| Prefix cache effectiveness metrics | Coverage for the vLLM v0.23.0 first-party prefix-cache counters and how to compute and interpret the prefix cache hit rate. | 0 | 2 | covered |
| Scheduler and KV pressure metrics | Coverage for a small vLLM v0.23.0 metric slice that exposes scheduler queue state, KV cache usage, and preemption signals. | 0 | 0 | not evaluated |
| Scheduler sequence capacity | Coverage for max_num_seqs scheduler capacity, configuration exposure, constraints, and KV-cache pressure guidance. | 0 | 0 | not evaluated |
| Scheduler token budget | Coverage for how vLLM represents and constrains max_num_batched_tokens in scheduler iteration token budgets. | 0 | 0 | not evaluated |
| vLLM metric identity | Metric identity coverage anchored by the complete v0.23.0 Prometheus inventory, with multi-version history where an admitted scope has tracked a metric across releases. | 0 | 2 | partial |
Schema.ai· vLLM