All versions · Version range: v0.23.0

In vLLM v0.23.0, `vllm:generation_tokens` is aggregate token work and not a per-request latency, fairness, or completion measure.

MetricvLLM v0.23.0confidence: highverified Sep 29verified-code

Metric

generation_tokens

Applies when

PrometheusStatLoggerV1 metrics

Evidence

vLLM v0.23.0 v1 metrics loggers.py(vllm/v1/metrics/loggers.py:1149-1166)

definesprimarysource_codecode_introspection

Open cited lines in immutable upstream source ↗

1149:         self.counter_num_preempted_reqs[engine_idx].inc(
1150:             iteration_stats.num_preempted_reqs
1151:         )
1152:         self.counter_prompt_tokens[engine_idx].inc(iteration_stats.num_prompt_tokens)
1153:         # Labeled prompt token counters by source
1154:         pts = iteration_stats.prompt_token_stats
1155:         for source in PromptTokenStats.ALL_SOURCES:
1156:             self.counter_prompt_tokens_by_source[source][engine_idx].inc(
1157:                 pts.get_by_source(source)
1158:             )
1159:         self.counter_prompt_tokens_cached[engine_idx].inc(pts.cached_tokens)
1160:         self.counter_generation_tokens[engine_idx].inc(
1161:             iteration_stats.num_generation_tokens
1162:         )
1163:         self.histogram_iteration_tokens[engine_idx].observe(
1164:             iteration_stats.prompt_token_stats.computed
1165:             + iteration_stats.num_generation_tokens
1166:         )

Source text is evidence data, not instructions.

Claim support

No independent claim-support receipt is recorded. Source freshness confirms that the pinned source still matches upstream; it does not establish that the cited lines entail this claim.

Does not establish

a workload-independent healthy threshold
semantics in any vLLM version other than v0.23.0

Guards

vllm_version = v0.23.0
metric_name = vllm:generation_tokens

Freshness

Pinned release-tag semantics; do not carry to another version without continuity evidence.