linear-attention repositories

Trending repositories tagged linear-attention, ranked by trending score. Updated daily.

  1. 1
    FareedKhan-dev/kimi-k3-in-c

    A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.

    GitHub · C · 12,516 stars · 1,940 forks · +127 stars in 24 hours · Trending score 4.17

  2. 2
    Intellindust-AI-Lab/GTR

    GTR: Gated Token Recurrence for Efficient Dense Prediction

    GitHub · Python · 150 stars · 14 forks · +99 stars in 24 hours · Trending score 3.44

  3. 3
    OmniJev/Flide

    🔥🔥 The extremely fast inference engine for decision model

    GitHub · Python · 550 stars · 38 forks · +7 stars in 24 hours · Trending score 2.17

  4. 4
    Interactive-Active-AI/NextTransformer

    :sunrise: A comprehensive, cutting-edge open-source framework for next-generation Transformers/LLM, with compute-matched benchmarking and a platform for autonomous architecture research.

    GitHub · Python · 487 stars · 41 forks · +6 stars in 24 hours · Trending score 2.15

  5. 5
    SNU-ARC/SketchSSM

    SketchSSM: Write to the Full State, Read from a Compact Sketch

    GitHub · Python · 16 stars · 0 forks · +3 stars in 24 hours · Trending score 0.92

  6. 6
    melonmath/microkimi

    The Kimi K3 and DeepSeek-V4-Flash-0731 architectures, reimplemented from scratch in pure Rust (zero dependencies) and verified 1:1 against the official code.

    GitHub · Rust · 23 stars · 2 forks · 0 stars in 24 hours · Trending score 0.00

  7. 7
    SunnyClaw-cx/SunnyNet

    An O(N) CPU-first linear recurrence inference runtime — hand-written AVX2/AVX-512 kernels, multi-architecture support (SunnyNet / RWKV-7 / Mamba-2 / GLA / DeltaNet / HGRN2)

    GitHub · Python · 18 stars · 1 forks · 0 stars in 24 hours · Trending score 0.00

  8. 8
    SpeedAI-Lab/DAMI

    DAMI: Dual-Axis Memory Initialization for Enhanced Long-Context Retrieval in Gated Linear Attention

    GitHub · Python · 9 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00