Geek Repo
followers
following
stars
Company:University of California, Berkeley
Location:Berkeley, CA
Home Page:https://woosuk.me
Twitter:@woosuk_k
Github PK Tool:Github PK Tool
[NeurIPS 2022] A Fast Post-Training Pruning Framework for Transformers
A high-throughput and memory-efficient inference and serving engine for LLMs
Enabling PyTorch on XLA Devices (e.g. Google TPU)