Pinned Loading

1. fudan-zvg/SOFT fudan-zvg/SOFT Public

   [NeurIPS 2021 Spotlight] & [IJCV 2024] SOFT: Softmax-free Transformer with Linear Complexity

   Python 310 26

2. deepspeedai/DeepSpeed deepspeedai/DeepSpeed Public

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

   Python 42.8k 4.9k

3. MAC-Attention MAC-Attention Public

   Python 7

4. NovaSky-AI/SkyRL NovaSky-AI/SkyRL Public

   SkyRL: A Modular Full-stack RL Library for LLMs

   Python 2.1k 390

5. ExFlow ExFlow Public

   Explore Inter-layer Expert Affinity in MoE Model Inference

   Python 16 1

6. Flover Flover Public

   Temporal Fusion Framework for Efficient Autoregressive Model Parallel Inference

   C++ 9