kouroshHakha/SkyRL
SkyRL: A Modular Full-stack RL Library for LLMs
SkyRL: A Modular Full-stack RL Library for LLMs
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.
AIPerf is a comprehensive benchmarking tool that measures the performance of generative AI models served by your preferred inference solution.
genetic and neural net optimization for circuit design
A high-throughput and memory-efficient inference and serving engine for LLMs
veRL: Volcano Engine Reinforcement Learning for LLM
DRL final project
SGLang is a fast serving framework for large language models and vision language models.
Sky-T1: Train your own O1 preview model within $450
Clean, accessible reproduction of DeepSeek R1-Zero
This is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data
An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)
Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
⚡ Building applications with LLMs through composability ⚡
Keeping track of RL experiments
An offline deep reinforcement learning library
Pytorch implementation of Neural Processes for functions and images :fireworks:
PyTorch implementation of Soft Actor-Critic (SAC)