@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 8d2cff8140
Fork 0

A high-throughput and memory-efficient inference and serving engine for LLMs

Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git

Synced Nov 5, 01:00 UTC

[Examples] Resettle Observability examples. (#40123)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>

wang.yuqi committed Apr 17, 2026 at 18:13 UTC 8d2cff8140eb2c5f6a7b28948c0944d11898d9d2
15 files changed +4 -4
docs/design/metrics.md
+2 -2
@@ -42,7 +42,7 @@ These are documented under [Inferencing and Serving -> Production Metrics](../us
42
43 ### Grafana Dashboard
44
45 -vLLM also provides [a reference example](../../examples/online_serving/prometheus_grafana/README.md) for how to collect and store these metrics using Prometheus and visualize them using a Grafana dashboard.
45 +vLLM also provides [a reference example](../../examples/observability/prometheus_grafana/README.md) for how to collect and store these metrics using Prometheus and visualize them using a Grafana dashboard.
46
47 The subset of metrics exposed in the Grafana dashboard gives us an indication of which metrics are especially important:
48
@@ -657,7 +657,7 @@ vLLM has support for OpenTelemetry tracing:
657 - Added by <https://github.com/vllm-project/vllm/pull/4687> and reinstated by <https://github.com/vllm-project/vllm/pull/20372>
658 - Configured with `--oltp-traces-endpoint` and `--collect-detailed-traces`
659 - [OpenTelemetry blog post](https://opentelemetry.io/blog/2024/llm-observability/)
660 -- [User-facing docs](../../examples/online_serving/opentelemetry/README.md)
660 +- [User-facing docs](../../examples/observability/opentelemetry/README.md)
661 - [Blog post](https://medium.com/@ronen.schaffer/follow-the-trail-supercharging-vllm-with-opentelemetry-distributed-tracing-aa655229b46f)
662 - [IBM product docs](https://www.ibm.com/docs/en/instana-observability/current?topic=mgaa-monitoring-large-language-models-llms-vllm-public-preview)
663
examples/observability/dashboards/README.md renamed
+2 -2
@@ -74,8 +74,8 @@ percli apply -f perses/performance_statistics.yaml
74
75 For detailed deployment instructions and platform-specific options, see:
76
77 -- **[Grafana Documentation](./grafana)** - JSON dashboards, operator usage, manual import
78 -- **[Perses Documentation](./perses)** - YAML specs, CLI usage, operator wrapping
77 +- **[Grafana Documentation](grafana)** - JSON dashboards, operator usage, manual import
78 +- **[Perses Documentation](perses)** - YAML specs, CLI usage, operator wrapping
79
80 ## Contributing
81
examples/observability/dashboards/grafana/README.md renamed
examples/observability/dashboards/grafana/performance_statistics.json renamed
examples/observability/dashboards/grafana/query_statistics.json renamed
examples/observability/dashboards/perses/README.md renamed
examples/observability/dashboards/perses/performance_statistics.yaml renamed
examples/observability/dashboards/perses/query_statistics.yaml renamed
examples/observability/metrics/offline.py renamed
examples/observability/opentelemetry/README.md renamed
examples/observability/opentelemetry/dummy_client.py renamed
examples/observability/prometheus_grafana/README.md renamed
examples/observability/prometheus_grafana/docker-compose.yaml renamed
examples/observability/prometheus_grafana/grafana.json renamed
examples/observability/prometheus_grafana/prometheus.yaml renamed