Skip to content

Fix g_idx init in transformers-like API #2204

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

Merged
merged 2 commits into from
May 12, 2025
Merged

Conversation

Kaihui-intel
Copy link
Contributor

Type of Change

bug fix

Description

error:

The size of tensor a (4096) must match the size of tensor b (128) at non-singleton dimension 0

When loading a GPTQ INT8 model, g_idx should be either None or a correct value, rather than a tensor of zeros.
image

Expected Behavior & Potential Risk

the expected behavior that triggered by this PR

How has this PR been tested?

how to reproduce the test (including hardware information)

Dependency Change?

any library dependency introduced or removed

Signed-off-by: Kaihui-intel <[email protected]>
Signed-off-by: Kaihui-intel <[email protected]>
@Kaihui-intel Kaihui-intel merged commit ab5c2fe into master May 12, 2025
24 checks passed
@Kaihui-intel Kaihui-intel deleted the kaihui/gptq_pvc branch May 12, 2025 08:10
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.

4 participants