Skip fused_moe replacement when llm-compressor oneshot already linearizes experts#1966
Merged
Conversation
…5 flow Signed-off-by: changwangss <chang1.wang@intel.com>
Signed-off-by: changwangss <chang1.wang@intel.com>
Contributor
|
/azp run Unit-Test-CUDA-AutoRound |
|
Azure Pipelines successfully started running 1 pipeline(s). |
XuehaoSun
approved these changes
Jun 30, 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
4 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
llm-compressor added linearize_moe in oneshot for Transformers v5.x. After this step, MoE experts are already linearized, so AutoRound fused_moe replacement is redundant. This PR adds a skip path for already-linearized experts, keeps fused-only replacement handlers, clarifies logs as "after replacement/skip", and adds UT coverage for linearized detection, expert counting with mixed modules (e.g. act_fn), and skip behavior.
Type of Change
Bug fix
Related Issues
Fixes or relates to vllm-project/llm-compressor#2647
#1962
Checklist Before Submitting
/azp run Unit-Test-CUDA-AutoRound.