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