Fix (llm): small fixes to LLM #1035
Merged
Conversation
This file contains 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
Collaborator
Giuseppe5
commented
Sep 27, 2024
•
Giuseppe5
commented
- Improve HQO implementation
- Support for MSE with groupwise quantization
- Add possibility to specify groupdim for groupwise weight quantization
nickfraser
approved these changes
Oct 7, 2024
| # - If we quantize the zero point, which will already have expanded shape matching the scale (although no padding, but we don't need the padding) | ||
| # - Groupwise HQO quantization, where weight will already have been padded and expanded | ||
| if len(x.shape) == len(self.expanded_groupwise_shape): | ||
| return x |
There was a problem hiding this comment.
Weird stuff / comments like this make me wonder if we need to re-think our implementation.
There was a problem hiding this comment.
(but let's not block this release)
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Outdated suggestions cannot be applied.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.