-
Notifications
You must be signed in to change notification settings - Fork 110
[BE] Update upload bm results GHA #7612
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
Signed-off-by: Huy Do <huydhn@gmail.com>
|
The latest updates on your projects. Learn more about Vercel for GitHub. |
Signed-off-by: Huy Do <huydhn@gmail.com>
Signed-off-by: Huy Do <huydhn@gmail.com>
| echo "DEVICE_NAME=$DEVICE_NAME" >> $GITHUB_ENV | ||
| - name: Get device type |
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.
This logic is from https://github.com/pytorch/pytorch-integration-testing/blob/main/.github/workflows/vllm-benchmark.yml#L139. There is a task to consolidate this into this official upload benchmark results GHA
Signed-off-by: Huy Do <huydhn@gmail.com>
This reverts commit faabc80.
Signed-off-by: Huy Do <huydhn@gmail.com>
Signed-off-by: Huy Do <huydhn@gmail.com>
Reverts #7612 Causing multiple failures on CI : https://github.com/pytorch/pytorch/actions/runs/20446693320/job/58754263235 Error: ``` Traceback (most recent call last): File "/home/ec2-user/actions-runner/_work/_actions/pytorch/test-infra/main/.github/actions/upload-benchmark-results/../../scripts/upload_benchmark_results.py", line 380, in <module> main() File "/home/ec2-user/actions-runner/_work/_actions/pytorch/test-infra/main/.github/actions/upload-benchmark-results/../../scripts/upload_benchmark_results.py", line 375, in main warn(f"Find no benchmark results in {args.benchmark_results}") AttributeError: 'Namespace' object has no attribute 'benchmark_results' ```
There are a couple of changes:
DEVICE_NAMEandDEVICE_TYPEfrom https://github.com/pytorch/pytorch-integration-testing/blob/main/.github/workflows/vllm-benchmark.yml and get rid of PyTorch as a dependency from this workflow to find the device name and type. Installing PyTorch just to get this information is a wastenvidia-ml-pyas a replacement ofpynvml