support deepspeed LinearLayer and LinearAllreduce #698
Conversation
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
Signed-off-by: Xin He <[email protected]>
xin3he
requested review from
wenhuach21,
n1ck-guo and
Copilot
and removed request for
wenhuach21 and
n1ck-guo
There was a problem hiding this comment.
Pull Request Overview
This PR adds support for DeepSpeed's tensor-parallel linear layers (LinearLayer and LinearAllreduce) to the auto_round quantization library. The changes enable quantization of models that use DeepSpeed's tensor-parallelized layers.
Key changes:
- Added DeepSpeed dependency detection and conditional imports
- Extended
SUPPORTED_LAYER_TYPESto include DeepSpeed linear layers - Implemented specialized forward pass handling for
LinearAllreducelayers with all-reduce communication
Reviewed Changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 3 comments.
| File | Description |
|---|---|
| auto_round/utils.py | Adds DeepSpeed detection, imports, and extends supported layer types |
| auto_round/wrapper.py | Implements DeepSpeed layer support with specialized forward methods and wrapper enhancements |
Co-authored-by: Copilot <[email protected]>
Co-authored-by: Copilot <[email protected]>
for more information, see https://pre-commit.ci
Signed-off-by: Xin He <[email protected]>
for more information, see https://pre-commit.ci
wenhuach21
approved these changes
Aug 1, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
support tensor-paralleled model from deepspeed