Skip to content

Fix the missing temporary name #1029

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 2 commits into from
Nov 14, 2025
Merged

Fix the missing temporary name #1029

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f87372a
fix
yiliu30 Nov 13, 2025
f6950fe
add note
yiliu30 Nov 13, 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
6 changes: 4 additions & 2 deletions auto_round/compressors/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1551,13 +1551,15 @@ def quantize(self) -> tuple[torch.nn.Module, dict[str, Any]]:
Returns:
The quantized model and layer configurations.
"""
for n, m in self.model.named_modules(): # TODO check if could removed
m.tmp_name = n

self._check_compatibility()
formats = self.formats if hasattr(self, "formats") else None
# It is best to modify the model structure in the quantize function and check the format,
# because it may cause the gguf format to not be exported normally.
self.model = _handle_moe_model(self.model, formats=formats)
# Assign temporary names after replacing modules
for n, m in self.model.named_modules(): # TODO check if could removed
m.tmp_name = n

# TODO check scale_dtype
if not self.is_auto_scheme:
Expand Down