Skip to content
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

Jump to bottom

Move STE/LSQ activation quantizers from QAT to trainable infrastructure for PyTorch #1178

Merged
merged 4 commits into from
Sep 3, 2024
Merged

Move STE/LSQ activation quantizers from QAT to trainable infrastructure for PyTorch #1178

merged 4 commits into from
Sep 3, 2024

Conversation

irenaby
Copy link
Collaborator

@irenaby irenaby commented Aug 20, 2024 •
edited
Loading

Pull Request Description:

Checklist before requesting a review:

  • I set the appropriate labels on the pull request.
  • I have added/updated the release note draft (if necessary).
  • I have updated the documentation to reflect my changes (if necessary).
  • All function and files are well documented.
  • All function and classes have type hints.
  • There is a licenses in all file.
  • The function and variable names are informative.
  • I have checked for code duplications.
  • I have added new unittest (if necessary).

@irenaby irenaby force-pushed the act_quant branch 6 times, most recently from 6373e39 to a6a8e92 Compare August 25, 2024 10:50
@irenaby irenaby changed the title move activation quantizers from qat to trainable infrastructure for p… Unify QAT and GPTQ activation quantizers for PyTorch Aug 25, 2024
@irenaby irenaby marked this pull request as ready for review August 25, 2024 11:47
@irenaby irenaby requested a review from ofirgo August 25, 2024 11:48
ofirgo
ofirgo requested changes Aug 29, 2024
View reviewed changes
model_compression_toolkit/trainable_infrastructure/__init__.py Outdated Show resolved Hide resolved
model_compression_toolkit/trainable_infrastructure/common/base_trainable_quantizer.py Show resolved Hide resolved
model_compression_toolkit/trainable_infrastructure/common/base_trainable_quantizer.py Outdated Show resolved Hide resolved
model_compression_toolkit/trainable_infrastructure/common/base_trainable_quantizer.py Show resolved Hide resolved
model_compression_toolkit/trainable_infrastructure/common/training_method.py Show resolved Hide resolved
...ytorch_tests/trainable_infrastructure_tests/trainable_pytorch/test_pytorch_base_quantizer.py Show resolved Hide resolved
tests/pytorch_tests/model_tests/feature_models/qat_test.py Outdated Show resolved Hide resolved
tests/pytorch_tests/function_tests/test_activation_quantization_holder_gptq.py Outdated Show resolved Hide resolved
tests/pytorch_tests/function_tests/test_activation_quantization_holder_gptq.py Outdated Show resolved Hide resolved
tests/keras_tests/feature_networks_tests/feature_networks/qat/qat_test.py Outdated Show resolved Hide resolved
@irenaby irenaby changed the title Unify QAT and GPTQ activation quantizers for PyTorch Move STE/LSQ activation quantizers from QAT to trainable infrastructure for PyTorch Sep 1, 2024
@ofirgo ofirgo self-requested a review September 3, 2024 11:57
@irenaby irenaby merged commit 3a3cc2c into main Sep 3, 2024
32 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@ofirgo ofirgo ofirgo approved these changes

Assignees
No one assigned
Labels
auto:gptq auto:qat auto:tests auto:trainable_infrastructure
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@irenaby @ofirgo