Skip to content
This repository was archived by the owner on Jan 28, 2026. It is now read-only.

[NPU] trial of HQQ q4_0#12534

Draft
rnwang04 wants to merge 6 commits intointel:mainfrom
rnwang04:hqq_q4_0
Draft

[NPU] trial of HQQ q4_0#12534
rnwang04 wants to merge 6 commits intointel:mainfrom
rnwang04:hqq_q4_0

Conversation

@rnwang04
Copy link
Copy Markdown
Contributor

Description

1. Why the change?

2. User API changes

3. Summary of the change

4. How to test?

  • Unit test: Please manually trigger the PR Validation here by inputting the PR number (e.g., 1234). And paste your action link here once it has been successfully finished.

@rnwang04 rnwang04 marked this pull request as draft December 12, 2024 09:24
W_mask = torch.abs(W_) < z_val
W_[W_mask] = z_val
iscale, _ = torch.median(W_q / W_q, axis=1, keepdim=True)
iscale, _ = torch.median(W_q / W_, axis=1, keepdim=True)
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

use mean instead of median?

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants