[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>

docs/design/metrics.md

@@ -49,7 +49,7 @@ The subset of metrics exposed in the Grafana dashboard gives us an indication of
 - `vllm:e2e_request_latency_seconds_bucket` - End to end request latency measured in seconds.
 - `vllm:prompt_tokens` - Prompt tokens.
 - `vllm:generation_tokens` - Generation tokens.
-- `vllm:time_per_output_token_seconds` - Inter-token latency (Time Per Output Token, TPOT) in seconds.
+- `vllm:inter_token_latency_seconds` - Inter-token latency (Time Per Output Token, TPOT) in seconds.
 - `vllm:time_to_first_token_seconds` - Time to First Token (TTFT) latency in seconds.
 - `vllm:num_requests_running` (also, `_swapped` and `_waiting`) - Number of requests in the RUNNING, WAITING, and SWAPPED states.
 - `vllm:kv_cache_usage_perc` - Percentage of used cache blocks by vLLM.

examples/online_serving/dashboards/grafana/performance_statistics.json

@@ -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"

examples/online_serving/dashboards/perses/performance_statistics.yaml

@@ -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])
                       )
                     )
 

tests/entrypoints/instrumentator/test_metrics.py

@@ -77,7 +77,7 @@ def _get_expected_values(num_requests: int, prompt_ids: list[int], max_tokens: i
     # {metric_family: [(suffix, expected_value)]}
     return {
         "vllm:time_to_first_token_seconds": [("_count", num_requests)],
-        "vllm:time_per_output_token_seconds": [
+        "vllm:inter_token_latency_seconds": [
             ("_count", num_requests * (max_tokens - 1))
         ],
         "vllm:e2e_request_latency_seconds": [("_count", num_requests)],
@@ -203,9 +203,6 @@ EXPECTED_METRICS_V1 = [
     "vllm:request_params_max_tokens_sum",
     "vllm:request_params_max_tokens_bucket",
     "vllm:request_params_max_tokens_count",
-    "vllm:time_per_output_token_seconds_sum",
-    "vllm:time_per_output_token_seconds_bucket",
-    "vllm:time_per_output_token_seconds_count",
     "vllm:time_to_first_token_seconds_sum",
     "vllm:time_to_first_token_seconds_bucket",
     "vllm:time_to_first_token_seconds_count",
@@ -238,9 +235,6 @@ HIDDEN_DEPRECATED_METRICS: list[str] = [
     "vllm:gpu_cache_usage_perc",
     "vllm:gpu_prefix_cache_queries",
     "vllm:gpu_prefix_cache_hits",
-    "vllm:time_per_output_token_seconds_sum",
-    "vllm:time_per_output_token_seconds_bucket",
-    "vllm:time_per_output_token_seconds_count",
 ]
 
 

vllm/v1/metrics/loggers.py

@@ -715,43 +715,6 @@ class PrometheusStatLogger(AggregateStatLoggerBase):
             histogram_time_to_first_token, engine_indexes, model_name
         )
 
-        # Deprecated in 0.11 - Renamed as vllm:inter_token_latency_seconds
-        # With 0.12.x you can enable with --show-hidden-metrics-for-version=0.11
-        # TODO: remove in 0.13.0
-        if self.show_hidden_metrics:
-            histogram_time_per_output_token = self._histogram_cls(
-                name="vllm:time_per_output_token_seconds",
-                documentation=(
-                    "Histogram of time per output token in seconds."
-                    "DEPRECATED: Use vllm:inter_token_latency_seconds instead."
-                ),
-                buckets=[
-                    0.01,
-                    0.025,
-                    0.05,
-                    0.075,
-                    0.1,
-                    0.15,
-                    0.2,
-                    0.3,
-                    0.4,
-                    0.5,
-                    0.75,
-                    1.0,
-                    2.5,
-                    5.0,
-                    7.5,
-                    10.0,
-                    20.0,
-                    40.0,
-                    80.0,
-                ],
-                labelnames=labelnames,
-            )
-            self.histogram_time_per_output_token = make_per_engine(
-                histogram_time_per_output_token, engine_indexes, model_name
-            )
-
         histogram_inter_token_latency = self._histogram_cls(
             name="vllm:inter_token_latency_seconds",
             documentation="Histogram of inter-token latency in seconds.",
@@ -1124,8 +1087,6 @@ class PrometheusStatLogger(AggregateStatLoggerBase):
             self.histogram_time_to_first_token[engine_idx].observe(ttft)
         for itl in iteration_stats.inter_token_latencies_iter:
             self.histogram_inter_token_latency[engine_idx].observe(itl)
-            if self.show_hidden_metrics:
-                self.histogram_time_per_output_token[engine_idx].observe(itl)
 
         for finished_request in iteration_stats.finished_requests:
             self.counter_request_success[finished_request.finish_reason][