Lausanne, Switzerland

Xiuying Wei

Advanced
@wimh966
wimh966.github.io/

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

131

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

49

rat-plus. RAT+: Train Dense, Infer Sparse - Recurrence Augmented Attention for Dilated Inference (ICML2026)

10
3
Apply