Skip to content
This repository was archived by the owner on Jun 3, 2025. It is now read-only.

ConvInteger quantization conversion for quant refactor #644

Merged
merged 3 commits into from
Apr 8, 2022
Merged

ConvInteger quantization conversion for quant refactor #644

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
47ea29e
ConvInteger quantization conversion for quant refactor
Mar 25, 2022
4b3f664
[quantization-refactor] mark/propagate conv export mode (#672)
bfineran Apr 7, 2022
5822da4
batch norm fold with existing bias param bug fix
Apr 8, 2022
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/sparseml/pytorch/sparsification/quantization/modifier_quantization.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -673,6 +673,12 @@ def _enable_module_qat(self, module: Module):
self._qat_enabled = True
self._calibrate_if_possible(module)

# mark export mode for module Conv layers
module.export_with_qlinearconv = self._quantize_conv_activations
if hasattr(module, "module"):
# for DP/DDP unwrapping
module.module.export_with_qlinearconv = self._quantize_conv_activations

def _calibrate_if_possible(self, module):
if self.num_calibration_steps == 0 and self._calibration_dataloader:
warnings.warn(
Expand Down
Loading