Fix MiniMax-M3 MXFP8 crash on 8xH200 (vllm-project/vllm#50856) - #750
Open
YASHSAWANTTT wants to merge 2 commits into
Open
Fix MiniMax-M3 MXFP8 crash on 8xH200 (vllm-project/vllm#50856)#750YASHSAWANTTT wants to merge 2 commits into
YASHSAWANTTT wants to merge 2 commits into
Conversation
Signed-off-by: Yash Sawant <yasawant@asu.edu>
Contributor
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
![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 MiniMax-M3.yaml configuration to restrict the --attention_config.indexer_kv_dtype fp8 argument to Blackwell hardware overrides, as the Triton indexer on Hopper and AMD only supports bf16. It also updates the troubleshooting guide to document this restriction and updates the date_updated metadata. There are no review comments, so I have no feedback to provide.
1 task
Signed-off-by: Yash Sawant <137981875+YASHSAWANTTT@users.noreply.github.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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Gate --attention_config.indexer_kv_dtype fp8 to Blackwell for the MXFP8 variant so Hopper (8xH200) no longer crashes on load — the Triton indexer only supports bf16.
Add a Troubleshooting note that FP8 index cache is Blackwell/MSA-only.
Fixes Issue: 50856
Test plan