fix(monitoring): update Grafana dashboard metrics prefix from sglang: to sglang_ (#15758)
This commit is contained in:
@@ -109,7 +109,7 @@
|
|||||||
},
|
},
|
||||||
"disableTextWrap": false,
|
"disableTextWrap": false,
|
||||||
"editorMode": "code",
|
"editorMode": "code",
|
||||||
"expr": "histogram_quantile(0.99, sum by (le) (rate(sglang:e2e_request_latency_seconds_bucket[$__rate_interval])))\r\n",
|
"expr": "histogram_quantile(0.99, sum by (le) (rate(sglang_e2e_request_latency_seconds_bucket[$__rate_interval])))\r\n",
|
||||||
"fullMetaSearch": false,
|
"fullMetaSearch": false,
|
||||||
"includeNullMetadata": true,
|
"includeNullMetadata": true,
|
||||||
"instant": false,
|
"instant": false,
|
||||||
@@ -125,7 +125,7 @@
|
|||||||
},
|
},
|
||||||
"disableTextWrap": false,
|
"disableTextWrap": false,
|
||||||
"editorMode": "code",
|
"editorMode": "code",
|
||||||
"expr": "histogram_quantile(0.9, sum by (le) (rate(sglang:e2e_request_latency_seconds_bucket[$__rate_interval])))\r\n",
|
"expr": "histogram_quantile(0.9, sum by (le) (rate(sglang_e2e_request_latency_seconds_bucket[$__rate_interval])))\r\n",
|
||||||
"fullMetaSearch": false,
|
"fullMetaSearch": false,
|
||||||
"hide": false,
|
"hide": false,
|
||||||
"includeNullMetadata": true,
|
"includeNullMetadata": true,
|
||||||
@@ -142,7 +142,7 @@
|
|||||||
},
|
},
|
||||||
"disableTextWrap": false,
|
"disableTextWrap": false,
|
||||||
"editorMode": "code",
|
"editorMode": "code",
|
||||||
"expr": "histogram_quantile(0.5, sum by (le) (rate(sglang:e2e_request_latency_seconds_bucket[$__rate_interval])))\r\n",
|
"expr": "histogram_quantile(0.5, sum by (le) (rate(sglang_e2e_request_latency_seconds_bucket[$__rate_interval])))\r\n",
|
||||||
"fullMetaSearch": false,
|
"fullMetaSearch": false,
|
||||||
"hide": false,
|
"hide": false,
|
||||||
"includeNullMetadata": true,
|
"includeNullMetadata": true,
|
||||||
@@ -159,7 +159,7 @@
|
|||||||
},
|
},
|
||||||
"disableTextWrap": false,
|
"disableTextWrap": false,
|
||||||
"editorMode": "code",
|
"editorMode": "code",
|
||||||
"expr": "avg(rate(sglang:e2e_request_latency_seconds_sum[$__rate_interval]) / rate(sglang:e2e_request_latency_seconds_count[$__rate_interval]))\r\n",
|
"expr": "avg(rate(sglang_e2e_request_latency_seconds_sum[$__rate_interval]) / rate(sglang_e2e_request_latency_seconds_count[$__rate_interval]))\r\n",
|
||||||
"fullMetaSearch": false,
|
"fullMetaSearch": false,
|
||||||
"hide": false,
|
"hide": false,
|
||||||
"includeNullMetadata": true,
|
"includeNullMetadata": true,
|
||||||
@@ -253,7 +253,7 @@
|
|||||||
},
|
},
|
||||||
"disableTextWrap": false,
|
"disableTextWrap": false,
|
||||||
"editorMode": "builder",
|
"editorMode": "builder",
|
||||||
"expr": "sum(increase(sglang:e2e_request_latency_seconds_bucket{model_name=~\"$model_name\"}[$__rate_interval])) by (le)\r\n",
|
"expr": "sum(increase(sglang_e2e_request_latency_seconds_bucket{model_name=~\"$model_name\"}[$__rate_interval])) by (le)\r\n",
|
||||||
"format": "heatmap",
|
"format": "heatmap",
|
||||||
"fullMetaSearch": false,
|
"fullMetaSearch": false,
|
||||||
"includeNullMetadata": true,
|
"includeNullMetadata": true,
|
||||||
@@ -355,7 +355,7 @@
|
|||||||
},
|
},
|
||||||
"disableTextWrap": false,
|
"disableTextWrap": false,
|
||||||
"editorMode": "code",
|
"editorMode": "code",
|
||||||
"expr": "histogram_quantile(0.99, sum by (le) (rate(sglang:time_to_first_token_seconds_bucket[$__rate_interval])))\r\n",
|
"expr": "histogram_quantile(0.99, sum by (le) (rate(sglang_time_to_first_token_seconds_bucket[$__rate_interval])))\r\n",
|
||||||
"fullMetaSearch": false,
|
"fullMetaSearch": false,
|
||||||
"includeNullMetadata": true,
|
"includeNullMetadata": true,
|
||||||
"instant": false,
|
"instant": false,
|
||||||
@@ -371,7 +371,7 @@
|
|||||||
},
|
},
|
||||||
"disableTextWrap": false,
|
"disableTextWrap": false,
|
||||||
"editorMode": "code",
|
"editorMode": "code",
|
||||||
"expr": "histogram_quantile(0.9, sum by (le) (rate(sglang:time_to_first_token_seconds_bucket[$__rate_interval])))\r\n",
|
"expr": "histogram_quantile(0.9, sum by (le) (rate(sglang_time_to_first_token_seconds_bucket[$__rate_interval])))\r\n",
|
||||||
"fullMetaSearch": false,
|
"fullMetaSearch": false,
|
||||||
"hide": false,
|
"hide": false,
|
||||||
"includeNullMetadata": true,
|
"includeNullMetadata": true,
|
||||||
@@ -388,7 +388,7 @@
|
|||||||
},
|
},
|
||||||
"disableTextWrap": false,
|
"disableTextWrap": false,
|
||||||
"editorMode": "code",
|
"editorMode": "code",
|
||||||
"expr": "histogram_quantile(0.5, sum by (le) (rate(sglang:time_to_first_token_seconds_bucket[$__rate_interval])))\r\n",
|
"expr": "histogram_quantile(0.5, sum by (le) (rate(sglang_time_to_first_token_seconds_bucket[$__rate_interval])))\r\n",
|
||||||
"fullMetaSearch": false,
|
"fullMetaSearch": false,
|
||||||
"hide": false,
|
"hide": false,
|
||||||
"includeNullMetadata": true,
|
"includeNullMetadata": true,
|
||||||
@@ -405,7 +405,7 @@
|
|||||||
},
|
},
|
||||||
"disableTextWrap": false,
|
"disableTextWrap": false,
|
||||||
"editorMode": "code",
|
"editorMode": "code",
|
||||||
"expr": "avg(rate(sglang:time_to_first_token_seconds_sum[$__rate_interval]) / rate(sglang:time_to_first_token_seconds_count[$__rate_interval]))\r\n",
|
"expr": "avg(rate(sglang_time_to_first_token_seconds_sum[$__rate_interval]) / rate(sglang_time_to_first_token_seconds_count[$__rate_interval]))\r\n",
|
||||||
"fullMetaSearch": false,
|
"fullMetaSearch": false,
|
||||||
"hide": false,
|
"hide": false,
|
||||||
"includeNullMetadata": true,
|
"includeNullMetadata": true,
|
||||||
@@ -503,7 +503,7 @@
|
|||||||
"disableTextWrap": false,
|
"disableTextWrap": false,
|
||||||
"editorMode": "builder",
|
"editorMode": "builder",
|
||||||
"exemplar": false,
|
"exemplar": false,
|
||||||
"expr": "sum by(le) (increase(sglang:time_to_first_token_seconds_bucket{model_name=~\"$model_name\"}[$__rate_interval]))",
|
"expr": "sum by(le) (increase(sglang_time_to_first_token_seconds_bucket{model_name=~\"$model_name\"}[$__rate_interval]))",
|
||||||
"format": "heatmap",
|
"format": "heatmap",
|
||||||
"fullMetaSearch": false,
|
"fullMetaSearch": false,
|
||||||
"includeNullMetadata": true,
|
"includeNullMetadata": true,
|
||||||
@@ -606,7 +606,7 @@
|
|||||||
},
|
},
|
||||||
"disableTextWrap": false,
|
"disableTextWrap": false,
|
||||||
"editorMode": "code",
|
"editorMode": "code",
|
||||||
"expr": "sglang:num_running_reqs",
|
"expr": "sglang_num_running_reqs",
|
||||||
"fullMetaSearch": false,
|
"fullMetaSearch": false,
|
||||||
"includeNullMetadata": true,
|
"includeNullMetadata": true,
|
||||||
"instant": false,
|
"instant": false,
|
||||||
@@ -707,7 +707,7 @@
|
|||||||
"uid": "ddyfngn31dg5cf"
|
"uid": "ddyfngn31dg5cf"
|
||||||
},
|
},
|
||||||
"editorMode": "code",
|
"editorMode": "code",
|
||||||
"expr": "sglang:gen_throughput",
|
"expr": "sglang_gen_throughput",
|
||||||
"instant": false,
|
"instant": false,
|
||||||
"legendFormat": "{{instance}}",
|
"legendFormat": "{{instance}}",
|
||||||
"range": true,
|
"range": true,
|
||||||
@@ -805,7 +805,7 @@
|
|||||||
},
|
},
|
||||||
"disableTextWrap": false,
|
"disableTextWrap": false,
|
||||||
"editorMode": "code",
|
"editorMode": "code",
|
||||||
"expr": "sglang:cache_hit_rate",
|
"expr": "sglang_cache_hit_rate",
|
||||||
"fullMetaSearch": false,
|
"fullMetaSearch": false,
|
||||||
"includeNullMetadata": true,
|
"includeNullMetadata": true,
|
||||||
"instant": false,
|
"instant": false,
|
||||||
@@ -906,7 +906,7 @@
|
|||||||
},
|
},
|
||||||
"disableTextWrap": false,
|
"disableTextWrap": false,
|
||||||
"editorMode": "code",
|
"editorMode": "code",
|
||||||
"expr": "sglang:num_queue_reqs",
|
"expr": "sglang_num_queue_reqs",
|
||||||
"fullMetaSearch": false,
|
"fullMetaSearch": false,
|
||||||
"includeNullMetadata": true,
|
"includeNullMetadata": true,
|
||||||
"instant": false,
|
"instant": false,
|
||||||
|
|||||||
Reference in New Issue
Block a user