Configure PyTorch x vLLM nightly dashboard #7614
+165
−0
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,146 @@ | ||
| import { BenchmarkUIConfig } from "../../config_book_types"; | ||
| import { | ||
| BRANCH_METADATA_COLUMN, | ||
| DEFAULT_DASHBOARD_BENCHMARK_INITIAL, | ||
| } from "../defaults/default_dashboard_config"; | ||
|
|
||
| export const PYTORCH_X_VLLM_BENCHMARK_ID = "pytorch_x_vllm_benchmark"; | ||
|
|
||
| const COMPARISON_TABLE_METADATA_COLUMNS = [ | ||
| { | ||
| field: "device", | ||
| displayName: "Hardware type", | ||
| }, | ||
| { | ||
| field: "arch", | ||
| displayName: "Hardware model", | ||
| }, | ||
| { | ||
| field: "extra_key.use_compile", | ||
| displayName: "Use Compile", | ||
| }, | ||
| { | ||
| field: "extra_key.request_rate", | ||
| displayName: "Request Rate", | ||
| }, | ||
| { | ||
| field: "extra_key.tensor_parallel_size", | ||
| displayName: "Tensor Parallel", | ||
| }, | ||
| { | ||
| field: "extra_key.input_len", | ||
| displayName: "Input Len", | ||
| }, | ||
| { | ||
| field: "extra_key.output_len", | ||
| displayName: "Max Output Len", | ||
| }, | ||
| ] as const; | ||
|
|
||
| export const PytorchXVllmBenchmarkDashboardConfig: BenchmarkUIConfig = { | ||
| benchmarkId: PYTORCH_X_VLLM_BENCHMARK_ID, | ||
| apiId: PYTORCH_X_VLLM_BENCHMARK_ID, | ||
| title: "PyTorch x vLLM Benchmark", | ||
| type: "dashboard", | ||
| dataBinding: { | ||
| initial: { | ||
| ...DEFAULT_DASHBOARD_BENCHMARK_INITIAL, | ||
| benchmarkId: PYTORCH_X_VLLM_BENCHMARK_ID, | ||
| }, | ||
| required_filter_fields: [], | ||
| }, | ||
| dataRender: { | ||
| type: "auto", | ||
| subSectionRenders: { | ||
| detail_view: { | ||
| filterConstraint: { | ||
| model: { | ||
| disabled: true, | ||
| }, | ||
| deviceName: { | ||
| disableOptions: [""], | ||
| }, | ||
| mode: { | ||
| disableOptions: [""], | ||
| }, | ||
| }, | ||
| renders: [ | ||
| { | ||
| type: "AutoBenchmarkTimeSeriesChartGroup", | ||
| title: "Metrics Time Series Chart Detail View", | ||
| config: { | ||
| type: "line", | ||
| groupByFields: ["metric"], | ||
| lineKey: [ | ||
| "model", | ||
| "extra_key.use_compile", | ||
| "extra_key.request_rate", | ||
| "extra_key.input_len", | ||
| "extra_key.output_len", | ||
| "metric", | ||
| "branch", | ||
| ], | ||
| chart: { | ||
| renderOptions: { | ||
| showLegendDetails: true, | ||
| }, | ||
| }, | ||
| }, | ||
| }, | ||
| { | ||
| type: "AutoBenchmarkTimeSeriesTable", | ||
| title: "Comparison Table Detail View", | ||
| config: { | ||
| primary: { | ||
| fields: ["model"], | ||
| displayName: "Model", | ||
| }, | ||
| extraMetadata: COMPARISON_TABLE_METADATA_COLUMNS, | ||
| renderOptions: { | ||
| missingText: "", | ||
| flex: { | ||
| primary: 2, | ||
| }, | ||
| }, | ||
| }, | ||
| }, | ||
| { | ||
| type: "AutoBenchmarkRawDataTable", | ||
| title: "Raw Data Table", | ||
| config: { | ||
| extraMetadata: [ | ||
| BRANCH_METADATA_COLUMN, | ||
| ...COMPARISON_TABLE_METADATA_COLUMNS, | ||
| ], | ||
| }, | ||
| }, | ||
| ], | ||
| }, | ||
| }, | ||
| renders: [ | ||
|
Contributor
There was a problem hiding this comment. @huydhn I will add another auto component to add pure description for dashboard, it's good that we tells the differerence between this benchmark basedon pinned commit, and another one based on pinned pytorch |
||
| { | ||
| type: "AutoBenchmarkPairwiseTable", | ||
| title: "Comparison Table", | ||
| config: { | ||
| primary: { | ||
| fields: ["model"], | ||
| displayName: "Model", | ||
| navigation: { | ||
| type: "subSectionRender", | ||
| value: "detail_view", | ||
| applyFilterFields: ["model", "device", "arch"], | ||
| }, | ||
| }, | ||
| extraMetadata: COMPARISON_TABLE_METADATA_COLUMNS, | ||
| renderOptions: { | ||
| missingText: "none", | ||
| bothMissingText: "", | ||
| flex: { | ||
| primary: 2, | ||
| }, | ||
| }, | ||
| }, | ||
| }, | ||
| ], | ||
| }, | ||
| }; | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@huydhn recommend add comment that it's generated based on pinned vllm commit
Uh oh!
There was an error while loading. Please reload this page.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
also, maybe put this under vllm section: "vLLM Benchmarks ", instead of pytorch,
maybe also update the description for the vllmx pinned pytorch description, so that we can tell the difference