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 1.1k 64

2. SPH_Project SPH_Project Public

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

   Python 158 11

3. mit-han-lab/llm-awq mit-han-lab/llm-awq Public

   [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

   Python 2.8k 233

4. 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 119 6

5. mit-han-lab/omniserve mit-han-lab/omniserve Public

   [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention

   C++ 575 35