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

Install compressed-tensors after llm-compressor #825

Merged
merged 4 commits into from
Oct 8, 2024

Conversation

dbarbuzzi
Copy link
Collaborator

SUMMARY:
These changes move the separate compressed-tensors installation to after llm-compressor is installed, as well as uninstall any existing version first.

There is also some very minor cleanup:

  • Refactor some pytest commands so the flag ordering is consistent between them
  • Replace the use of always() to allow jobs to be cancelable without affecting existing logic/intentions

TEST PLAN:
Branch/PR checks should have the same outcome as main (unless some of the existing failure are related to transformers specifically requiring a non-nightly install of compressed-tensors).

The 'always()' function is dangerous. When used, it makes it impossible
to cancel a job because it returns true even if the job is canceled.
Using "success() || failure()" instead is
functionally equivalent in this use-case.
@dsikka dsikka merged commit 8b313d5 into vllm-project:main Oct 8, 2024
5 of 6 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants