Pinned Loading

1. gpu-sparse gpu-sparse Public

   GPU kernels for exact learned sparse retrieval (SPLADE) on a GPU-resident inverted index

   Python 1

2. tilemaxsim tilemaxsim Public

   IO-aware GPU Triton kernels for MaxSim scoring in multi-vector (ColBERT-style) retrieval

   Python 3 1

3. sgl-project/sglang sgl-project/sglang Public

   SGLang is a high-performance serving framework for large language models and multimodal models.

   Python 30.3k 7.2k

4. radixark/miles radixark/miles Public

   Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.

   Python 1.7k 311

5. NovaSky-AI/SkyRL NovaSky-AI/SkyRL Public

   SkyRL: A Modular Full-stack RL Library for LLMs

   Python 2.1k 384

6. sidmadala/CS443-RLHF sidmadala/CS443-RLHF Public

   RLHF implementation for UIUC's CS 443: Reinforcement Learning

   Jupyter Notebook