garrett4wade

DeepSpeedExamples

Example models using DeepSpeed

openrlhf-vllm

DeepSpeed-for-dschat

util-scripts

garrett4wade.github.io

sphinx-action

Github action that builds docs using sphinx and places errors inline

OpenRLHF-1

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & Mixtral)

sphinx-pages

Build html documentation by Sphinx, and push to branch gh-pages.

sipo

Iteratively Learn Diverse Strategies with State Distance Information

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

cugae

CUDA implementation of Generalized Advantage Estimation (GAE)

flash-attention

Fast and memory-efficient exact attention

gpu-burn

Multi-GPU CUDA stress test

scaling_marl

Trust-Region-Methods-in-Multi-Agent-Reinforcement-Learning

revisiting_marl

Official codebase for paper "Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning" (ICML22)

atari_dqn

build_football_engine

Build script for Google Research Football on M1 Mac.

ray_rl

rl-tf1