Datadog Dashboards

vLLM Inference Monitor (中文汉化版)

Good 850 downloads0 views0 commentsRevision 1Created Converted from Grafana dashboard #25237 by q673475900
How to import

In Datadog: Dashboards → New Dashboard → ⚙ Configure → Import dashboard JSON → paste this JSON.

Reactions

基于原版 #24755 的完整中文汉化版本。覆盖 vLLM 推理核心指标：调度器效率、KV Cache 使用率、TTFT/TPOT 延迟、Prefix Cache 命中率、请求完成原因分布等。已适配 Grafana 10.4+，开箱即用。

vLLM Inference Monitor (中文汉化版)

Conversion quality

Good 85

Share of panels whose queries were translated without loss. Partial and unsupported panels keep the original PromQL in a note widget.

  • Native0
  • OpenMetrics14
  • Partial6
  • Unsupported0

Metrics without a native Datadog mapping

These metric names were kept in OpenMetrics naming. Adjust them if you collect with a native Datadog integration.

vllm:num_requests_waiting ×4vllm:request_success_total ×4vllm:num_requests_running ×3vllm:e2e_request_latency_seconds_bucket ×3vllm:request_queue_time_seconds_bucket ×3vllm:request_time_per_output_token_seconds_bucket ×3vllm:e2e_request_latency_seconds_count ×2vllm:prompt_tokens_total ×2vllm:generation_tokens_total ×2vllm:time_to_first_token_seconds_bucket ×2vllm:kv_cache_usage_perc ×2vllm:num_preemptions_totalvllm:e2e_request_latency_seconds_sumvllm:request_prompt_tokens_bucketvllm:request_generation_tokens_bucketvllm:prefix_cache_hits_totalvllm:prefix_cache_queries_totalvllm:num_requests_swapped
Tagsvllmllminferenceprometheusaichinesemonitoring
Integrationsvllm_request_successvllm_num_preemptionsvllm_e2e_request_latency_secondsvllm_prompt_tokensvllm_generation_tokensvllm_request_prompt_tokensvllm_prefix_cache_hitsvllm_prefix_cache_queries

Revisions

  • Revision 1Converted from grafana.com revision 1Download JSON

Rate this dashboard

Sign in to rate.

0 comments

No comments yet.