Skip to content

[Bugfix][Helm]: update Grafana dashboards to current vLLM metric names #989

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
bitnik wants to merge 1 commit into
base: main
Choose a base branch
from
+13 −105
Open

[Bugfix][Helm]: update Grafana dashboards to current vLLM metric names #989

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
72 changes: 5 additions & 67 deletions helm/dashboards/vllm-dashboard.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -369,7 +369,7 @@
"targets": [
{
"editorMode": "builder",
"expr": "avg(vllm:time_per_output_token_seconds_sum) / avg(vllm:time_per_output_token_seconds_count)",
"expr": "avg(vllm:request_time_per_output_token_seconds_sum) / avg(vllm:request_time_per_output_token_seconds_count)",
"legendFormat": "Avg ITL",
"range": true,
"refId": "A"
Expand Down Expand Up @@ -656,6 +656,7 @@
"color": {
"mode": "palette-classic"
},
"unit": "percentunit",
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
Expand Down Expand Up @@ -729,7 +730,7 @@
"targets": [
{
"editorMode": "builder",
"expr": "vllm:gpu_cache_usage_perc",
"expr": "vllm:kv_cache_usage_perc",
Comment thread
bitnik marked this conversation as resolved.
"legendFormat": "{{instance}}",
"range": true,
"refId": "A"
Expand Down Expand Up @@ -834,70 +835,6 @@
"title": "GPU KV Cache Hit Rate",
"type": "timeseries"
},
{

@gemini-code-assist gemini-code-assist Bot Jul 1, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

There are two improvement opportunities here:

  1. Deprecated Metrics: The preceding panel "GPU KV Cache Hit Rate" (lines 800-836) uses the deprecated metrics vllm:gpu_prefix_cache_hits_total and vllm:gpu_prefix_cache_queries_total (at line 825). Since this PR updates the dashboard queries to current vLLM metric names, these should be updated to the current non-deprecated metric names: vllm:prefix_cache_hits_total and vllm:prefix_cache_queries_total respectively.
  2. Panel Layout: Since the "Number of Swapped Requests" panel (which was positioned at x: 12, y: 39 with width 12) has been removed, the "GPU KV Cache Hit Rate" panel (positioned at x: 0, y: 39 with width 12) now has an empty space of width 12 next to it. Consider increasing its width (w) to 24 (at line 802) to utilize the full width of the dashboard.

"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"description": "Requests moved from GPU to CPU",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green"
},
{
"color": "red",
"value": 0
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 39
},
"id": 21,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"percentChangeColorMode": "standard",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "12.0.0+security-01",
"targets": [
{
"editorMode": "builder",
"expr": "vllm:num_requests_swapped",
"legendFormat": "Swapped Requests",
"range": true,
"refId": "A"
}
],
"title": "Number of Swapped Requests",
"type": "stat"
},
{
"collapsed": false,
"gridPos": {
Expand All @@ -921,6 +858,7 @@
"color": {
"mode": "palette-classic"
},
"unit": "percentunit",
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
Expand Down Expand Up @@ -995,7 +933,7 @@
{
"disableTextWrap": false,
"editorMode": "builder",
"expr": "vllm:gpu_cache_usage_perc",
"expr": "vllm:kv_cache_usage_perc",
Comment thread
bitnik marked this conversation as resolved.
"fullMetaSearch": false,
"includeNullMetadata": true,
"legendFormat": "GPU Usage",
Expand Down
46 changes: 8 additions & 38 deletions helm/dashboards/vllm-model-metrics-dashboard.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -402,7 +402,7 @@
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "histogram_quantile(0.99, sum by(le) (rate(vllm:time_per_output_token_seconds_bucket{model_name=\"$model_name\"}[$__rate_interval])))",
"expr": "histogram_quantile(0.99, sum by(le) (rate(vllm:request_time_per_output_token_seconds_bucket{model_name=\"$model_name\"}[$__rate_interval])))",
"fullMetaSearch": false,
"includeNullMetadata": false,
"instant": false,
Expand All @@ -418,7 +418,7 @@
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "histogram_quantile(0.95, sum by(le) (rate(vllm:time_per_output_token_seconds_bucket{model_name=\"$model_name\"}[$__rate_interval])))",
"expr": "histogram_quantile(0.95, sum by(le) (rate(vllm:request_time_per_output_token_seconds_bucket{model_name=\"$model_name\"}[$__rate_interval])))",
"fullMetaSearch": false,
"hide": false,
"includeNullMetadata": false,
Expand All @@ -435,7 +435,7 @@
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "histogram_quantile(0.9, sum by(le) (rate(vllm:time_per_output_token_seconds_bucket{model_name=\"$model_name\"}[$__rate_interval])))",
"expr": "histogram_quantile(0.9, sum by(le) (rate(vllm:request_time_per_output_token_seconds_bucket{model_name=\"$model_name\"}[$__rate_interval])))",
"fullMetaSearch": false,
"hide": false,
"includeNullMetadata": false,
Expand All @@ -452,7 +452,7 @@
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "histogram_quantile(0.5, sum by(le) (rate(vllm:time_per_output_token_seconds_bucket{model_name=\"$model_name\"}[$__rate_interval])))",
"expr": "histogram_quantile(0.5, sum by(le) (rate(vllm:request_time_per_output_token_seconds_bucket{model_name=\"$model_name\"}[$__rate_interval])))",
"fullMetaSearch": false,
"hide": false,
"includeNullMetadata": false,
Expand All @@ -468,7 +468,7 @@
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"expr": "rate(vllm:time_per_output_token_seconds_sum{model_name=\"$model_name\"}[$__rate_interval])\n/\nrate(vllm:time_per_output_token_seconds_count{model_name=\"$model_name\"}[$__rate_interval])",
"expr": "rate(vllm:request_time_per_output_token_seconds_sum{model_name=\"$model_name\"}[$__rate_interval])\n/\nrate(vllm:request_time_per_output_token_seconds_count{model_name=\"$model_name\"}[$__rate_interval])",
"hide": false,
"instant": false,
"legendFormat": "Mean",
Expand All @@ -484,7 +484,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"description": "Number of requests in RUNNING, WAITING, and SWAPPED state",
"description": "Number of requests in RUNNING, and WAITING",
"fieldConfig": {
"defaults": {
"color": {
Expand Down Expand Up @@ -577,23 +577,6 @@
"refId": "A",
"useBackend": false
},
{
Comment thread
bitnik marked this conversation as resolved.
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "vllm:num_requests_swapped{model_name=\"$model_name\"}",
"fullMetaSearch": false,
"hide": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "Num Swapped",
"range": true,
"refId": "B",
"useBackend": false
},
{
"datasource": {
"type": "prometheus",
Expand All @@ -608,7 +591,7 @@
"instant": false,
"legendFormat": "Num Waiting",
"range": true,
"refId": "C",
"refId": "B",
"useBackend": false
}
],
Expand Down Expand Up @@ -869,24 +852,11 @@
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"expr": "vllm:gpu_cache_usage_perc{model_name=\"$model_name\"}",
"expr": "vllm:kv_cache_usage_perc{model_name=\"$model_name\"}",
"instant": false,
"legendFormat": "GPU Cache Usage",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"expr": "vllm:cpu_cache_usage_perc{model_name=\"$model_name\"}",
"hide": false,
"instant": false,
"legendFormat": "CPU Cache Usage",
"range": true,
"refId": "B"
}
],
"title": "Cache Utilization",
Expand Down