Skip to content

Pinned Loading

  1. PAT PAT Public

    Prefix-Aware Attention for LLM Decoding

    Python 54 3

  2. flash-linear-attention-npu flash-linear-attention-npu Public

    🚀 Efficient linear attention kernels for Ascend NPUs

    C++ 82 110

  3. OLED-MoE OLED-MoE Public

    Accelerating MoE-Based dLLM Inference via Inter-Iteration Locality-Aware Expert Offloading

    Python 16

  4. ReWY ReWY Public

    Faster Gradient Computation for Delta-Rule Attention Family

    Python 17

Repositories

Showing 6 of 6 repositories
  • flash-linear-attention-npu Public

    🚀 Efficient linear attention kernels for Ascend NPUs

    flashserve/flash-linear-attention-npu's past year of commit activity
    C++ 82 110 153 231 Updated Nov 21, 2026
  • Mosaic Public

    [ICML'26] MOSAIC: Unlocking Over 30× Context Length for Diffusion LLMs Inference via Global Memory Planning and Dynamic Peak Taming

    flashserve/Mosaic's past year of commit activity
    Python 16 Apache-2.0 0 0 0 Updated Nov 8, 2026
  • ReWY Public

    Faster Gradient Computation for Delta-Rule Attention Family

    flashserve/ReWY's past year of commit activity
    Python 17 MIT 0 0 0 Updated Nov 3, 2026
  • OLED-MoE Public

    Accelerating MoE-Based dLLM Inference via Inter-Iteration Locality-Aware Expert Offloading

    flashserve/OLED-MoE's past year of commit activity
    Python 16 0 0 0 Updated Sep 30, 2026
  • RAGPulse Public

    An Open-Source RAG Workload Trace to Optimize RAG Serving Systems

    flashserve/RAGPulse's past year of commit activity
    Python 45 MIT 4 0 0 Updated Sep 1, 2026
  • PAT Public

    Prefix-Aware Attention for LLM Decoding

    flashserve/PAT's past year of commit activity
    Python 54 MIT 3 0 0 Updated May 26, 2026

Top languages

Loading…