Skip to content

Fix mcore nvfp4 export for vllm #816

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

Open
meenchen wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix mcore nvfp4 export for vllm #816

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions modelopt/torch/export/unified_export_megatron.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -331,6 +331,9 @@ def save_pretrained(
"exclude_modules": ["lm_head"],
},
}
if "NVFP4" in quantization:
Copy link
Collaborator

@cjluo-nv cjluo-nv Jan 26, 2026

Choose a reason for hiding this comment

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

how about we always save group_size if group_size is valid?

# for vllm, the group size is required
hf_quant_config["quantization"]["group_size"] = 16
with open(save_directory + "/hf_quant_config.json", "w") as f:
json.dump(hf_quant_config, f, indent=4)

Expand Down
Loading