Include SAM Fast in torch.compile nightly benchmark workflow #2856
Conversation
| @@ -4,6 +4,7 @@ | |||
| pip uninstall torchtext torchdata torch torchvision torchaudio -y | |||
|
|
|||
| # Install nightly PyTorch and torchvision from the specified index URL | |||
| pip install chardet | |||
There was a problem hiding this comment.
Included this dependency because one of the previous benchmark runs failed because of the absence of this module: https://github.com/pytorch/serve/actions/runs/7255062486/job/19764967013
There was a problem hiding this comment.
Was this happening locally? I didnt notice this. If not, can you please move this to the dependencies section of the benchmark run?
There was a problem hiding this comment.
I think I noticed it locally as well. I will include it in the benchmark_model_dependencies.sh script which you suggested.
| @@ -39,5 +39,8 @@ jobs: | |||
| sudo apt-get update -y | |||
| sudo apt-get install -y apache2-utils | |||
| pip install -r benchmarks/requirements-ab.txt | |||
| chmod +x examples/large_models/segment_anything_fast/install_segment_anything_fast.sh | |||
There was a problem hiding this comment.
Please make this a separate step
There was a problem hiding this comment.
Will update the PR.
There was a problem hiding this comment.
I'm thinking this should be a script under benchmarks. You can call it benchmark_model_dependencies.sh . So, if there are more things in the future, we can add it there
There was a problem hiding this comment.
Sounds good. I will create this script.
| uses: actions/setup-python@v4 | ||
| with: | ||
| python-version: 3.8 | ||
| python-version: 3.10.9 |
There was a problem hiding this comment.
One of the previous runs had failed when I specified just 3.10: https://github.com/pytorch/serve/actions/runs/7255048620/job/19764929373
Commit ID: bcda479
We can choose the versions according to https://raw.githubusercontent.com/actions/python-versions/main/versions-manifest.json.
There was a problem hiding this comment.
You need to use quotes, check this workflow https://github.com/pytorch/serve/blob/master/.github/workflows/regression_tests_cpu_binaries.yml#L20
There was a problem hiding this comment.
Oh I understand. I will update the workflow accordingly.
Updated PR according to suggestions. |
Description
Please read our CONTRIBUTING.md prior to creating your first pull request.
The objective of this PR is to include the SAM Fast model with weights corresponding to vit_b and a process batch size of 4.
Testing:
Ran benchmark workflow in the commit .
Testing after 1st revision:
Ran benchmark workflow in the commit e89c1ba.