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

Commit 30ca1bd

authored

ONNX QAT -> Quant conversion for Gemm nodes w/o QAT activations (#528) (#529)

* ONNX QAT -> Quant conversion for Gemm nodes w/o QAT activations * remove testing block string * small imoprt fix in transformers init file

1 parent fcc0c55 commit 30ca1bdCopy full SHA for 30ca1bd

2 files changed

+276

-117

lines changed

src/sparseml
- pytorch/utils/quantization
  - quantize_qat_export.py
- transformers
  - __init__.py

+276

-117

lines changed

Comments

(0)