Skip to content

Instantly share code, notes, and snippets.

@initcron
Last active October 10, 2025 03:25
Show Gist options
  • Save initcron/02f3842ce6911dd7e3224800bfbecf1e to your computer and use it in GitHub Desktop.
Save initcron/02f3842ce6911dd7e3224800bfbecf1e to your computer and use it in GitHub Desktop.
{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": {
"type": "grafana",
"uid": "-- Grafana --"
},
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
}
]
},
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 0,
"id": 31,
"links": [],
"panels": [
{
"fieldConfig": {
"defaults": {
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 6,
"x": 0,
"y": 0
},
"id": 1,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"percentChangeColorMode": "standard",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "12.1.1",
"targets": [
{
"expr": "sum(rate(chat_requests_total[1m]))",
"refId": "A"
}
],
"title": "Chat RPS",
"type": "stat"
},
{
"fieldConfig": {
"defaults": {
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 6,
"x": 6,
"y": 0
},
"id": 4,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"percentChangeColorMode": "standard",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "12.1.1",
"targets": [
{
"expr": "sum(rate(retriever_requests_total[1m]))",
"refId": "A"
}
],
"title": "Retriever RPS",
"type": "stat"
},
{
"fieldConfig": {
"defaults": {
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 6,
"x": 12,
"y": 0
},
"id": 12,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"percentChangeColorMode": "standard",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "12.1.1",
"targets": [
{
"expr": "sum(vllm:num_requests_waiting)",
"legendFormat": "waiting",
"refId": "A"
},
{
"expr": "sum(vllm:num_requests_running)",
"legendFormat": "running",
"refId": "B"
}
],
"title": "vLLM Queue / Running",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 6,
"w": 6,
"x": 18,
"y": 0
},
"id": 10,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "12.1.1",
"targets": [
{
"expr": "sum(rate(vllm:prompt_tokens_total[5m]))",
"legendFormat": "prompt t/s",
"refId": "A"
},
{
"expr": "sum(rate(vllm:generation_tokens_total[5m]))",
"legendFormat": "generation t/s",
"refId": "B"
}
],
"title": "vLLM Tokens/sec",
"type": "timeseries"
},
{
"fieldConfig": {
"defaults": {
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 6,
"x": 0,
"y": 4
},
"id": 7,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"percentChangeColorMode": "standard",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "12.1.1",
"targets": [
{
"expr": "chat_prompt_tokens",
"refId": "A"
}
],
"title": "Prompt Tokens (last)",
"type": "stat"
},
{
"fieldConfig": {
"defaults": {
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 6,
"x": 6,
"y": 4
},
"id": 8,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"percentChangeColorMode": "standard",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "12.1.1",
"targets": [
{
"expr": "chat_completion_tokens",
"refId": "A"
}
],
"title": "Completion Tokens (last)",
"type": "stat"
},
{
"fieldConfig": {
"defaults": {
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 6,
"x": 12,
"y": 4
},
"id": 9,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"percentChangeColorMode": "standard",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "12.1.1",
"targets": [
{
"expr": "chat_total_tokens",
"refId": "A"
}
],
"title": "Total Tokens (last)",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 7,
"w": 12,
"x": 0,
"y": 8
},
"id": 11,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "12.1.1",
"targets": [
{
"expr": "histogram_quantile(0.95, sum by (le) (rate(vllm:time_to_first_token_seconds_bucket[5m])))",
"legendFormat": "TTFT p95",
"refId": "A"
},
{
"expr": "histogram_quantile(0.95, sum by (le) (rate(vllm:e2e_request_latency_seconds_bucket[5m])))",
"legendFormat": "E2E p95",
"refId": "B"
},
{
"expr": "histogram_quantile(0.95, sum by (le) (rate(vllm:request_inference_time_seconds_bucket[5m])))",
"legendFormat": "inference p95",
"refId": "C"
},
{
"expr": "histogram_quantile(0.95, sum by (le) (rate(vllm:time_per_output_token_seconds_bucket[5m])))",
"legendFormat": "TPOT p95",
"refId": "D"
}
],
"title": "vLLM Latencies (p95)",
"type": "timeseries"
},
{
"fieldConfig": {
"defaults": {
"custom": {
"align": "auto",
"cellOptions": {
"type": "auto"
},
"inspect": false
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 7,
"w": 6,
"x": 12,
"y": 8
},
"id": 13,
"options": {
"cellHeight": "sm",
"footer": {
"countRows": false,
"fields": "",
"reducer": [
"sum"
],
"show": false
},
"showHeader": true
},
"pluginVersion": "12.1.1",
"targets": [
{
"expr": "retriever_index_items",
"legendFormat": "index_items",
"refId": "A"
},
{
"expr": "retriever_meta_items",
"legendFormat": "meta_items",
"refId": "B"
}
],
"title": "Retriever Index & Meta Sizes",
"type": "table"
},
{
"datasource": {
"type": "prometheus"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 7,
"w": 12,
"x": 0,
"y": 15
},
"id": 14,
"interval": "1m",
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "12.1.1",
"targets": [
{
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{cluster=\"\", namespace=\"atharva-ml\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"\", namespace=\"atharva-ml\", workload_type=~\"deployment\"}\n) by (workload, workload_type)",
"legendFormat": "{{workload}}",
"refId": "A"
}
],
"title": "Deployments CPU (atharva-ml)",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 7,
"w": 12,
"x": 12,
"y": 15
},
"id": 15,
"interval": "1m",
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "12.1.1",
"targets": [
{
"expr": "sum(\n container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"\", namespace=\"atharva-ml\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"\", namespace=\"atharva-ml\", workload_type=~\"deployment\"}\n) by (workload, workload_type)",
"legendFormat": "{{workload}}",
"refId": "A"
}
],
"title": "Deployments Memory (atharva-ml)",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 7,
"w": 12,
"x": 0,
"y": 22
},
"id": 2,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "12.1.1",
"targets": [
{
"expr": "histogram_quantile(0.50, sum by (le) (rate(chat_end_to_end_latency_seconds_bucket[5m])))",
"legendFormat": "p50",
"refId": "A"
},
{
"expr": "histogram_quantile(0.95, sum by (le) (rate(chat_end_to_end_latency_seconds_bucket[5m])))",
"legendFormat": "p95",
"refId": "B"
}
],
"title": "Chat E2E Latency (p50/p95)",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 7,
"w": 12,
"x": 12,
"y": 22
},
"id": 3,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "12.1.1",
"targets": [
{
"expr": "histogram_quantile(0.95, sum by (le) (rate(rag_retrieval_latency_seconds_bucket[5m])))",
"legendFormat": "retriever (inside chat)",
"refId": "A"
},
{
"expr": "histogram_quantile(0.95, sum by (le) (rate(vllm:e2e_request_latency_seconds_bucket[5m])))",
"legendFormat": "vLLM (inside chat)",
"refId": "B"
}
],
"title": "Chat Sub-steps p95 (Retriever & vLLM)",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 7,
"w": 12,
"x": 0,
"y": 29
},
"id": 5,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "12.1.1",
"targets": [
{
"expr": "histogram_quantile(0.50, sum by (le) (rate(retriever_search_latency_seconds_bucket[5m])))",
"legendFormat": "p50",
"refId": "A"
},
{
"expr": "histogram_quantile(0.95, sum by (le) (rate(retriever_search_latency_seconds_bucket[5m])))",
"legendFormat": "p95",
"refId": "B"
}
],
"title": "Retriever Search Latency (p50/p95)",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 7,
"w": 12,
"x": 12,
"y": 29
},
"id": 6,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "12.1.1",
"targets": [
{
"expr": "histogram_quantile(0.95, sum by (le) (rate(retriever_dense_encode_latency_seconds_bucket[5m])))",
"legendFormat": "dense encode",
"refId": "A"
},
{
"expr": "histogram_quantile(0.95, sum by (le) (rate(retriever_dense_faiss_latency_seconds_bucket[5m])))",
"legendFormat": "dense faiss",
"refId": "B"
},
{
"expr": "histogram_quantile(0.95, sum by (le) (rate(retriever_sparse_vectorize_latency_seconds_bucket[5m])))",
"legendFormat": "sparse vectorize",
"refId": "C"
},
{
"expr": "histogram_quantile(0.95, sum by (le) (rate(retriever_sparse_dot_latency_seconds_bucket[5m])))",
"legendFormat": "sparse dot",
"refId": "D"
}
],
"title": "Retriever Sub-steps p95 (Dense/Sparse)",
"type": "timeseries"
}
],
"preload": false,
"schemaVersion": 41,
"tags": [],
"templating": {
"list": []
},
"time": {
"from": "now-15m",
"to": "now"
},
"timepicker": {},
"timezone": "browser",
"title": "Atharva LLMOps- Overview",
"uid": "09dbc849-df80-4b82-9a49-7cd6bb2b7cad",
"version": 1
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment