Fix duplicated weights in fp8 quantization#37667
Merged
Merged
Conversation
Contributor
|
Hi 👋, thank you for opening this pull request! The pull request is converted to draft by default. The CI will be paused while the PR is in draft mode. When it is ready for review, please click the |
Cyrilvallez
changed the title
SunMarc
approved these changes
Apr 22, 2025
Member
SunMarc
left a comment
SunMarc
left a comment
There was a problem hiding this comment.
Nice catch ! Thanks for fixing !
zucchini-nlp
pushed a commit
to zucchini-nlp/transformers
that referenced
this pull request
May 14, 2025
* fix fp8 * Update quantizer_finegrained_fp8.py * fix circular import * Update quantizer_finegrained_fp8.py
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do?
#35926 moved the fp8 params from buffers to parameters (which makes sense), but the quantizer itself was not updated, so the parameters would still be added as buffers leading to duplicated weights (they would live as both buffers and parameters).
Also, note that we SHOULD NEVER use
set_module_tensor_to_deviceas it clears the cuda cache at each call which is really inefficient, and defeats all the purpose of cuda warmup we do infrom_pretrainedcc @SunMarc @MekkCyber