[Metrics] Complete removal of deprecated vllm:time_per_output_token_seconds metric (#32661)
This PR completes the removal of the deprecated vllm:time_per_output_token_seconds metric that was deprecated in v0.11, hidden in v0.12, scheduled for removal in v0.13, but delayed until v0.15. Signed-off-by: carlory <baofa.fan@daocloud.io> Co-authored-by: Claude Haiku 4.5 <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Haiku 4.5
parent
c4e5bdf61b
commit
bb9172030e
@@ -884,7 +884,7 @@
|
||||
"targets": [
|
||||
{
|
||||
"editorMode": "code",
|
||||
"expr": "rate(vllm:time_per_output_token_seconds_sum[$__interval]) / rate(vllm:time_per_output_token_seconds_count[$__interval])",
|
||||
"expr": "rate(vllm:inter_token_latency_seconds_sum[$__interval]) / rate(vllm:inter_token_latency_seconds_count[$__interval])",
|
||||
"legendFormat": "ITL (Avg)",
|
||||
"range": true,
|
||||
"refId": "A"
|
||||
@@ -895,7 +895,7 @@
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"expr": "histogram_quantile(0.50, sum by(le) (rate(vllm:time_per_output_token_seconds_bucket[$__interval])))",
|
||||
"expr": "histogram_quantile(0.50, sum by(le) (rate(vllm:inter_token_latency_seconds_bucket[$__interval])))",
|
||||
"hide": false,
|
||||
"instant": false,
|
||||
"legendFormat": "ITL (p50)",
|
||||
@@ -908,7 +908,7 @@
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"expr": "histogram_quantile(0.90, sum by(le) (rate(vllm:time_per_output_token_seconds_bucket[$__interval])))",
|
||||
"expr": "histogram_quantile(0.90, sum by(le) (rate(vllm:inter_token_latency_seconds_bucket[$__interval])))",
|
||||
"hide": false,
|
||||
"instant": false,
|
||||
"legendFormat": "ITL (p90)",
|
||||
@@ -921,7 +921,7 @@
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"expr": "histogram_quantile(0.99, sum by(le) (rate(vllm:time_per_output_token_seconds_bucket[$__interval])))",
|
||||
"expr": "histogram_quantile(0.99, sum by(le) (rate(vllm:inter_token_latency_seconds_bucket[$__interval])))",
|
||||
"hide": false,
|
||||
"instant": false,
|
||||
"legendFormat": "ITL (p99)",
|
||||
@@ -990,7 +990,7 @@
|
||||
"targets": [
|
||||
{
|
||||
"editorMode": "code",
|
||||
"expr": "histogram_quantile(0.90, sum by(le) (rate(vllm:time_per_output_token_seconds_bucket[$__range])))",
|
||||
"expr": "histogram_quantile(0.90, sum by(le) (rate(vllm:inter_token_latency_seconds_bucket[$__range])))",
|
||||
"legendFormat": "__auto",
|
||||
"range": true,
|
||||
"refId": "A"
|
||||
@@ -1057,7 +1057,7 @@
|
||||
"targets": [
|
||||
{
|
||||
"editorMode": "code",
|
||||
"expr": "histogram_quantile(0.99, sum by(le) (rate(vllm:time_per_output_token_seconds_bucket[$__range])))",
|
||||
"expr": "histogram_quantile(0.99, sum by(le) (rate(vllm:inter_token_latency_seconds_bucket[$__range])))",
|
||||
"legendFormat": "__auto",
|
||||
"range": true,
|
||||
"refId": "A"
|
||||
@@ -1124,7 +1124,7 @@
|
||||
"targets": [
|
||||
{
|
||||
"editorMode": "code",
|
||||
"expr": "(sum(increase(vllm:time_per_output_token_seconds_sum[$__range])) / sum(increase(vllm:time_per_output_token_seconds_count[$__range])))",
|
||||
"expr": "(sum(increase(vllm:inter_token_latency_seconds_sum[$__range])) / sum(increase(vllm:inter_token_latency_seconds_count[$__range])))",
|
||||
"legendFormat": "__auto",
|
||||
"range": true,
|
||||
"refId": "A"
|
||||
@@ -1191,7 +1191,7 @@
|
||||
"targets": [
|
||||
{
|
||||
"editorMode": "code",
|
||||
"expr": "histogram_quantile(0.50, sum by(le) (rate(vllm:time_per_output_token_seconds_bucket[$__range])))",
|
||||
"expr": "histogram_quantile(0.50, sum by(le) (rate(vllm:inter_token_latency_seconds_bucket[$__range])))",
|
||||
"legendFormat": "__auto",
|
||||
"range": true,
|
||||
"refId": "A"
|
||||
|
||||
@@ -309,9 +309,9 @@ spec:
|
||||
kind: PrometheusDatasource
|
||||
name: accelerators-thanos-querier-datasource
|
||||
query: >
|
||||
sum by (model_name) (rate(vllm:time_per_output_token_seconds_sum{model_name=~"$Deployment_id"}[$__interval]))
|
||||
sum by (model_name) (rate(vllm:inter_token_latency_seconds_sum{model_name=~"$Deployment_id"}[$__interval]))
|
||||
/
|
||||
sum by (model_name) (rate(vllm:time_per_output_token_seconds_count{model_name=~"$Deployment_id"}[$__interval]))
|
||||
sum by (model_name) (rate(vllm:inter_token_latency_seconds_count{model_name=~"$Deployment_id"}[$__interval]))
|
||||
seriesNameFormat: '{{model_name}}'
|
||||
- kind: TimeSeriesQuery
|
||||
spec:
|
||||
@@ -325,7 +325,7 @@ spec:
|
||||
histogram_quantile(
|
||||
0.50,
|
||||
sum by (le, model_name) (
|
||||
rate(vllm:time_per_output_token_seconds_bucket{model_name=~"$Deployment_id"}[$__interval])
|
||||
rate(vllm:inter_token_latency_seconds_bucket{model_name=~"$Deployment_id"}[$__interval])
|
||||
)
|
||||
)
|
||||
seriesNameFormat: '{{model_name}} p50'
|
||||
@@ -341,7 +341,7 @@ spec:
|
||||
histogram_quantile(
|
||||
0.90,
|
||||
sum by (le, model_name) (
|
||||
rate(vllm:time_per_output_token_seconds_bucket{model_name=~"$Deployment_id"}[$__interval])
|
||||
rate(vllm:inter_token_latency_seconds_bucket{model_name=~"$Deployment_id"}[$__interval])
|
||||
)
|
||||
)
|
||||
seriesNameFormat: '{{model_name}} p90'
|
||||
@@ -357,7 +357,7 @@ spec:
|
||||
histogram_quantile(
|
||||
0.99,
|
||||
sum by (le, model_name) (
|
||||
rate(vllm:time_per_output_token_seconds_bucket{model_name=~"$Deployment_id"}[$__interval])
|
||||
rate(vllm:inter_token_latency_seconds_bucket{model_name=~"$Deployment_id"}[$__interval])
|
||||
)
|
||||
)
|
||||
seriesNameFormat: '{{model_name}} p99'
|
||||
@@ -381,9 +381,9 @@ spec:
|
||||
kind: PrometheusDatasource
|
||||
name: accelerators-thanos-querier-datasource
|
||||
query: >
|
||||
(sum by (model_name) (increase(vllm:time_per_output_token_seconds_sum{model_name=~"$Deployment_id"}[$__range])))
|
||||
(sum by (model_name) (increase(vllm:inter_token_latency_seconds_sum{model_name=~"$Deployment_id"}[$__range])))
|
||||
/
|
||||
(sum by (model_name) (increase(vllm:time_per_output_token_seconds_count{model_name=~"$Deployment_id"}[$__range])))
|
||||
(sum by (model_name) (increase(vllm:inter_token_latency_seconds_count{model_name=~"$Deployment_id"}[$__range])))
|
||||
|
||||
"13":
|
||||
kind: Panel
|
||||
@@ -407,7 +407,7 @@ spec:
|
||||
histogram_quantile(
|
||||
0.50,
|
||||
sum by (le, model_name) (
|
||||
rate(vllm:time_per_output_token_seconds_bucket{model_name=~"$Deployment_id"}[$__interval])
|
||||
rate(vllm:inter_token_latency_seconds_bucket{model_name=~"$Deployment_id"}[$__interval])
|
||||
)
|
||||
)
|
||||
|
||||
@@ -433,7 +433,7 @@ spec:
|
||||
histogram_quantile(
|
||||
0.90,
|
||||
sum by (le, model_name) (
|
||||
rate(vllm:time_per_output_token_seconds_bucket{model_name=~"$Deployment_id"}[$__interval])
|
||||
rate(vllm:inter_token_latency_seconds_bucket{model_name=~"$Deployment_id"}[$__interval])
|
||||
)
|
||||
)
|
||||
|
||||
@@ -459,7 +459,7 @@ spec:
|
||||
histogram_quantile(
|
||||
0.99,
|
||||
sum by (le, model_name) (
|
||||
rate(vllm:time_per_output_token_seconds_bucket{model_name=~"$Deployment_id"}[$__interval])
|
||||
rate(vllm:inter_token_latency_seconds_bucket{model_name=~"$Deployment_id"}[$__interval])
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user