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.

Sign up for GitHub

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

Jump to bottom

[Misc] Update w2 scale loading for GPTQMarlinMoE #12757

Merged
merged 3 commits into from
Feb 6, 2025
Merged

[Misc] Update w2 scale loading for GPTQMarlinMoE #12757

merged 3 commits into from
Feb 6, 2025

Conversation

dsikka
Copy link
Contributor

@dsikka dsikka commented Feb 5, 2025 •
edited by github-actions bot
Loading

Summary

  • Adds is_k_full condition
  • Conditionally partitions w2 weight scales based on act order
  • Add additional test cases

@dsikka
clean-up
94fe48b 
Signed-off-by: Dipika <[email protected]>
@github-actions GitHub Actions
Copy link

github-actions bot commented Feb 5, 2025

👋 Hi! Thank you for contributing to the vLLM project.
Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can do one of these:

  • Add ready label to the PR
  • Enable auto-merge.

🚀

@dsikka
Copy link
Contributor Author

dsikka commented Feb 5, 2025

@ElizaWszola Please take a look
I need to find additional models to test this with

ElizaWszola and others added 2 commits February 5, 2025 08:06
@dsikka dsikka marked this pull request as ready for review February 6, 2025 02:23
@dsikka
Copy link
Contributor Author

dsikka commented Feb 6, 2025

@mgoin
Can we enable weight-loading large tests so that MoE models can run

@robertgshaw2-redhat robertgshaw2-redhat added the ready ONLY add when PR is ready to merge/full CI is needed label Feb 6, 2025
@robertgshaw2-redhat robertgshaw2-redhat enabled auto-merge (squash) February 6, 2025 02:25
@robertgshaw2-redhat
Copy link
Collaborator

Thanks!

mgoin
mgoin approved these changes Feb 6, 2025
View reviewed changes
Copy link
Member

@mgoin mgoin left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Nice find

@mgoin mgoin changed the title [Misc] Update w2 scale loading for GTPQMarlinMoE [Misc] Update w2 scale loading for GPTQMarlinMoE Feb 6, 2025
@simon-mo simon-mo merged commit 7ca9934 into vllm-project:main Feb 6, 2025
56 of 65 checks passed
fxmarty-amd pushed a commit to fxmarty-amd/vllm that referenced this pull request Feb 7, 2025
@dsikka @fxmarty-amd
[Misc] Update w2 scale loading for GPTQMarlinMoE (vllm-project#12757)
4a5e237 
Signed-off-by: Felix Marty <[email protected]>
AoyuQC pushed a commit to AoyuQC/vllm that referenced this pull request Feb 8, 2025
@dsikka
[Misc] Update w2 scale loading for GPTQMarlinMoE (vllm-project#12757)
7539e3a
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@mgoin mgoin mgoin approved these changes

@robertgshaw2-redhat robertgshaw2-redhat robertgshaw2-redhat approved these changes

@youkaichao youkaichao Awaiting requested review from youkaichao youkaichao is a code owner

@tlrmchlsmth tlrmchlsmth Awaiting requested review from tlrmchlsmth tlrmchlsmth is a code owner

Assignees
No one assigned
Labels
ready ONLY add when PR is ready to merge/full CI is needed
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
5 participants
@dsikka @robertgshaw2-redhat @mgoin @simon-mo @ElizaWszola