Skip to content
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

Update IR for Torch-TensorRT userbenchmark #1946

Closed
wants to merge 1 commit into from

Conversation

gs-olive
Copy link
Contributor

  • Update IR from default to torch_compile, to ensure testing is against the desired torch_compile backend

@gs-olive gs-olive temporarily deployed to docker-s3-upload September 28, 2023 17:26 — with GitHub Actions Inactive
@gs-olive gs-olive temporarily deployed to docker-s3-upload September 28, 2023 17:26 — with GitHub Actions Inactive
@facebook-github-bot
Copy link
Contributor

@xuzhao9 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

@facebook-github-bot
Copy link
Contributor

@xuzhao9 merged this pull request in 3e4aae8.

@xuzhao9
Copy link
Contributor

xuzhao9 commented Sep 28, 2023

Testing workflow: https://github.com/pytorch/benchmark/actions/runs/6342994996

@gs-olive
Copy link
Contributor Author

Thanks for testing that out - I noticed it is still saying ir is default, in this stderr message: INFO:torch_tensorrt._compile:ir was set to default, using dynamo as ir. I have addressed this issue in #1947 and tested it out locally to ensure the correct IR is selected. I appreciate your help with this.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants