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 14, 05:30 UTC
[Docs] fix broken links in metrics.md (#22315)
Signed-off-by: Guy Stone <guys@spotify.com> Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Guy Stone committed
Aug 8, 2025 at 19:22 UTC
2fcf6b27b6902a18aaf4a6fb8cf5c7efc8afc731
1 file changed
+4
-4
docs/design/metrics.md
+4
-4
@@ -57,11 +57,11 @@ In v0, the following metrics are exposed via a Prometheus-compatible `/metrics`
57
- `vllm:spec_decode_num_draft_tokens_total` (Counter)
58
- `vllm:spec_decode_num_emitted_tokens_total` (Counter)
59
60
-These are documented under [Inferencing and Serving -> Production Metrics](../../usage/metrics.md).
60
+These are documented under [Inferencing and Serving -> Production Metrics](../usage/metrics.md).
61
62
### Grafana Dashboard
63
64
-vLLM also provides [a reference example](../../examples/online_serving/prometheus_grafana.md) for how to collect and store these metrics using Prometheus and visualize them using a Grafana dashboard.
64
+vLLM also provides [a reference example](../examples/online_serving/prometheus_grafana.md) for how to collect and store these metrics using Prometheus and visualize them using a Grafana dashboard.
65
66
The subset of metrics exposed in the Grafana dashboard gives us an indication of which metrics are especially important:
67
@@ -455,7 +455,7 @@ In general:
455
[an escape hatch](https://kubernetes.io/docs/concepts/cluster-administration/system-metrics/#show-hidden-metrics)
456
for some time before deleting them.
457
458
-See the [deprecation policy](../../contributing/deprecation_policy.md) for
458
+See the [deprecation policy](../contributing/deprecation_policy.md) for
459
the project-wide deprecation policy.
460
461
### Unimplemented - `vllm:tokens_total`
@@ -655,7 +655,7 @@ v0 has support for OpenTelemetry tracing:
655
- Added by <gh-pr:4687>
656
- Configured with `--oltp-traces-endpoint` and `--collect-detailed-traces`
657
- [OpenTelemetry blog post](https://opentelemetry.io/blog/2024/llm-observability/)
658
-- [User-facing docs](../../examples/online_serving/opentelemetry.md)
658
+- [User-facing docs](../examples/online_serving/opentelemetry.md)
659
- [Blog post](https://medium.com/@ronen.schaffer/follow-the-trail-supercharging-vllm-with-opentelemetry-distributed-tracing-aa655229b46f)
660
- [IBM product docs](https://www.ibm.com/docs/en/instana-observability/current?topic=mgaa-monitoring-large-language-models-llms-vllm-public-preview)
661