SGLang Monitoring and Observability with OpenTelemetry

Overview

SGLang is an inference server that you run yourself. It serves models over an OpenAI-compatible API. It reports its own health in two ways: Prometheus metrics on an HTTP endpoint, and OpenTelemetry traces for each request. This guide sends both to SigNoz.

The metrics answer questions that only the server can answer. How many tokens per second is the GPU producing? How full is the key-value cache, the memory pool that holds attention state for active requests? How many requests wait in the queue?

The gen_ai.* spans described in LLM observability come from the application that calls a model. SGLang reports what the server itself is doing. The two are complementary, and most teams collect both.

Most steps are identical. Update the endpoint and remove the ingestion key header as shown in Cloud to Self-Hosted.

Prerequisites

An SGLang server that you can restart
An OpenTelemetry Collector that can reach the SGLang host. See Install the OpenTelemetry Collector
An instance of SigNoz (Cloud or Self-Hosted)

Send SGLang metrics to SigNoz

Step 1: Start SGLang with metrics enabled

SGLang does not expose metrics by default. Add --enable-metrics to the launch command:

python -m sglang.launch_server \
  --model-path <your-model> \
  --host 0.0.0.0 \
  --port 30000 \
  --enable-metrics

Verify these values:

<your-model>: The model you serve, for example Qwen/Qwen2.5-7B-Instruct.

SGLang serves metrics at /metrics on the same port as the API. Confirm the endpoint responds before you move on:

curl -s http://localhost:30000/metrics | head

Step 2: Add a scrape job to the Collector

Append this scrape job to your existing otel-collector-config.yaml. Do not replace the whole file.

receivers:
  prometheus:
    config:
      scrape_configs:
        - job_name: sglang
          scrape_interval: 30s
          static_configs:
            - targets: ['<sglang-host>:30000']

Verify these values:

<sglang-host>: The hostname or IP address of the machine that runs SGLang.

Then add the receiver to your metrics pipeline:

service:
  pipelines:
    metrics:
      receivers: [prometheus] # append prometheus to your existing receivers list
      processors: [batch]
      exporters: [otlphttp]

Step 3: Restart the Collector

Restart the Collector so that it loads the new scrape job, then watch its logs for scrape errors.

sudo systemctl restart otelcol-contrib
sudo journalctl -u otelcol-contrib -f

For more information on installing and configuring the Collector, see Install OpenTelemetry Collector on VM.

kubectl rollout restart deployment/<release>-k8s-infra-otel-deployment -n <collector-namespace>
kubectl logs -f deployment/<release>-k8s-infra-otel-deployment -n <collector-namespace>

The SigNoz K8s Infra chart installs two Collectors. Add the scrape job to the Deployment, which handles cluster-wide scraping, rather than to the per-node <release>-k8s-infra-otel-agent DaemonSet. Replace <release> with your Helm release name and <collector-namespace> with the namespace that runs it. If you run your own Collector under a different name, use that name instead.

For more information on installing and configuring the Collector, see Install the SigNoz K8s Infra chart.

The MSI installs the Collector as a Windows service named otelcol-contrib, with OpenTelemetry Collector as its display name. Run this in PowerShell:

Restart-Service -Name otelcol-contrib
Get-EventLog -LogName Application -Source otelcol-contrib -Newest 20

For more information on installing and configuring the Collector, see Install OpenTelemetry Collector on VM.

Send a request to SGLang so that the server has something to report.

Export Request Traces (Optional)

Metrics tell you how the server behaves as a whole. Traces show where time went inside a single request. Traces go straight from SGLang to SigNoz and do not pass through the Collector, so the scrape job above is unaffected.

Set two environment variables, then add two flags to the launch command from Step 1:

export OTEL_EXPORTER_OTLP_TRACES_PROTOCOL=http/protobuf
export OTEL_EXPORTER_OTLP_TRACES_HEADERS="signoz-ingestion-key=<your-ingestion-key>"
 
python -m sglang.launch_server \
  --model-path <your-model> \
  --host 0.0.0.0 \
  --port 30000 \
  --enable-metrics \
  --enable-trace \
  --otlp-traces-endpoint https://ingest.<region>.signoz.cloud:443/v1/traces

Verify these values:

<region>: Your SigNoz Cloud region.
<your-ingestion-key>: Your SigNoz ingestion key.

You must set both environment variables. SGLang sends no authentication header of its own, and it defaults to gRPC.

SGLang creates its gRPC exporter with insecure=True, which disables TLS. SigNoz Cloud requires TLS, so traces sent over gRPC will fail. Use http/protobuf as shown above. gRPC works only against a Collector that you run without TLS on your own network.

SGLang names each root span after the request that produced it, for example Req b70a51cd. Every request therefore creates a new operation name. The service page in SigNoz shows overflow_operation once the list exceeds its limit. The traces themselves are unaffected, and you can still filter and group them by duration, status, and resource attributes.

Restart SGLang after you change the launch command.

Validate

Open Metrics > Metrics Explorer and filter with service.name = 'sglang'. The Prometheus receiver takes that value from the job_name in your scrape job. Metrics appear within one scrape interval.

SGLang metrics in the SigNoz Metrics Explorer — *SGLang metrics in the Metrics Explorer, filtered by service.name*

If you enabled traces, open Traces and filter with the same service.name = 'sglang'. SGLang sets that name itself and ignores OTEL_SERVICE_NAME, so every SGLang server reports as sglang.

SGLang spans in the SigNoz Traces Explorer — *SGLang decode spans in the Traces Explorer*

Metrics Reference

Metric	Type	What it tells you
`sglang:gen_throughput`	Gauge	Output tokens generated per second. This is the tokens-per-second figure.
`sglang:prompt_tokens_total`	Counter	Prefill tokens processed.
`sglang:generation_tokens_total`	Counter	Output tokens produced.
`sglang:time_to_first_token_seconds`	Histogram	Delay before the first output token. Drives how fast a streaming response feels.
`sglang:inter_token_latency_seconds`	Histogram	Delay between output tokens after the first one.
`sglang:e2e_request_latency_seconds`	Histogram	Total request duration.
`sglang:num_running_reqs`	Gauge	Requests the server is decoding right now.
`sglang:num_queue_reqs`	Gauge	Requests waiting to start. A number above zero means the server is saturated.
`sglang:token_usage`	Gauge	Fraction of the key-value cache pool in use, from 0 to 1.
`sglang:cache_hit_rate`	Gauge	Fraction of prefill tokens served from the prefix cache.

Every metric carries model_name, engine_type, tp_rank, pp_rank, and moe_ep_rank labels. The token counters add is_streaming. Group by model_name when one server hosts several models.

On a server that uses tensor parallelism, only rank 0 records request metrics by default, so a sum across ranks counts each request once. The --enable-metrics-for-all-schedulers flag makes every rank record separately, which doubles those sums unless you filter on tp_rank. Add tp_rank = '0' to your own queries against the scheduler gauges. The dashboard template already does this.

SGLang also splits the queue gauges when you run it with --enable-priority-scheduling. It reports the total under priority = '' and a breakdown under priority = '<int>', so summing every series counts each request twice. Filter on priority = '' for totals. This filter also works on servers that run without priority scheduling, where the label is absent.

The Collector splits each Prometheus histogram into three metrics. Query sglang:time_to_first_token_seconds.bucket for percentiles, and the matching .count and .sum metrics for rate and average. The base name alone returns nothing.

Metric names vary between SGLang releases. The names above come from v0.5.19. For the full list, see the SGLang production metrics reference.

Troubleshooting

The metrics endpoint returns 404

Likely cause: the server started without --enable-metrics.

Fix: add the flag and restart SGLang.

Verify: curl -s http://localhost:30000/metrics | head prints lines that start with # HELP.

The Collector logs a connection refused error

Likely cause: SGLang is bound to 127.0.0.1, so nothing outside the host can reach it.

Fix: start the server with --host 0.0.0.0, and open port 30000 to the Collector host in your firewall.

Verify: run curl -s http://<sglang-host>:30000/metrics | head from the machine that runs the Collector.

Metrics arrive but every value is zero

Likely cause: the server has served no requests since it started. Counters and gauges stay at zero until traffic arrives.

Fix: send a request to the server.

Verify: sglang:prompt_tokens_total rises in Metrics Explorer.

Traces do not appear

Likely cause: the server is still exporting over gRPC, which cannot reach SigNoz Cloud.

Fix: set OTEL_EXPORTER_OTLP_TRACES_PROTOCOL=http/protobuf and OTEL_EXPORTER_OTLP_TRACES_HEADERS in the environment of the SGLang process, then restart it.

Verify: spans with service.name = sglang appear in the Traces explorer.

Next steps

SGLang dashboard template
Set up alerts on queue depth and time to first token
LLM observability for tracing the application that calls this server

Get Help

If you need help with the steps in this topic, please reach out to us on SigNoz Community Slack. If you are a SigNoz Cloud user, please use in product chat support located at the bottom right corner of your SigNoz instance or contact us at cloud-support@signoz.io.