Adds metrics endpoint

METRICS.md

@@ -0,0 +1,84 @@
+# Aggregated Metrics Endpoint
+
+The model-runner now exposes an aggregated `/metrics` endpoint that collects and labels metrics from all active llama.cpp runners.
+
+## Overview
+
+When llama.cpp models are running, each server automatically exposes Prometheus-compatible metrics at its `/metrics` endpoint. The model-runner now aggregates these metrics from all active runners, adds identifying labels, and serves them through a unified `/metrics` endpoint. This provides a comprehensive view of all running models with proper Prometheus labeling.
+
+## Aggregated Metrics Format
+
+Instead of exposing metrics from a single runner, the endpoint now aggregates metrics from all active runners and adds labels to identify the source:
+
+### Example Output
+
+```prometheus
+# HELP llama_prompt_tokens_total Total number of prompt tokens processed
+# TYPE llama_prompt_tokens_total counter
+llama_prompt_tokens_total{backend="llama.cpp",model="llama3.2:latest",mode="completion"} 4934
+llama_prompt_tokens_total{backend="llama.cpp",model="ai/mxbai-embed-large:335M-F16",mode="embedding"} 4525
+
+# HELP llama_generation_tokens_total Total number of tokens generated
+# TYPE llama_generation_tokens_total counter
+llama_generation_tokens_total{backend="llama.cpp",model="llama3.2:latest",mode="completion"} 2156
+
+# HELP llama_requests_total Total number of requests processed
+# TYPE llama_requests_total counter
+llama_requests_total{backend="llama.cpp",model="llama3.2:latest",mode="completion"} 127
+llama_requests_total{backend="llama.cpp",model="ai/mxbai-embed-large:335M-F16",mode="embedding"} 89
+```
+
+### Labels Added
+
+Each metric is automatically labeled with:
+- **`backend`**: The inference backend (e.g., "llama.cpp")
+- **`model`**: The model name (e.g., "llama3.2:latest")
+- **`mode`**: The operation mode ("completion" or "embedding")
+
+## Usage
+
+### Enabling Metrics (Default)
+
+By default, the aggregated metrics endpoint is enabled. When the model-runner starts with active runners, you can access metrics at:
+
+```
+GET /metrics
+```
+
+### Disabling Metrics
+
+To disable the metrics endpoint, set the `DISABLE_METRICS` environment variable:
+
+```bash
+export DISABLE_METRICS=1
+```
+
+### TCP Port Access
+
+If you're running the model-runner with a TCP port (using `MODEL_RUNNER_PORT`), you can access metrics via HTTP:
+
+```bash
+# If MODEL_RUNNER_PORT=8080
+curl http://localhost:8080/metrics
+```
+
+### Unix Socket Access
+
+If using Unix sockets (default), you'll need to use a tool that supports Unix socket HTTP requests:
+
+```bash
+# Using curl with Unix socket
+curl --unix-socket model-runner.sock http://localhost/metrics
+```
+
+## Metrics Available
+
+The aggregated endpoint exposes all metrics from active llama.cpp runners, typically including:
+
+- **Request metrics**: Total requests, request duration, queue statistics
+- **Token metrics**: Prompt tokens, generation tokens, tokens per second
+- **Memory metrics**: Memory usage, cache statistics
+- **Model metrics**: Model loading status, context usage
+- **Performance metrics**: Processing latency, throughput
+
+All metrics retain their original names and types but gain the additional identifying labels.

README.md

@@ -95,6 +95,9 @@ curl http://localhost:8080/engines/llama.cpp/v1/chat/completions -X POST -d '{
 
 # Delete a model
 curl http://localhost:8080/models/ai/smollm2 -X DELETE
+
+# Get metrics
+curl http://localhost:8080/metrics
 ```
 
 The response will contain the model's reply:
@@ -122,3 +125,22 @@ The response will contain the model's reply:
   }
 }
 ```
+
+## Metrics
+
+The Model Runner exposes [the metrics endpoint](https://github.com/ggml-org/llama.cpp/tree/master/tools/server#get-metrics-prometheus-compatible-metrics-exporter) of llama.cpp server at the `/metrics` endpoint. This allows you to monitor model performance, request statistics, and resource usage.
+
+### Accessing Metrics
+
+```sh
+# Get metrics in Prometheus format
+curl http://localhost:8080/metrics
+```
+
+### Configuration
+
+- **Enable metrics (default)**: Metrics are enabled by default
+- **Disable metrics**: Set `DISABLE_METRICS=1` environment variable
+- **Monitoring integration**: Add the endpoint to your Prometheus configuration
+
+Check [METRICS.md](./METRICS.md) for more details.

go.mod

@@ -8,11 +8,14 @@ require (
 	github.com/docker/model-distribution v0.0.0-20250512190053-b3792c042d57
 	github.com/google/go-containerregistry v0.20.3
 	github.com/jaypipes/ghw v0.16.0
+	github.com/mattn/go-shellwords v1.0.12
 	github.com/opencontainers/go-digest v1.0.0
 	github.com/opencontainers/image-spec v1.1.1
+	github.com/prometheus/client_model v0.6.2
+	github.com/prometheus/common v0.64.0
 	github.com/sirupsen/logrus v1.9.3
 	github.com/stretchr/testify v1.10.0
-	golang.org/x/sync v0.12.0
+	golang.org/x/sync v0.14.0
 )
 
 require (
@@ -21,7 +24,7 @@ require (
 	github.com/containerd/errdefs v1.0.0 // indirect
 	github.com/containerd/log v0.1.0 // indirect
 	github.com/containerd/stargz-snapshotter/estargz v0.16.3 // indirect
-	github.com/davecgh/go-spew v1.1.1 // indirect
+	github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc // indirect
 	github.com/distribution/reference v0.6.0 // indirect
 	github.com/docker/cli v27.5.0+incompatible // indirect
 	github.com/docker/distribution v2.8.3+incompatible // indirect
@@ -34,28 +37,31 @@ require (
 	github.com/henvic/httpretty v0.1.4 // indirect
 	github.com/jaypipes/pcidb v1.0.1 // indirect
 	github.com/json-iterator/go v1.1.12 // indirect
-	github.com/klauspost/compress v1.17.11 // indirect
-	github.com/mattn/go-shellwords v1.0.12 // indirect
+	github.com/klauspost/compress v1.18.0 // indirect
 	github.com/mitchellh/go-homedir v1.1.0 // indirect
 	github.com/moby/locker v1.0.1 // indirect
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/modern-go/reflect2 v1.0.2 // indirect
+	github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
 	github.com/pkg/errors v0.9.1 // indirect
-	github.com/pmezard/go-difflib v1.0.0 // indirect
+	github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect
 	github.com/rs/dnscache v0.0.0-20230804202142-fc85eb664529 // indirect
 	github.com/smallnest/ringbuffer v0.0.0-20241116012123-461381446e3d // indirect
 	github.com/vbatts/tar-split v0.11.6 // indirect
 	go.opentelemetry.io/auto/sdk v1.1.0 // indirect
-	go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.58.0 // indirect
+	go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.60.0 // indirect
 	go.opentelemetry.io/otel v1.35.0 // indirect
 	go.opentelemetry.io/otel/metric v1.35.0 // indirect
 	go.opentelemetry.io/otel/trace v1.35.0 // indirect
-	golang.org/x/crypto v0.35.0 // indirect
-	golang.org/x/exp v0.0.0-20241108190413-2d47ceb2692f // indirect
-	golang.org/x/mod v0.22.0 // indirect
-	golang.org/x/sys v0.31.0 // indirect
-	golang.org/x/tools v0.29.0 // indirect
+	golang.org/x/crypto v0.37.0 // indirect
+	golang.org/x/exp v0.0.0-20250106191152-7588d65b2ba8 // indirect
+	golang.org/x/mod v0.24.0 // indirect
+	golang.org/x/sys v0.33.0 // indirect
+	golang.org/x/tools v0.32.0 // indirect
 	gonum.org/v1/gonum v0.15.1 // indirect
+	google.golang.org/genproto/googleapis/rpc v0.0.0-20250414145226-207652e42e2e // indirect
+	google.golang.org/grpc v1.72.0 // indirect
+	google.golang.org/protobuf v1.36.6 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 	howett.net/plist v1.0.0 // indirect
 )

go.sum

@@ -27,8 +27,9 @@ github.com/containerd/stargz-snapshotter/estargz v0.16.3/go.mod h1:uyr4BfYfOj3G9
 github.com/containerd/typeurl/v2 v2.2.3 h1:yNA/94zxWdvYACdYO8zofhrTVuQY73fFU1y++dYSw40=
 github.com/containerd/typeurl/v2 v2.2.3/go.mod h1:95ljDnPfD3bAbDJRugOiShd/DlAAsxGtUBhJxIn7SCk=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
-github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc h1:U9qPSI2PIWSS1VwoXQT9A3Wy9MM3WgvqSxFWenqJduM=
+github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/distribution/reference v0.6.0 h1:0IXCQ5g4/QMHHkarYzh5l+u8T3t73zM5QvfrDyIgxBk=
 github.com/distribution/reference v0.6.0/go.mod h1:BbU0aIcezP1/5jX/8MP0YiH4SdvB5Y4f/wlDRiLyi3E=
 github.com/docker/cli v27.5.0+incompatible h1:aMphQkcGtpHixwwhAXJT1rrK/detk2JIvDaFkLctbGM=
@@ -58,6 +59,8 @@ github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX
 github.com/google/go-containerregistry v0.20.3 h1:oNx7IdTI936V8CQRveCjaxOiegWwvM7kqkbXTpyiovI=
 github.com/google/go-containerregistry v0.20.3/go.mod h1:w00pIgBRDVUDFM6bq+Qx8lwNWK+cxgCuX1vd3PIBDNI=
 github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
+github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
+github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/gpustack/gguf-parser-go v0.14.1 h1:tmz2eTnSEFfE52V10FESqo9oAUquZ6JKQFntWC/wrEg=
 github.com/gpustack/gguf-parser-go v0.14.1/go.mod h1:GvHh1Kvvq5ojCOsJ5UpwiJJmIjFw3Qk5cW7R+CZ3IJo=
 github.com/henvic/httpretty v0.1.4 h1:Jo7uwIRWVFxkqOnErcoYfH90o3ddQyVrSANeS4cxYmU=
@@ -69,8 +72,8 @@ github.com/jaypipes/pcidb v1.0.1/go.mod h1:6xYUz/yYEyOkIkUt2t2J2folIuZ4Yg6uByCGF
 github.com/jessevdk/go-flags v1.4.0/go.mod h1:4FA24M0QyGHXBuZZK/XkWh8h0e1EYbRYJSGM75WSRxI=
 github.com/json-iterator/go v1.1.12 h1:PV8peI4a0ysnczrg+LtxykD8LfKY9ML6u2jnxaEnrnM=
 github.com/json-iterator/go v1.1.12/go.mod h1:e30LSqwooZae/UwlEbR2852Gd8hjQvJoHmT4TnhNGBo=
-github.com/klauspost/compress v1.17.11 h1:In6xLpyWOi1+C7tXUUWv2ot1QvBjxevKAaI6IXrJmUc=
-github.com/klauspost/compress v1.17.11/go.mod h1:pMDklpSncoRMuLFrf1W9Ss9KT+0rH90U12bZKk7uwG0=
+github.com/klauspost/compress v1.18.0 h1:c/Cqfb0r+Yi+JtIEq73FWXVkRonBlf0CRNYc8Zttxdo=
+github.com/klauspost/compress v1.18.0/go.mod h1:2Pp+KzxcywXVXMr50+X0Q/Lsb43OQHYWRCY2AiWywWQ=
 github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
 github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
 github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
@@ -90,14 +93,21 @@ github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd h1:TRLaZ9cD/w
 github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
 github.com/modern-go/reflect2 v1.0.2 h1:xBagoLtFs94CBntxluKeaWgTMpvLxC4ur3nMaC9Gz0M=
 github.com/modern-go/reflect2 v1.0.2/go.mod h1:yWuevngMOJpCy52FWWMvUC8ws7m/LJsjYzDa0/r8luk=
+github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 h1:C3w9PqII01/Oq1c1nUAm88MOHcQC9l5mIlSMApZMrHA=
+github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822/go.mod h1:+n7T8mK8HuQTcFwEeznm/DIxMOiR9yIdICNftLE1DvQ=
 github.com/opencontainers/go-digest v1.0.0 h1:apOUWs51W5PlhuyGyz9FCeeBIOUDA/6nW8Oi/yOhh5U=
 github.com/opencontainers/go-digest v1.0.0/go.mod h1:0JzlMkj0TRzQZfJkVvzbP0HBR3IKzErnv2BNG4W4MAM=
 github.com/opencontainers/image-spec v1.1.1 h1:y0fUlFfIZhPF1W537XOLg0/fcx6zcHCJwooC2xJA040=
 github.com/opencontainers/image-spec v1.1.1/go.mod h1:qpqAh3Dmcf36wStyyWU+kCeDgrGnAve2nCC8+7h8Q0M=
 github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
 github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
-github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 h1:Jamvg5psRIccs7FGNTlIRMkT8wgtp5eCXdBlqhYGL6U=
+github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/prometheus/client_model v0.6.2 h1:oBsgwpGs7iVziMvrGhE53c/GrLUsZdHnqNwqPLxwZyk=
+github.com/prometheus/client_model v0.6.2/go.mod h1:y3m2F6Gdpfy6Ut/GBsUqTWZqCUvMVzSfMLjcu6wAwpE=
+github.com/prometheus/common v0.64.0 h1:pdZeA+g617P7oGv1CzdTzyeShxAGrTBsolKNOLQPGO4=
+github.com/prometheus/common v0.64.0/go.mod h1:0gZns+BLRQ3V6NdaerOhMbwwRbNh9hkGINtQAsP5GS8=
 github.com/rogpeppe/go-internal v1.13.1 h1:KvO1DLK/DRN07sQ1LQKScxyZJuNnedQ5/wKSR38lUII=
 github.com/rogpeppe/go-internal v1.13.1/go.mod h1:uMEvuHeurkdAXX61udpOXGD/AzZDWNMNyH2VO9fmH0o=
 github.com/rs/dnscache v0.0.0-20230804202142-fc85eb664529 h1:18kd+8ZUlt/ARXhljq+14TwAoKa61q6dX8jtwOf6DH8=
@@ -117,39 +127,43 @@ go.opencensus.io v0.24.0 h1:y73uSU6J157QMP2kn2r30vwW1A2W2WFwSCGnAVxeaD0=
 go.opencensus.io v0.24.0/go.mod h1:vNK8G9p7aAivkbmorf4v+7Hgx+Zs0yY+0fOtgBfjQKo=
 go.opentelemetry.io/auto/sdk v1.1.0 h1:cH53jehLUN6UFLY71z+NDOiNJqDdPRaXzTel0sJySYA=
 go.opentelemetry.io/auto/sdk v1.1.0/go.mod h1:3wSPjt5PWp2RhlCcmmOial7AvC4DQqZb7a7wCow3W8A=
-go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.58.0 h1:yd02MEjBdJkG3uabWP9apV+OuWRIXGDuJEUJbOHmCFU=
-go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.58.0/go.mod h1:umTcuxiv1n/s/S6/c2AT/g2CQ7u5C59sHDNmfSwgz7Q=
+go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.60.0 h1:sbiXRNDSWJOTobXh5HyQKjq6wUC5tNybqjIqDpAY4CU=
+go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.60.0/go.mod h1:69uWxva0WgAA/4bu2Yy70SLDBwZXuQ6PbBpbsa5iZrQ=
 go.opentelemetry.io/otel v1.35.0 h1:xKWKPxrxB6OtMCbmMY021CqC45J+3Onta9MqjhnusiQ=
 go.opentelemetry.io/otel v1.35.0/go.mod h1:UEqy8Zp11hpkUrL73gSlELM0DupHoiq72dR+Zqel/+Y=
 go.opentelemetry.io/otel/metric v1.35.0 h1:0znxYu2SNyuMSQT4Y9WDWej0VpcsxkuklLa4/siN90M=
 go.opentelemetry.io/otel/metric v1.35.0/go.mod h1:nKVFgxBZ2fReX6IlyW28MgZojkoAkJGaE8CpgeAU3oE=
+go.opentelemetry.io/otel/sdk v1.35.0 h1:iPctf8iprVySXSKJffSS79eOjl9pvxV9ZqOWT0QejKY=
+go.opentelemetry.io/otel/sdk v1.35.0/go.mod h1:+ga1bZliga3DxJ3CQGg3updiaAJoNECOgJREo9KHGQg=
+go.opentelemetry.io/otel/sdk/metric v1.35.0 h1:1RriWBmCKgkeHEhM7a2uMjMUfP7MsOF5JpUCaEqEI9o=
+go.opentelemetry.io/otel/sdk/metric v1.35.0/go.mod h1:is6XYCUMpcKi+ZsOvfluY5YstFnhW0BidkR+gL+qN+w=
 go.opentelemetry.io/otel/trace v1.35.0 h1:dPpEfJu1sDIqruz7BHFG3c7528f6ddfSWfFDVt/xgMs=
 go.opentelemetry.io/otel/trace v1.35.0/go.mod h1:WUk7DtFp1Aw2MkvqGdwiXYDZZNvA/1J8o6xRXLrIkyc=
-golang.org/x/crypto v0.35.0 h1:b15kiHdrGCHrP6LvwaQ3c03kgNhhiMgvlhxHQhmg2Xs=
-golang.org/x/crypto v0.35.0/go.mod h1:dy7dXNW32cAb/6/PRuTNsix8T+vJAqvuIy5Bli/x0YQ=
-golang.org/x/exp v0.0.0-20241108190413-2d47ceb2692f h1:XdNn9LlyWAhLVp6P/i8QYBW+hlyhrhei9uErw2B5GJo=
-golang.org/x/exp v0.0.0-20241108190413-2d47ceb2692f/go.mod h1:D5SMRVC3C2/4+F/DB1wZsLRnSNimn2Sp/NPsCrsv8ak=
-golang.org/x/mod v0.22.0 h1:D4nJWe9zXqHOmWqj4VMOJhvzj7bEZg4wEYa759z1pH4=
-golang.org/x/mod v0.22.0/go.mod h1:6SkKJ3Xj0I0BrPOZoBy3bdMptDDU9oJrpohJ3eWZ1fY=
+golang.org/x/crypto v0.37.0 h1:kJNSjF/Xp7kU0iB2Z+9viTPMW4EqqsrywMXLJOOsXSE=
+golang.org/x/crypto v0.37.0/go.mod h1:vg+k43peMZ0pUMhYmVAWysMK35e6ioLh3wB8ZCAfbVc=
+golang.org/x/exp v0.0.0-20250106191152-7588d65b2ba8 h1:yqrTHse8TCMW1M1ZCP+VAR/l0kKxwaAIqN/il7x4voA=
+golang.org/x/exp v0.0.0-20250106191152-7588d65b2ba8/go.mod h1:tujkw807nyEEAamNbDrEGzRav+ilXA7PCRAd6xsmwiU=
+golang.org/x/mod v0.24.0 h1:ZfthKaKaT4NrhGVZHO1/WDTwGES4De8KtWO0SIbNJMU=
+golang.org/x/mod v0.24.0/go.mod h1:IXM97Txy2VM4PJ3gI61r1YEk/gAj6zAHN3AdZt6S9Ww=
 golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
-golang.org/x/sync v0.12.0 h1:MHc5BpPuC30uJk597Ri8TV3CNZcTLu6B6z4lJy+g6Jw=
-golang.org/x/sync v0.12.0/go.mod h1:1dzgHSNfp02xaA81J2MS99Qcpr2w7fw1gpm99rleRqA=
+golang.org/x/sync v0.14.0 h1:woo0S4Yywslg6hp4eUFjTVOyKt0RookbpAHG4c1HmhQ=
+golang.org/x/sync v0.14.0/go.mod h1:1dzgHSNfp02xaA81J2MS99Qcpr2w7fw1gpm99rleRqA=
 golang.org/x/sys v0.0.0-20190916202348-b4ddaad3f8a3/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20220715151400-c0bba94af5f8/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.31.0 h1:ioabZlmFYtWhL+TRYpcnNlLwhyxaM9kWTDEmfnprqik=
-golang.org/x/sys v0.31.0/go.mod h1:BJP2sWEmIv4KK5OTEluFJCKSidICx8ciO85XgH3Ak8k=
-golang.org/x/term v0.29.0 h1:L6pJp37ocefwRRtYPKSWOWzOtWSxVajvz2ldH/xi3iU=
-golang.org/x/term v0.29.0/go.mod h1:6bl4lRlvVuDgSf3179VpIxBF0o10JUpXWOnI7nErv7s=
-golang.org/x/tools v0.29.0 h1:Xx0h3TtM9rzQpQuR4dKLrdglAmCEN5Oi+P74JdhdzXE=
-golang.org/x/tools v0.29.0/go.mod h1:KMQVMRsVxU6nHCFXrBPhDB8XncLNLM0lIy/F14RP588=
+golang.org/x/sys v0.33.0 h1:q3i8TbbEz+JRD9ywIRlyRAQbM0qF7hu24q3teo2hbuw=
+golang.org/x/sys v0.33.0/go.mod h1:BJP2sWEmIv4KK5OTEluFJCKSidICx8ciO85XgH3Ak8k=
+golang.org/x/term v0.31.0 h1:erwDkOK1Msy6offm1mOgvspSkslFnIGsFnxOKoufg3o=
+golang.org/x/term v0.31.0/go.mod h1:R4BeIy7D95HzImkxGkTW1UQTtP54tio2RyHz7PwK0aw=
+golang.org/x/tools v0.32.0 h1:Q7N1vhpkQv7ybVzLFtTjvQya2ewbwNDZzUgfXGqtMWU=
+golang.org/x/tools v0.32.0/go.mod h1:ZxrU41P/wAbZD8EDa6dDCa6XfpkhJ7HFMjHJXfBDu8s=
 gonum.org/v1/gonum v0.15.1 h1:FNy7N6OUZVUaWG9pTiD+jlhdQ3lMP+/LcTpJ6+a8sQ0=
 gonum.org/v1/gonum v0.15.1/go.mod h1:eZTZuRFrzu5pcyjN5wJhcIhnUdNijYxX1T2IcrOGY0o=
-google.golang.org/genproto/googleapis/rpc v0.0.0-20241021214115-324edc3d5d38 h1:zciRKQ4kBpFgpfC5QQCVtnnNAcLIqweL7plyZRQHVpI=
-google.golang.org/genproto/googleapis/rpc v0.0.0-20241021214115-324edc3d5d38/go.mod h1:GX3210XPVPUjJbTUbvwI8f2IpZDMZuPJWDzDuebbviI=
-google.golang.org/grpc v1.68.1 h1:oI5oTa11+ng8r8XMMN7jAOmWfPZWbYpCFaMUTACxkM0=
-google.golang.org/grpc v1.68.1/go.mod h1:+q1XYFJjShcqn0QZHvCyeR4CXPA+llXIeUIfIe00waw=
-google.golang.org/protobuf v1.36.3 h1:82DV7MYdb8anAVi3qge1wSnMDrnKK7ebr+I0hHRN1BU=
-google.golang.org/protobuf v1.36.3/go.mod h1:9fA7Ob0pmnwhb644+1+CVWFRbNajQ6iRojtC/QF5bRE=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20250414145226-207652e42e2e h1:ztQaXfzEXTmCBvbtWYRhJxW+0iJcz2qXfd38/e9l7bA=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20250414145226-207652e42e2e/go.mod h1:qQ0YXyHHx3XkvlzUtpXDkS29lDSafHMZBAZDc03LQ3A=
+google.golang.org/grpc v1.72.0 h1:S7UkcVa60b5AAQTaO6ZKamFp1zMZSU0fGDK2WZLbBnM=
+google.golang.org/grpc v1.72.0/go.mod h1:wH5Aktxcg25y1I3w7H69nHfXdOG3UiadoBtjh3izSDM=
+google.golang.org/protobuf v1.36.6 h1:z1NpPI8ku2WgiWnf+t9wTPsn6eP1L7ksHUlkfLvd9xY=
+google.golang.org/protobuf v1.36.6/go.mod h1:jduwjTPXsFjZGTmRluh+L6NjiWu7pchiJ2/5YcXBHnY=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
 gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=

main.go

@@ -112,6 +112,18 @@ func main() {
 		router.Handle(route, scheduler)
 	}
 
+	// Add metrics endpoint if enabled
+	if os.Getenv("DISABLE_METRICS") != "1" {
+		metricsHandler := metrics.NewAggregatedMetricsHandler(
+			log.WithField("component", "metrics"),
+			scheduler,
+		)
+		router.Handle("/metrics", metricsHandler)
+		log.Info("Metrics endpoint enabled at /metrics")
+	} else {
+		log.Info("Metrics endpoint disabled")
+	}
+
 	server := &http.Server{Handler: router}
 	serverErrors := make(chan error, 1)
 

pkg/inference/backends/llamacpp/llamacpp_config.go

@@ -15,7 +15,7 @@ type Config struct {
 
 // NewDefaultLlamaCppConfig creates a new LlamaCppConfig with default values.
 func NewDefaultLlamaCppConfig() *Config {
-	args := append([]string{"--jinja", "-ngl", "100"})
+	args := append([]string{"--jinja", "-ngl", "100", "--metrics"})
 
 	// Special case for Windows ARM64
 	if runtime.GOOS == "windows" && runtime.GOARCH == "arm64" {

pkg/inference/backends/llamacpp/llamacpp_config_test.go

@@ -81,6 +81,7 @@ func TestGetArgs(t *testing.T) {
 			expected: []string{
 				"--jinja",
 				"-ngl", "100",
+				"--metrics",
 				"--model", modelPath,
 				"--host", socket,
 			},
@@ -91,6 +92,7 @@ func TestGetArgs(t *testing.T) {
 			expected: []string{
 				"--jinja",
 				"-ngl", "100",
+				"--metrics",
 				"--model", modelPath,
 				"--host", socket,
 				"--embeddings",