Unify the return type of w8a8 matmul between fallback and the actual impl.#9452
Merged
vanbasten23 merged 5 commits intomasterfrom Jul 10, 2025
Merged
Unify the return type of w8a8 matmul between fallback and the actual impl.#9452vanbasten23 merged 5 commits intomasterfrom
vanbasten23 merged 5 commits intomasterfrom
Conversation
yaochengji
approved these changes
Jul 8, 2025
Collaborator
yaochengji
left a comment
There was a problem hiding this comment.
LGTM, thanks for fixing this!
e527723 to
9c2c0b2
Compare
8f36349 to
aac2352
Compare
Collaborator
Author
|
Thanks for the review! |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
We need to unify the return type between fallback and the actual impl. Specifically, in the fallback impl
quantized_matmul_int8_non_xla, if we don't specify a dtype, it'll use the default dtype torch.float32. This can cause issue in vLLM.Test plan: