Projects
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
Python - Released: 09 Feb 2023 - 28,039
alpa
Training and serving large-scale neural networks with auto parallelization.
Python - Released: 22 Feb 2021 - 2,990
macaron-net
Codes for "Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View"
Python - Released: 01 Jun 2019 - 146
g2-lstm
Codes for "Towards Binary-Valued Gates for Robust LSTM Training".
Python - Released: 31 May 2018 - 76