Jae-Won Chung d4acf518d0

[Metrics] Fix KV cache usage percent metric multiproc (#28792) ...

The `vllm:kv_cache_usage_perc` Gauge metric is missing `multiprocess_mode="mostrecent"` and ends up returning

```
vllm:kv_cache_usage_perc{engine="0",model_name="Qwen/Qwen3-VL-8B-Instruct",pid="277"} 0.0
vllm:kv_cache_usage_perc{engine="0",model_name="Qwen/Qwen3-VL-8B-Instruct",pid="275"} 0.0
vllm:kv_cache_usage_perc{engine="0",model_name="Qwen/Qwen3-VL-8B-Instruct",pid="273"} 0.6530455880475035
...
```

The deprecated `vllm:gpu_cache_usage_perc` Gauge metric has `multiprocess_mode="mostrecent"`.

Signed-off-by: Jae-Won Chung <jwnchung@umich.edu>

2025-11-17 09:54:15 +00:00

..

__init__.py

…

loggers.py

[Metrics] Fix KV cache usage percent metric multiproc (#28792)

2025-11-17 09:54:15 +00:00

prometheus.py

…

ray_wrappers.py

[KVConnector] Add metrics to Prometheus-Grafana dashboard (#26811)

2025-10-29 18:44:49 +00:00

reader.py

…

stats.py

[Metrics] Refactor LoRA state tracking (#26801)

2025-11-10 16:34:36 +08:00