[feat](minimax): refactor rmsnorm for minimax#613
Open
PerryZhang01 wants to merge 3 commits intomainfrom
Open
Conversation
PerryZhang01
force-pushed
the
minimax_norm
branch
5 times, most recently
from
6eeab48 to
943adb6
Compare
PerryZhang01
force-pushed
the
minimax_norm
branch
3 times, most recently
from
698fc4b to
9b94450
Compare
PerryZhang01
force-pushed
the
minimax_norm
branch
from
9b94450 to
4000925
Compare
valarLip
requested changes
Apr 21, 2026
| self.rotary_emb = rotary_emb | ||
| self.q_norm = q_norm | ||
| self.k_norm = k_norm | ||
| self.norm_accross_all_heads = False |
Contributor
Author
There was a problem hiding this comment.
variable name or other something else?
This was referenced Apr 28, 2026
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Motivation
This PR refactors rmsnorm in minimax_v2.py. In minimax norm operation uses whole q dim and k dim rather than one head dim, so it should introduce allreduce in tp mode. this pr algins vllm code. (https://github.com/vllm-project/vllm/blob/main/vllm/model_executor/models/minimax_m2.py#L222)
TEST