Skip to content
Open
Changes from all commits
Commits
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: 6 additions & 0 deletions src/compressed_tensors/quantization/quant_config.py
Original file line number Diff line number Diff line change
Expand Up @@ -297,6 +297,12 @@ def requires_calibration_data(self):
if scheme.output_activations is not None:
if not scheme.output_activations.dynamic:
return True
if (
scheme.weights is not None
and scheme.weights.observer is not None
and scheme.weights.observer.lower() == "imatrix_mse"

@HDCharles HDCharles Jul 21, 2026

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

lets make a list of observers that require calibration in llm-compressor and use it here instead of hardcoding a bunch of observer names

):
return True

return False

Expand Down
Loading