Pinned Loading

1. apache/flink apache/flink Public

   Apache Flink

   Java 26.4k 14.2k

2. MinivLLM MinivLLM Public

   Forked from Wenyueh/MinivLLM

   Based on Nano-vLLM, a simple replication of vLLM with self-contained paged attention and flash attention implementation

   Python

3. ray-project/ray ray-project/ray Public

   Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

   Python 44.2k 8.2k

4. RL-Align/RL-Kernel RL-Align/RL-Kernel Public

   High-performance RL post-training infrastructure. Designed to achieve bitwise operator-level train-inference consistency across heterogeneous engines and extreme memory efficiency for GRPO, PPO, etc.

   Python 444 126

5. reasoning-from-scratch reasoning-from-scratch Public

   Forked from rasbt/reasoning-from-scratch

   Implement a reasoning LLM in PyTorch from scratch, step by step

   Jupyter Notebook

6. vllm-project/vllm vllm-project/vllm Public

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

   Python 96.1k 24.3k