.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 11: general.file_type u32 = 2 llama_model_loader: - kv 12: tokenizer.ggml.model str = llama llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,32000] = ["<unk>", "<s>", "</s>", "<0x00>", "<... llama_model_loader: - kv 14: tokenizer.ggml.scores arr[f32,32000] = [0.000000, 0.000000, 0.000000, 0.0000... llama_model_loader: - kv 15: tokenizer.ggml.token_type arr[i32,32000] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ... llama_model_loader: - kv 16: tokenizer.ggml.merges arr[str,58980] = ["▁ t", "i n", "e r", "▁ a", "h e... llama_model_loader: - kv 17: tokenizer.ggml.bos_token_id u32 = 1 llama_model_loader: - kv 18: tokenizer.ggml.eos_token_id u32 = 2 llama_model_loader: - kv 19: tokenizer.ggml.unknown_token_id u32 = 0 llama_model_loader: - kv 20: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 21: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 22: tokenizer.chat_template str = {{ bos_token }}{% for message in mess... llama_model_loader: - kv 23: general.quantization_version u32 = 2 llama_model_loader: - type f32: 65 tensors llama_model_loader: - type q4_0: 225 tensors llama_model_loader: - type q6_K: 1 tensors llm_load_vocab: special tokens definition check successful ( 259/32000 ). llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = llama llm_load_print_meta: vocab type = SPM llm_load_print_meta: n_vocab = 32000 llm_load_print_meta: n_merges = 0 llm_load_print_meta: n_ctx_train = 32768 llm_load_print_meta: n_embd = 4096 llm_load_print_meta: n_head = 32 llm_load_print_meta: n_head_kv = 8 llm_load_print_meta: n_layer = 32 llm_load_print_meta: n_rot = 128 llm_load_print_meta: n_embd_head_k = 128 llm_load_print_meta: n_embd_head_v = 128 llm_load_print_meta: n_gqa = 4 llm_load_print_meta: n_embd_k_gqa = 1024 llm_load_print_meta: n_embd_v_gqa = 1024 llm_load_print_meta: f_norm_eps = 0.0e+00 llm_load_print_meta: f_norm_rms_eps = 1.0e-05 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: f_logit_scale = 0.0e+00 llm_load_print_meta: n_ff = 14336 llm_load_print_meta: n_expert = 0 llm_load_print_meta: n_expert_used = 0 llm_load_print_meta: causal attn = 1 llm_load_print_meta: pooling type = 0 llm_load_print_meta: rope type = 0 llm_load_print_meta: rope scaling = linear llm_load_print_meta: freq_base_train = 1000000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_yarn_orig_ctx = 32768 llm_load_print_meta: rope_finetuned = unknown llm_load_print_meta: ssm_d_conv = 0 llm_load_print_meta: ssm_d_inner = 0 llm_load_print_meta: ssm_d_state = 0 llm_load_print_meta: ssm_dt_rank = 0 llm_load_print_meta: model type = 7B llm_load_print_meta: model ftype = Q4_0 llm_load_print_meta: model params = 7.24 B llm_load_print_meta: model size = 3.83 GiB (4.54 BPW) llm_load_print_meta: general.name = mistralai llm_load_print_meta: BOS token = 1 '<s>' llm_load_print_meta: EOS token = 2 '</s>' llm_load_print_meta: UNK token = 0 '<unk>' llm_load_print_meta: LF token = 13 '<0x0A>' llm_load_tensors: ggml ctx size = 0.11 MiB llm_load_tensors: CPU buffer size = 3917.87 MiB .................................................................................................. llama_new_context_with_model: n_ctx = 2048 llama_new_context_with_model: n_batch = 512 llama_new_context_with_model: n_ubatch = 512 llama_new_context_with_model: freq_base = 1000000.0 llama_new_context_with_model: freq_scale = 1 llama_kv_cache_init: CPU 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 output buffer size = 0.14 MiB llama_new_context_with_model: CPU compute buffer size = 164.01 MiB llama_new_context_with_model: graph nodes = 1030 llama_new_context_with_model: graph splits = 1 {"function":"initialize","level":"INFO","line":448,"msg":"initializing slots","n_slots":1,"tid":"22658407044992","timestamp":1714147640} {"function":"initialize","level":"INFO","line":457,"msg":"new slot","n_ctx_slot":2048,"slot_id":0,"tid":"22658407044992","timestamp":1714147640} {"function":"main","level":"INFO","line":3064,"msg":"model loaded","tid":"22658407044992","timestamp":1714147640} {"function":"main","hostname":"127.0.0.1","level":"INFO","line":3267,"msg":"HTTP server listening","n_threads_http":"3","port":"39645","tid":"22658407044992","timestamp":1714147640} {"function":"update_slots","level":"INFO","line":1578,"msg":"all slots are idle and system prompt is empty, clear the KV cache","tid":"22658407044992","timestamp":1714147640} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":0,"tid":"22658407044992","timestamp":1714147640} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":44072,"status":200,"tid":"22653821568576","timestamp":1714147640} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":1,"tid":"22658407044992","timestamp":1714147640} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":44078,"status":200,"tid":"22653821568576","timestamp":1714147640} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":2,"tid":"22658407044992","timestamp":1714147640} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":44094,"status":200,"tid":"22653821568576","timestamp":1714147640} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":3,"tid":"22658407044992","timestamp":1714147640} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":44102,"status":200,"tid":"22653821568576","timestamp":1714147640} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":4,"tid":"22658407044992","timestamp":1714147640} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":44120,"status":200,"tid":"22653821568576","timestamp":1714147640} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":5,"tid":"22658407044992","timestamp":1714147640} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":44116,"status":200,"tid":"22653823669824","timestamp":1714147640} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":6,"tid":"22658407044992","timestamp":1714147641} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":44942,"status":200,"tid":"22653823669824","timestamp":1714147641} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":7,"tid":"22658407044992","timestamp":1714147641} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":44942,"status":200,"tid":"22653823669824","timestamp":1714147641} {"function":"launch_slot_with_data","level":"INFO","line":830,"msg":"slot is processing task","slot_id":0,"task_id":8,"tid":"22658407044992","timestamp":1714147641} {"function":"update_slots","ga_i":0,"level":"INFO","line":1809,"msg":"slot progression","n_past":0,"n_past_se":0,"n_prompt_tokens_processed":15,"slot_id":0,"task_id":8,"tid":"22658407044992","timestamp":1714147641} {"function":"update_slots","level":"INFO","line":1836,"msg":"kv cache rm [p0, end)","p0":0,"slot_id":0,"task_id":8,"tid":"22658407044992","timestamp":1714147641} [GIN] 2024/04/26 - 16:07:21 | 200 | 66.373µs | 127.0.0.1 | GET "/api/version" {"function":"print_timings","level":"INFO","line":269,"msg":"prompt eval time = 6808.76 ms / 15 tokens ( 453.92 ms per token, 2.20 tokens per second)","n_prompt_tokens_processed":15,"n_tokens_second":2.2030430192616457,"slot_id":0,"t_prompt_processing":6808.764,"t_token":453.9176,"task_id":8,"tid":"22658407044992","timestamp":1714147724} {"function":"print_timings","level":"INFO","line":283,"msg":"generation eval time = 76398.96 ms / 141 runs ( 541.84 ms per token, 1.85 tokens per second)","n_decoded":141,"n_tokens_second":1.845574957856754,"slot_id":0,"t_token":541.8365673758866,"t_token_generation":76398.956,"task_id":8,"tid":"22658407044992","timestamp":1714147724} {"function":"print_timings","level":"INFO","line":293,"msg":" total time = 83207.72 ms","slot_id":0,"t_prompt_processing":6808.764,"t_token_generation":76398.956,"t_total":83207.72,"task_id":8,"tid":"22658407044992","timestamp":1714147724} {"function":"log_server_request","level":"INFO","line":2734,"method":"POST","msg":"request","params":{},"path":"/completion","remote_addr":"127.0.0.1","remote_port":44942,"status":200,"tid":"22653823669824","timestamp":1714147724} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":0,"n_processing_slots":1,"task_id":151,"tid":"22658407044992","timestamp":1714147724} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":44942,"status":200,"tid":"22653823669824","timestamp":1714147724} {"function":"update_slots","level":"INFO","line":1640,"msg":"slot released","n_cache_tokens":156,"n_ctx":2048,"n_past":155,"n_system_tokens":0,"slot_id":0,"task_id":8,"tid":"22658407044992","timestamp":1714147724,"truncated":false} [GIN] 2024/04/26 - 16:08:44 | 200 | 1m57s | 192.168.1.167 | POST "/api/generate" ``` ### OS Linux ### GPU Other ### CPU Intel ### Ollama version 0.1.32
GiteaMirror added the bug label 2026-04-28 10:18:08 -05:00
GiteaMirror commented 2026-04-28 10:18:12 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (May 2, 2024):

I believe {"error":"unexpected server status: 1"} maps to no slots available - in newer versions we should report a better error message now.

We've also made various improvements in this area of code for concurrency support in 0.1.33, although I'm not sure if it will fix the root cause. Can you give an RC of 0.1.33 a try and let us know?

https://github.com/ollama/ollama/releases

<!-- gh-comment-id:2091244784 --> @dhiltgen commented on GitHub (May 2, 2024): I believe `{"error":"unexpected server status: 1"}` maps to `no slots available` - in newer versions we should report a better error message now. We've also made various improvements in this area of code for concurrency support in 0.1.33, although I'm not sure if it will fix the root cause. Can you give an RC of 0.1.33 a try and let us know? https://github.com/ollama/ollama/releases
GiteaMirror commented 2026-04-28 10:18:13 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (May 9, 2024):

This should be fixed as in 0.1.33. If not please leave a note and we can re-open this!

<!-- gh-comment-id:2103438970 --> @jmorganca commented on GitHub (May 9, 2024): This should be fixed as in 0.1.33. If not please leave a note and we can re-open this!
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#48960
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?