Fix wrong benchmark data associated with commits #6366
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Outdated suggestions cannot be applied.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.
While debugging the issue on vLLM dashboard in vllm-project/vllm#14303 (comment), I notice a dashboard issue where benchmark data is associated with the wrong commit in the detail chart table.
For example, https://hud.pytorch.org/benchmark/llms?startTime=Wed%2C%2026%20Feb%202025%2021%3A05%3A15%20GMT&stopTime=Wed%2C%2005%20Mar%202025%2021%3A05%3A15%20GMT&granularity=day&lBranch=main&lCommit=257e200a2537a8175392d3bb285473ab80867576&rBranch=main&rCommit=f71b00a19e25abebdff13a5ae9acc93749125e11&repoName=vllm-project%2Fvllm&benchmarkName=&modelName=meta-llama%2FMeta-Llama-3.1-8B-Instruct&backendName=&modeName=&dtypeName=&deviceName=cuda%20(NVIDIA%20H100)&archName=All%20Platforms wrongly show data from other commits with different
workflow_id
. They shouldn't be there on some commits because the benchmark failed to run there.Preview
https://torchci-git-fork-huydhn-fix-wrong-data-commit-fbopensource.vercel.app/benchmark/llms?startTime=Wed%2C%2026%20Feb%202025%2021%3A05%3A15%20GMT&stopTime=Wed%2C%2005%20Mar%202025%2021%3A05%3A15%20GMT&granularity=day&lBranch=main&lCommit=257e200a2537a8175392d3bb285473ab80867576&rBranch=main&rCommit=f71b00a19e25abebdff13a5ae9acc93749125e11&repoName=vllm-project%2Fvllm&benchmarkName=&modelName=meta-llama%2FMeta-Llama-3.1-8B-Instruct&backendName=&modeName=&dtypeName=&deviceName=cuda%20(NVIDIA%20H100)&archName=All%20Platforms that only show data from the correct commit
I also cleanup some leftover TODO, and add a separator to the table.