transformers/examples/metrics-monitoring/continuous-batching-dashboard.json
Arthur 211f2b0875
Add CB (#38085)
* stash for now

* initial commit

* small updated

* up

* up

* works!

* nits and fixes

* don't loop too much

* finish working example

* update

* fix the small freeblocks issue

* feat: stream inputs to continuous batch

* fix: update attn from `eager` to `sdpa`

* refactor: fmt

* refactor: cleanup unnecessary code

* feat: add `update` fn to `PagedAttentionCache`

* feat: broken optimal block size computation

* fix: debugging invalid cache logic

* fix: attention mask

* refactor: use custom prompts for example

* feat: add streaming output

* fix: prefill split

refactor: add doc strings and unsound/redundant logic
fix: compute optimal blocks logic

* fix: send decoded tokens when `prefilling_split` -> `decoding`

* refactor: move logic to appropriate parent class

* fix: remove truncation as we split prefilling anyways

refactor: early return when we have enough selected requests

* feat: add paged attention forward

* push Ggraoh>

* add paged sdpa

* update

* btter mps defaults

* feat: add progress bar for `generate_batch`

* feat: add opentelemetry metrics (ttft + batch fill %age)

* feat: add tracing

* Add cuda graphs (#38059)

* draft cudagraphs addition

* nits

* styling

* update

* fix

* kinda draft of what it should look like

* fixes

* lol

* not sure why inf everywhere

* can generate but output is shit

* some fixes

* we should have a single device synch

* broken outputs but it does run

* refactor

* updates

* updates with some fixes

* fix mask causality

* another commit that casts after

* add error

* simplify example

* update

* updates

* revert llama changes

* fix merge conflicts

* fix: tracing and metrics

* my updates

* update script default values

* fix block allocation issue

* fix prefill split attnetion mask

* no bugs

* add paged eager

* fix

* update

* style

* feat: add pytorch traces

* fix

* fix

* refactor: remove pytorch profiler data

* style

* nits

* cleanup

* draft test file

* fix

* fix

* fix paged and graphs

* small renamings

* cleanups and push

* refactor: move tracing and metrics logic to utils

* refactor: trace more blocks of code

* nits

* nits

* update

* to profile or not to profile

* refactor: create new output object

* causal by default

* cleanup but generations are still off for IDK what reason

* simplifications but not running still

* this does work.

* small quality of life updates

* nits

* updaet

* fix the scheduler

* fix warning

* ol

* fully fixed

* nits

* different generation parameters

* nice

* just style

* feat: add cache memory usage

* feat: add kv cache free memory

* feat: add active/waiting count & req latency

* do the sampling

* fix: synchronize CUDA only if available and improve error handling in ContinuousBatchingManager

* fix on mps

* feat: add dashboard & histogram buckets

* perf: improve waiting reqs data structures

* attempt to compile, but we should only do it on mps AFAIK

* feat: decouple scheduling logic

* just a draft

* c;eanup and fixup

* optional

* style

* update

* update

* remove the draft documentation

* fix import as well

* update

* fix the test

* style doomed

---------

Co-authored-by: Luc Georges <luc.sydney.georges@gmail.com>
2025-05-22 17:43:48 +02:00

974 lines
33 KiB
JSON

{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": {
"type": "grafana",
"uid": "-- Grafana --"
},
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"target": {
"limit": 100,
"matchAny": false,
"tags": [],
"type": "dashboard"
},
"type": "dashboard"
}
]
},
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 0,
"id": 2,
"links": [],
"panels": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"description": "Memory usage of the PagedAttentionCache",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"max": 10737418240,
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green"
},
{
"color": "yellow",
"value": 5368709120
},
{
"color": "red",
"value": 8589934592
}
]
},
"unit": "bytes"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 6,
"x": 0,
"y": 0
},
"id": 2,
"options": {
"minVizHeight": 75,
"minVizWidth": 75,
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showThresholdLabels": false,
"showThresholdMarkers": true,
"sizing": "auto"
},
"pluginVersion": "12.0.0",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "kv_cache_memory_bytes",
"fullMetaSearch": false,
"includeNullMetadata": true,
"legendFormat": "__auto",
"range": true,
"refId": "A",
"useBackend": false
}
],
"title": "KV Cache Memory Usage",
"transparent": true,
"type": "gauge"
},
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "dark-blue"
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 6,
"x": 6,
"y": 0
},
"id": 13,
"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",
"targets": [
{
"disableTextWrap": false,
"editorMode": "builder",
"expr": "active_requests_count",
"fullMetaSearch": false,
"includeNullMetadata": true,
"legendFormat": "__auto",
"range": true,
"refId": "A",
"useBackend": false
}
],
"title": "Active Requests",
"transparent": true,
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "dark-orange"
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 6,
"x": 12,
"y": 0
},
"id": 14,
"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",
"targets": [
{
"disableTextWrap": false,
"editorMode": "builder",
"expr": "waiting_requests_count",
"fullMetaSearch": false,
"includeNullMetadata": true,
"legendFormat": "__auto",
"range": true,
"refId": "A",
"useBackend": false
}
],
"title": "Waiting Requests",
"transparent": true,
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"description": "Ratio of decode tokens to prefill tokens in a batch",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "blue"
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 6,
"x": 18,
"y": 0
},
"id": 6,
"options": {
"colorMode": "value",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "auto",
"percentChangeColorMode": "standard",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "12.0.0",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "decode_prefill_ratio",
"fullMetaSearch": false,
"includeNullMetadata": true,
"legendFormat": "__auto",
"range": true,
"refId": "A",
"useBackend": false
}
],
"title": "Decode/Prefill Ratio",
"transparent": true,
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"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"
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 8
},
"id": 10,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "12.0.0",
"targets": [
{
"editorMode": "code",
"expr": "rate(decode_tokens_processed_total[$__rate_interval])",
"legendFormat": "__auto",
"range": true,
"refId": "A"
}
],
"title": "Decode tokens throupught tok/s",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green"
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 8
},
"id": 11,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "12.0.0",
"targets": [
{
"editorMode": "code",
"expr": "rate(prefill_tokens_processed_total[$__rate_interval])",
"legendFormat": "__auto",
"range": true,
"refId": "A"
}
],
"title": "Prefill rate tok/s",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"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"
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 16
},
"id": 9,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "12.0.0",
"targets": [
{
"editorMode": "code",
"expr": "histogram_quantile(0.95, sum by(le) (rate(batch_fill_percentage_percent_bucket[$__rate_interval])))",
"legendFormat": "p95",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"editorMode": "code",
"expr": "histogram_quantile(0.99, sum by(le) (rate(batch_fill_percentage_percent_bucket[$__rate_interval])))",
"hide": false,
"instant": false,
"legendFormat": "p99",
"range": true,
"refId": "B"
},
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"editorMode": "code",
"expr": "histogram_quantile(0.5, sum by(le) (rate(batch_fill_percentage_percent_bucket[$__rate_interval])))",
"hide": false,
"instant": false,
"legendFormat": "p50",
"range": true,
"refId": "C"
}
],
"title": "Batch fill percentage percentiles",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"description": "KV Cache Memory Usage Over Time",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 20,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 2,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green"
},
{
"color": "red",
"value": 80
}
]
},
"unit": "bytes"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 16
},
"id": 4,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "12.0.0",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "kv_cache_memory_bytes",
"fullMetaSearch": false,
"includeNullMetadata": true,
"legendFormat": "Used memory",
"range": true,
"refId": "A",
"useBackend": false
},
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "kv_cache_free_memory_bytes",
"fullMetaSearch": false,
"hide": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "free memory",
"range": true,
"refId": "B",
"useBackend": false
}
],
"title": "KV Cache Memory Usage Over Time",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green"
},
{
"color": "red",
"value": 80
}
]
},
"unit": "ms"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 24
},
"id": 8,
"options": {
"displayMode": "gradient",
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": false
},
"maxVizHeight": 300,
"minVizHeight": 10,
"minVizWidth": 0,
"namePlacement": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showUnfilled": true,
"sizing": "auto",
"valueMode": "color"
},
"pluginVersion": "12.0.0",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "histogram_quantile(0.95, sum by(le) (rate(ttft_milliseconds_bucket[$__rate_interval])))",
"fullMetaSearch": false,
"includeNullMetadata": true,
"legendFormat": "p95",
"range": true,
"refId": "A",
"useBackend": false
},
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "histogram_quantile(0.5, sum by(le) (rate(ttft_milliseconds_bucket[$__rate_interval])))",
"fullMetaSearch": false,
"hide": false,
"includeNullMetadata": true,
"legendFormat": "p50",
"range": true,
"refId": "B",
"useBackend": false
},
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "histogram_quantile(0.99, sum by(le) (rate(ttft_milliseconds_bucket[$__rate_interval])))",
"fullMetaSearch": false,
"hide": false,
"includeNullMetadata": false,
"instant": false,
"legendFormat": "p99",
"range": true,
"refId": "C",
"useBackend": false
}
],
"title": "Time to First Token (TTFT)",
"type": "bargauge"
},
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"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"
},
{
"color": "red",
"value": 80
}
]
},
"unit": "ms"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 24
},
"id": 12,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "12.0.0",
"targets": [
{
"editorMode": "code",
"expr": "histogram_quantile(0.5, sum by(le) (rate(request_latency_milliseconds_bucket[$__rate_interval])))",
"legendFormat": "p50",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"editorMode": "code",
"expr": "histogram_quantile(0.95, sum by(le) (rate(request_latency_milliseconds_bucket[$__rate_interval])))",
"hide": false,
"instant": false,
"legendFormat": "p95",
"range": true,
"refId": "B"
},
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"editorMode": "code",
"expr": "histogram_quantile(0.99, sum by(le) (rate(request_latency_milliseconds_bucket[$__rate_interval])))",
"hide": false,
"instant": false,
"legendFormat": "p99",
"range": true,
"refId": "C"
}
],
"title": "Request latency percentiles",
"type": "timeseries"
}
],
"preload": false,
"refresh": "5s",
"schemaVersion": 41,
"tags": [],
"templating": {
"list": []
},
"time": {
"from": "now-15m",
"to": "now"
},
"timepicker": {},
"timezone": "",
"title": "Transformers Continuous Batching Metrics",
"uid": "Lw6CTvVSz",
"version": 5
}