Skip to content

fix: correct scale parameter remapping logic in Llama4ForConditionalGeneration #11282

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

Merged
merged 3 commits into from
Oct 7, 2025
Merged

fix: correct scale parameter remapping logic in Llama4ForConditionalGeneration #11282

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
cb848a4
fix: correct scale parameter remapping logic in Llama4ForConditionalG…
JustinTong0323 Oct 6, 2025
a86cc26
Update python/sglang/srt/models/mllama4.py
JustinTong0323 Oct 6, 2025
89f1050
Merge branch 'main' into fix-llama4-quant-weight-load
JustinTong0323 Oct 6, 2025
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
2 changes: 1 addition & 1 deletion python/sglang/srt/models/mllama4.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -700,7 +700,7 @@ def _handle_scale_remapping(self, name: str, params_dict: dict) -> bool:
"""Handle scale parameter remapping. Returns True if handled."""
if "scale" in name and "expert" not in name:
remapped_name = maybe_remap_kv_scale_name(name, params_dict)
return remapped_name is not None and remapped_name != name
return remapped_name != name
return False

def _handle_stacked_params(
Expand Down
Loading