Skip to content

Conversation

rnwang04
Copy link
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
@@ -119,10 +119,12 @@ def update_scale_hqq(x: Tensor, iscale: Tensor, min_max: list):
W_ = (x - W_e).clone()
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
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 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