Triton+TRT-LLM TRT-LLM disaggregated-serving gauge, label-switched

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. Backend-contributed via the Triton custom metrics API, NOT a Triton core metric. All six families share the model and version labels. Observed label values: ['kv_cache_transfer_ms', 'request_count']. The one LLM-specific piece Triton core delegates and here gets back: KV transfer time and count for disaggregated serving.