fix(inference): correct known-issue precisions#441
Merged
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
functionstackx
added a commit
that referenced
this pull request
Jun 11, 2026
…P4) (#442) #441 applied the precision swap to the wrong entries. The GB300 Dynamo TRT MTP accuracy issue (NVIDIA/srt-slurm#51) affects FP8, and the MI355X MoRI SGLang MTP issue (sgl-project/sglang#27194) affects FP4. Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Note
Low Risk
Small data-only change to warning metadata; wrong precisions would mislabel charts but does not affect inference execution or auth.
Overview
Corrects which DeepSeek R1 benchmark precisions trigger known-issue warnings on inference charts and in CSV exports.
GB300 Dynamo TRT MTP (
NVIDIA/srt-slurm#51) is now limited to fp4 instead of fp8. MI355X MoRI SGLang MTP (sgl-project/sglang#27194) is now limited to fp8 instead of matching every precision.known-issues.test.tsis updated so each entry has positive and negative precision cases aligned with those rules.Reviewed by Cursor Bugbot for commit d786dbd. Bugbot is set up for automated code reviews on this repo. Configure here.