Skip to content

Fix code for llmc llama4 quantization #1161

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.

Sign up for GitHub

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

Jump to bottom
Merged
chensuyue merged 9 commits into from
Dec 23, 2025
Merged

Fix code for llmc llama4 quantization #1161

chensuyue merged 9 commits into from
Dec 23, 2025

Conversation

@mengniwang95
Copy link
Contributor

@mengniwang95 mengniwang95 commented Dec 18, 2025 •
edited
Loading

  • LLMC uses quantize_block API to quantize block, where iters maybe 0, add process for dump_info in _quantize_block
  • LLMC passes decoding layer into quantize_block, which doesn't have config attribute

@mengniwang95 mengniwang95 mentioned this pull request Dec 18, 2025
Open
@yiliu30
Copy link
Contributor

yiliu30 commented Dec 19, 2025

@XuehaoSun @chensuyue Is it possible to cherry‑pick this into 0.9.3, so we can use it when we upgrade AutoRound on the LLMC side?
cc @thuang6

@yiliu30 yiliu30 requested review from n1ck-guo and yiliu30 December 19, 2025 00:33
yiliu30
yiliu30 approved these changes Dec 19, 2025
View reviewed changes
Copy link
Contributor

@yiliu30 yiliu30 left a comment

Choose a reason for hiding this comment

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

code change LGTM

xin3he
xin3he reviewed Dec 19, 2025
View reviewed changes
wenhuach21
wenhuach21 reviewed Dec 19, 2025
View reviewed changes
@mengniwang95
Copy link
Contributor Author

mengniwang95 commented Dec 19, 2025

@n1ck-guo please take a look for the template part code change

@chensuyue chensuyue added this to the 0.9.3 milestone Dec 22, 2025
@chensuyue chensuyue merged commit 3c88b3b into main Dec 23, 2025
28 checks passed
@chensuyue chensuyue deleted the mengni/llmc_llama4 branch December 23, 2025 06:16
chensuyue pushed a commit that referenced this pull request Dec 23, 2025
@mengniwang95 @chensuyue
Fix code for llmc llama4 quantization (#1161)
13c4c81 
Signed-off-by: Mengni Wang <[email protected]>
(cherry picked from commit 3c88b3b)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@xin3he xin3he xin3he left review comments

@wenhuach21 wenhuach21 wenhuach21 left review comments

@yiliu30 yiliu30 yiliu30 approved these changes

@n1ck-guo n1ck-guo n1ck-guo approved these changes

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

0.9.3

Development

Successfully merging this pull request may close these issues.

7 participants

@mengniwang95 @yiliu30 @xin3he @wenhuach21 @n1ck-guo @chensuyue