Pinned Loading

1. deepseek-ai/DeepGEMM deepseek-ai/DeepGEMM Public

   DeepGEMM: clean and efficient BLAS kernel library on GPU

   Cuda 7.9k 1.3k

2. deepseek-ai/DeepEP deepseek-ai/DeepEP Public

   DeepEP: an efficient expert-parallel communication library

   Cuda 10.2k 1.5k

3. deepseek-ai/TileKernels deepseek-ai/TileKernels Public

   A kernel library written in tilelang

   Python 1.8k 165

4. tile-ai/tilelang tile-ai/tilelang Public

   Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

   Python 7.5k 752

5. deepseek-ai/DeepJIT deepseek-ai/DeepJIT Public

   A lightweight library for xPU kernel JIT compilation

   C++ 337 32

6. tsinghua-ideal/Canvas tsinghua-ideal/Canvas Public

   Canvas: End-to-End Kernel Architecture Search in Neural Networks

   C++ 30 5