8000 refine inference step 2 by wenhuach21 · Pull Request #498 · intel/auto-round · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

refine inference step 2 #498

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 14 commits into from
Apr 9, 2025
Merged

refine inference step 2 #498

merged 14 commits into from
Apr 9, 2025

Conversation

wenhuach21
Copy link
Contributor
@wenhuach21 wenhuach21 commented Apr 9, 2025

Done: remind better backend,3bits support, test auto backend, gptq_awq format support
TODO:refine config.json/divide_group_size_checker/

@wenhuach21 wenhuach21 changed the title [WIP]refine inference step 2 refine inference step 2 Apr 9, 2025
@wenhuach21 wenhuach21 requested a review from Copilot April 9, 2025 08:42
Copy link
@Copilot Copilot AI left a comment

Choose a reason for hiding this comment

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

Copilot reviewed 8 out of 8 changed files in this pull request and generated 1 comment.

Comments suppressed due to low confidence (1)

auto_round/export/export_to_autoround/export.py:78

  • Since 3-bit support has been added elsewhere, consider updating this condition to include 3-bit cases if they are supported, to ensure consistency across the codebase.
elif "auto_round" in backend and "gptq" in backend and bits in (2, 4, 8):

wenhuach21 and others added 3 commits April 9, 2025 16:49
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
@wenhuach21 wenhuach21 requested review from n1ck-guo and WeiweiZhang1 and removed request for n1ck-guo April 9, 2025 08:53
8000
@wenhuach21 wenhuach21 merged commit 37341f5 into main Apr 9, 2025
8 checks passed
@wenhuach21 wenhuach21 deleted the refine_inference branch April 9, 2025 15:36
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.

3 participants
0