Pinned Loading

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

   [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without lossing end-to-end metrics across language, image, and video models.

   Cuda 2.5k 238

2. thu-ml/SpargeAttn thu-ml/SpargeAttn Public

   [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.

   Cuda 735 60

3. SPH_Project SPH_Project Public

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

   Python 189 16

4. 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 3.3k 274

5. thu-nics/MoA thu-nics/MoA Public

   [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>

   Python 146 8

6. 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++ 763 52