[Cherry-pick to release/v0.5.12] [Bug] Fix V4-Pro NaN on Blackwell by converting fp8_einsum input scale to ue8m0 (#25733)#26063
Merged
Kangyan-Zhou merged 1 commit intoMay 22, 2026
Conversation
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request updates the DeepSeek V4 model implementation by adding a call to deep_gemm.ceil_to_ue8m0 to adjust the scale factor o_s before performing an FP8 einsum operation. I have no feedback to provide as there were no review comments to evaluate.
3 tasks
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Cherry-pick of commit
79ea30d1f134b741ddc55f75db45c0299fa2a642torelease/v0.5.12.Source PR: #25733 (#25733)
Source commit:
79ea30d1f134b741ddc55f75db45c0299fa2a642Original title: [Bug] Fix V4-Pro NaN on Blackwell by converting fp8_einsum input scale to ue8m0
This PR was automatically created by the cherry-pick workflow.
CI States
Latest PR Test (Base): ❌ Missing
run-cilabel -- add it to run CI tests.Latest PR Test (Extra): ❌ Blocked --
run-ciis required first.