Skip to content

Test Marlin MoE with desc_act=true #2622

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

Merged
merged 1 commit into from
Oct 21, 2024
Merged

Conversation

danieldk
Copy link
Member

@danieldk danieldk commented Oct 8, 2024

What does this PR do?

Update the Mixtral GPTQ test to use a model with desc_act=true and group_size!=-1 to ensure that we are checking activation sorting/non-full K (with tensor parallelism). The desc_act=false case is already checked by the Mixtral AWQ test.

Before submitting

  • This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
  • Did you read the contributor guideline,
    Pull Request section?
  • Was this discussed/approved via a Github issue or the forum? Please add a link
    to it if that's the case.
  • Did you make sure to update the documentation with your changes? Here are the
    documentation guidelines, and
    here are tips on formatting docstrings.
  • Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

Update the Mixtral GPTQ test to use a model with `desc_act=true` and
`group_size!=-1` to ensure that we are checking activation
sorting/non-full K (with tensor parallelism). The `desc_act=false` case
is already checked by the Mixtral AWQ test.
@danieldk danieldk merged commit 7f54b73 into main Oct 21, 2024
9 of 10 checks passed
@danieldk danieldk deleted the tests/marlin-moe-desc-act branch October 21, 2024 10:50
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.

2 participants