Skip to content

vllm_omni.metrics.prometheus

OmniPrometheusMetrics

Label-bound wrapper around the raw Prometheus metrics.

Metric collectors use the vllm:omni_ prefix to avoid being removed by upstream vLLM's unregister_vllm_metrics(), which strips every collector whose _name contains "vllm".

request_failed

request_failed() -> None

request_succeeded

request_succeeded(
    e2e_seconds: float, finished_reason: str = "stop"
) -> None

set_running

set_running(n: int) -> None

set_waiting

set_waiting(n: int) -> None

OmniRequestCounter

Running-request counter written by the orchestrator thread, read by the client thread.

value instance-attribute

value = 0

decrement

decrement() -> None

increment

increment() -> None