We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 6367bde commit d98eae4Copy full SHA for d98eae4
examples/online_serving/prometheus_grafana/grafana.json
@@ -852,7 +852,7 @@
852
"uid": "${DS_PROMETHEUS}"
853
},
854
"editorMode": "code",
855
- "expr": "vllm:gpu_cache_usage_perc{model_name=\"$model_name\"}",
+ "expr": "vllm:kv_cache_usage_perc{model_name=\"$model_name\"}",
856
"instant": false,
857
"legendFormat": "GPU Cache Usage",
858
"range": true,
0 commit comments