vLLM v0.23.0 metric identity

Coverage

Identity facts for the complete v0.23.0 Prometheus metric inventory — which metrics exist, their instrument kind, their label names, and their literal histogram bucket boundaries — generated from the pinned metric registration code.

Strong for whether a fixed-name metric exists at v0.23.0 and what Prometheus instrument kind it is registered as, across the complete 45-metric inventory; strong for label names and literal bucket boundaries where registration declares them statically; none for units, for bucket boundaries computed at runtime, or for label sets built at runtime.

Generated slice, not hand-authored: every claim here is produced by scripts/generate_metric_identity_claims.py from registration call sites in the pinned v0.23.0 snapshots, and is reproducible by re-running it. Instrument-kind coverage is complete over the closed inventory (45 of 45); label and bucket coverage is partial by construction, and the shortfalls are declared below rather than inferred. Seven instrument-kind claims predate the generator, are hand-authored, and are checked against the extraction rather than overwritten by it.

Claims in this topic (94)

Metrics in this topic (45)

• cache_config_info — 1 claim
• corrupted_requests — 2 claims
• e2e_request_latency_seconds — 3 claims
• engine_sleep_state — 2 claims
• estimated_flops_per_gpu_total — 1 claim
• estimated_read_bytes_per_gpu_total — 1 claim
• estimated_write_bytes_per_gpu_total — 1 claim
• external_prefix_cache_hits — 2 claims
• external_prefix_cache_queries — 2 claims
• generation_tokens — 2 claims
• inter_token_latency_seconds — 3 claims
• iteration_tokens_total — 3 claims
• kv_block_idle_before_evict_seconds — 3 claims
• kv_block_lifetime_seconds — 3 claims
• kv_block_reuse_gap_seconds — 3 claims
• kv_cache_usage_perc — 2 claims
• lora_requests_info — 1 claim
• mm_cache_hits — 2 claims
• mm_cache_queries — 2 claims
• num_preemptions — 2 claims
• num_requests_running — 2 claims
• num_requests_waiting — 2 claims
• num_requests_waiting_by_reason — 2 claims
• prefix_cache_hits — 2 claims
• prefix_cache_queries — 2 claims
• prompt_tokens — 2 claims
• prompt_tokens_by_source — 2 claims
• prompt_tokens_cached — 2 claims
• request_decode_time_seconds — 3 claims
• request_generation_tokens — 2 claims
• request_inference_time_seconds — 3 claims
• request_max_num_generation_tokens — 2 claims
• request_params_max_tokens — 2 claims
• request_params_n — 3 claims
• request_prefill_kv_computed_tokens — 2 claims
• request_prefill_time_seconds — 3 claims
• request_prompt_tokens — 2 claims
• request_queue_time_seconds — 3 claims
• request_success — 2 claims
• request_time_per_output_token_seconds — 3 claims
• spec_decode_num_accepted_tokens — 1 claim
• spec_decode_num_accepted_tokens_per_pos — 1 claim
• spec_decode_num_draft_tokens — 1 claim
• spec_decode_num_drafts — 1 claim
• time_to_first_token_seconds — 3 claims

Surfaces

• Prometheus /metrics endpoint — 45 inventoried members

Known gaps