[Metrics] Add group-aware KV cache capacity to vllm:cache_config_info (#42206)
The startup log already reports the correct group-aware KV cache capacity for hybrid models, but Prometheus did not expose matching info in 'vllm:cache_config_info`. This PR adds kv_cache_size_tokens and kv_cache_max_concurrency. Signed-off-by: Ethan Feng <ethan.fengch@gmail.com>
This commit is contained in:
@@ -78,6 +78,9 @@ class EngineCoreReadyResponse:
|
||||
dp_stats_address: str | None
|
||||
dtype: str
|
||||
vllm_version: str
|
||||
# KV cache capacity (None for encoder-only/attention-free models).
|
||||
kv_cache_size_tokens: int | None = None
|
||||
kv_cache_max_concurrency: float | None = None
|
||||
|
||||
|
||||
class EngineCoreRequest(
|
||||
|
||||
Reference in New Issue
Block a user