vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

server: concurrency fix + monitoring - add /metrics prometheus compatible endpoint (#5708)

Browse source 
* server: monitoring - add /metrics prometheus compatible endpoint

* server: concurrency issue, when 2 task are waiting for results, only one call thread is notified

* server: metrics - move to a dedicated struct
This commit is contained in:
Pierrick Hymbert 2024-02-25 13:49:43 +01:00 • committed by GitHub
parent 1289408817
commit d52d7819b8
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 191 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

13
examples/server/README.md
View file

@ -41,6 +41,7 @@ see https://github.com/ggerganov/llama.cpp/issues/1437
- `--grp-attn-w`: Set the group attention width to extend context size through self-extend(default: 512), used together with group attention factor `--grp-attn-n`
- `-n, --n-predict`: Set the maximum tokens to predict (default: -1)
- `--slots-endpoint-disable`: To disable slots state monitoring endpoint. Slots state may contain user data, prompts included.
- `--metrics`: enable prometheus `/metrics` compatible endpoint (default: disabled)
- `--chat-template JINJA_TEMPLATE`: Set custom jinja chat template. This parameter accepts a string, not a file name (default: template taken from model's metadata). We only support [some pre-defined templates](https://github.com/ggerganov/llama.cpp/wiki/Templates-supported-by-llama_chat_apply_template)
## Build
@ -457,6 +458,18 @@ Notice that each `probs` is an array of length `n_probs`.
]
```
- **GET** `/metrics`: [Prometheus](https://prometheus.io/) compatible metrics exporter endpoint if `--metrics` is enabled:
Available metrics:
- `llamacpp:prompt_tokens_total`: Number of prompt tokens processed.
- `llamacpp:tokens_predicted_total`: Number of generation tokens processed.
- `llamacpp:prompt_tokens_seconds`: Average prompt throughput in tokens/s.
- `llamacpp:predicted_tokens_seconds`: Average generation throughput in tokens/s.
- `llamacpp:kv_cache_usage_ratio`: KV-cache usage. 1 means 100 percent usage.
- `llamacpp:kv_cache_tokens`: KV-cache tokens.
- `llamacpp:requests_processing`: Number of request processing.
- `llamacpp:requests_deferred`: Number of request deferred.
## More examples
### Change system prompt on runtime