Skip to content

Support transformers loading quantized moe model #1067

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
mengniwang95 merged 9 commits into from
Nov 27, 2025
Merged

Support transformers loading quantized moe model #1067

mengniwang95 merged 9 commits into from
Nov 27, 2025

Conversation

@mengniwang95
Copy link
Contributor

@mengniwang95 mengniwang95 commented Nov 25, 2025 •
edited
Loading

  • Update modeling files of llama4 and gptoss
  • Add moe handler in convert_hf_model
  • Add ut for llama4 and gptoss

@mengniwang95
Copy link
Contributor Author

mengniwang95 commented Nov 25, 2025

@XuehaoSun please add llama4 model in CI machine

yiliu30
yiliu30 reviewed Nov 25, 2025
View reviewed changes
yiliu30
yiliu30 reviewed Nov 25, 2025
View reviewed changes
@yiliu30 yiliu30 self-requested a review November 26, 2025 13:46
@mengniwang95 mengniwang95 merged commit b1b60e4 into main Nov 27, 2025
26 checks passed
@mengniwang95 mengniwang95 deleted the mengni/tf_load branch November 27, 2025 05:43
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@yiliu30 yiliu30 yiliu30 approved these changes

@n1ck-guo n1ck-guo Awaiting requested review from n1ck-guo

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@mengniwang95 @yiliu30