WoosukKwon

Woosuk Kwon's repositories

[NeurIPS 2022] A Fast Post-Training Pruning Framework for Transformers

Language:Python180 5 19

A high-throughput and memory-efficient inference and serving engine for LLMs

Language:PythonApache-2.0600

Enabling PyTorch on XLA Devices (e.g. Google TPU)

Language:C++NOASSERTION100

Official repository for Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinions

Language:PythonBSD-3-Clause000