Skip to content

fix rtn bug #966

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 1 commit into from
Oct 30, 2025
Merged

fix rtn bug #966

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
9 changes: 5 additions & 4 deletions auto_round/compressors/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1310,10 +1310,11 @@ def _quantize_rtn(self) -> tuple[torch.nn.Module, dict[str, Any]]:
self.model.to("cpu")

enable_imatrix = False
if has_gguf_k and not self.disable_opt_rtn:
enable_imatrix = True
if self.data_type == "int" and self.sym:
enable_imatrix = True
if not self.disable_opt_rtn:
if has_gguf_k:
enable_imatrix = True
elif self.data_type == "int" and self.sym:
enable_imatrix = True

if enable_imatrix:
self._quant_rtn_with_imatrix(all_to_quantized_module_names)
Expand Down