Skip to content

[WIP] Support for more gguf format and float zp for Q*_1 #560

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

Open
wants to merge 5 commits into
base: main
Choose a base branch
from

Conversation

n1ck-guo
Copy link
Contributor

No description provided.

@@ -162,6 +162,7 @@ def __init__(
device_map: Union[str, dict] = None,
super_bits: int = None,
super_group_size: int = None,
float_zp: bool = False,
Copy link
Contributor

@wenhuach21 wenhuach21 May 14, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

When the user only exports to GGUF using the q*1 format, switch to float zero points directly (add a new datatype), no need to add additional arguments to the API and wrapperlinear. If gptq/awq are also exported, using int zp and add a warning that this may affect the accuracy of gguf

n1ck-guo added 2 commits May 14, 2025 03:05
Signed-off-by: n1ck-guo <[email protected]>
Signed-off-by: n1ck-guo <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants