Pinned Loading

1. thu-ml/SageAttention thu-ml/SageAttention Public

   Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models.

   Cuda 586 27

2. SPH_Project SPH_Project Public

   SPH Realization of Fluid Simulation. Featuring Large Scale Simulation, Rigid-Fluid Coupling and High Viscosity Fluid.

   Python 138 10

3. thu-nics/MoA thu-nics/MoA Public

   The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>

   Python 100 6

4. mit-han-lab/qserve mit-han-lab/qserve Public

   QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving

   Python 455 25