xwjiang2010

vllm

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

ray-meetup-cifar10-demo

ray air cifar10 demo for ray meetup

dotfiles

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

koch

pytorch

ray

An open source framework that provides a simple, universal API for building distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.

tune-sklearn-xgboost