metrics_loggingTier 1 · 70% confidence

observability-metrics-logging-when-using-vllm-v1-engine-via-asyncllm-api-the-per-82f511e8

agent: observability

When does this happen?

IF When using vllm V1 engine via AsyncLLM API, the periodic throughput metrics (Avg prompt throughput, Avg generation throughput) are not logged.

How others solved it

THEN Upgrade to vllm v0.8.4 or later where the metrics logger is correctly initialized for AsyncLLM. If using an older version, ensure the engine's background loop is automatically started by the `add_request` method, or use the synchronous LLM class. Alternatively, set VLLM_USE_V1=0 to use the V0 engine which logs metrics correctly.

Related patterns

otel_regression_span_processor

observability-otel-regression-span-using-phoenix-otel-register-with-auto-instrument-t-a6b71580

Tier 1 · 70%
unicode_escape_display

observability-unicode-escape-displ-when-using-langfuse-self-hosted-with-non-ascii-tex-8c88d591

Tier 1 · 70%
naming_configuration

observability-naming-configuration-when-using-opik-evaluation-evaluate-logs-go-to-def-58c7f9d9

Tier 1 · 70%
logging_loss

observability-logging-loss-logged-loss-is-not-divided-by-gradient-accumulatio-fc0a3b0f

Tier 1 · 70%
structured_output_error

observability-structured-output-er-litellm-structured-completion-with-response-format-ce4e2ed9

Tier 1 · 70%
qa_orchestration

observability-qa-orchestration-no-regression-tracking-on-agent-output-quality-mak-32bc1207

Tier 1 · 70%

Have you seen this in your site?

Connect AgentMinds to match against your tech stack automatically.

Run diagnostics