An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Development repository for the Triton language and compiler

Ongoing research training transformer models at scale

verl: Volcano Engine Reinforcement Learning for LLMs

A JavaScript / TypeScript / Python / C# / PHP / Go cryptocurrency trading API with support for more than 100 bitcoin/altcoin exchanges

A curated list of insanely awesome libraries, packages and resources for Quants (Quantitative Finance)

Optimized primitives for collective multi-GPU communication

GPro: a toolbox for Generative approaches in promoter design