Triton pending-request gauge

Triton main, docs/user_guide/metrics.md, read 2026-10-04. On by default: 'By default, these metrics are available at http://localhost:8002/metrics', and the endpoint is pure pull - 'not pushed or published to any remote server'. tritonserver --allow-metrics=false turns the whole thing off. Labels are model and version, and crucially the LATENCY families are per MODEL, per request-update - not per-request observations as in vLLM/SGLang/TGI. The honest queue-depth metric, and the docs define it precisely: 'incremented when a request is enqueued to the server (TRITONSERVER_ServerInferAsync) and is decremented when a backend is about to start executing the request'. The docs also enumerate where a request CAN be pending (default scheduler backlog, dynamic batcher queue, sequence batcher queues, rate limiter queues) and where it will NOT (ensemble scheduler, frontends) - so the number's meaning depends on which features are on.