Skip to content

@moonmath-ai MoonMath.ai

Change the repository type filter

All

    Repositories list

    6 repositories

    • SageAttention

      Public
      Quantized Attention achieves speedup of 2-5x and 3-11x compared to FlashAttention and xformers, without lossing end-to-end metrics across language, image, and video models.
      Cuda
      •
      Apache License 2.0
      •238•0•0•0•Updated Oct 8, 2025Oct 8, 2025

    • moon-lite-attention

      Public
      Fast and memory-efficient exact attention (fork of flash-attention)
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •2k•0•0•0•Updated Sep 22, 2025Sep 22, 2025

    • moondex

      Public
      MoonMath.ai’s index of knowledge
      0•1•0•0•Updated Sep 8, 2025Sep 8, 2025

    • Jenga

      Public
      Official Implementation: Training-Free Efficient Video Generation via Dynamic Token Carving
      Python
      •12•0•0•0•Updated Aug 22, 2025Aug 22, 2025

    • radial-attention

      Public
      Radial Attention Official Implementation
      Python
      •
      Apache License 2.0
      •29•0•0•0•Updated Aug 6, 2025Aug 6, 2025

    • Wan2.1-pv-skip

      Public
      Wan: Open and Advanced Large-Scale Video Generative Models
      Python
      •
      Apache License 2.0
      •2k•0•0•0•Updated Jul 17, 2025Jul 17, 2025