-
Notifications
You must be signed in to change notification settings - Fork 197
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Fix (llm): small fixes to LLM #1035
Conversation
Giuseppe5
commented
Sep 27, 2024
•
edited
Loading
edited
- Improve HQO implementation
- Support for MSE with groupwise quantization
- Add possibility to specify groupdim for groupwise weight quantization
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM!
# - 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.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Weird stuff / comments like this make me wonder if we need to re-think our implementation.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
(but let's not block this release)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Agreed