← Trending

Tangerine Index lists products launched since ChatGPT and people's reactions to them.

flash-linear-attention

github.com

🚀 Efficient implementations for emerging model architectures

Open source

Visit github.comexternal siteGitHub6,027 starsexternal site

Reactions (1)

Similar products

by description similarity

  1. FlashQLA

    high-performance linear attention kernel library built on TileLang

    GitHub750 starsgithub.comLibraryOpen sourcelatest reaction

  2. flash-sparse-attention

    Trainable fast and memory-efficient sparse attention

    GitHub747 starsgithub.comOpen sourcelatest reaction

  3. ring-flash-attention

    Ring attention implementation with flash attention

    GitHub1,067 starsgithub.comOpen sourcelatest reaction

  4. cuLA

    CUDA kernels for linear attention variants, written in CuTe DSL and CUTLASS C++.

    GitHub560 starsgithub.comOpen sourcelatest reaction

  5. mav

    Model Activity Visualiser

    GitHub521 starsgithub.comOpen sourcelatest reaction