wimh966

QDrop

The official PyTorch implementation of the ICLR2022 paper, QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization

outlier_suppression

The official PyTorch implementation of the NeurIPS2022 (spotlight) paper, Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models

BRECQ

Pytorch implementation of BRECQ, ICLR 2021

I-BERT

[ICML'21] I-BERT: Integer-only BERT Quantization

nlp-architect

A model library for exploring state-of-the-art deep learning topologies and techniques for optimizing Natural Language Processing neural networks

Outlier_Suppression_Plus

TensorRT

TensorRT is a C++ library for high performance inference on NVIDIA GPUs and deep learning accelerators.

wimh966.github.io