gemm repositories

Trending repositories tagged gemm, ranked by trending score. Updated daily.

  1. 1
    NVIDIA/cudnn-frontend

    cuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.

    GitHub · Cuda · 1,007 stars · 340 forks · +3 stars in 24 hours · Trending score 1.47

  2. 2
    OpenNMT/CTranslate2

    Fast inference engine for Transformer models

    GitHub · C++ · 4,757 stars · 562 forks · +1 stars in 24 hours · Trending score 1.05

  3. 3
    CNugteren/CLBlast

    Tuned OpenCL BLAS

    GitHub · C++ · 1,201 stars · 216 forks · +1 stars in 24 hours · Trending score 0.99

  4. 4
    ROCm/iris

    AMD RAD's multi-GPU Triton-based framework for seamless multi-GPU programming

    GitHub · Python · 206 stars · 63 forks · 0 stars in 24 hours · Trending score 0.66

  5. 5
    michael-lehn/ulmBLAS

    ulmBLAS

    GitHub · C++ · 121 stars · 34 forks · +1 stars in 24 hours · Trending score 0.54

  6. 6
    OpenBitSys/vlut.cpp

    [MobiSys 2026] On-device ultra-low-bit LLM inference with LUT

    GitHub · C++ · 29 stars · 6 forks · 0 stars in 24 hours · Trending score 0.37

  7. 7
    Danialjfz/Opti-GEMM

    Step-by-step CUDA GEMM optimization: from naive kernels to architecture-aware GPU performance analysis.

    GitHub · Cuda · 5 stars · 1 forks · 0 stars in 24 hours · Trending score 0.09

  8. 8
    cp2k/dbcsr

    DBCSR: Distributed Block Compressed Sparse Row matrix library

    GitHub · Fortran · 157 stars · 60 forks · 0 stars in 24 hours · Trending score 0.00

  9. 9
    Alfinaa9442/v100-skinny

    Run Qwen3.6-27B on four Tesla V100s at 366 tok/s using hand-written NVFP4 CUDA kernels and chain-MTP speculation.

    GitHub · Python · 20 stars · 1 forks · 0 stars in 24 hours · Trending score 0.00

  10. 10
    FP4-is-All-you-Need/BLAS

    Exact matrix products on FP4 Tensor Cores: the Adaptive Weight Encoding (AWE) catalog and the BLAS routines built on it.

    GitHub · Cuda · 6 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00

  11. 11
    astding/mmaemu

    Bit-exact emulation of NVIDIA tensor-core FP8 GEMMs (torch._scaled_mm, Transformer Engine) as an H100 PCIe or RTX 4060 computes them, on the CPU or another CUDA GPU

    GitHub · Python · 60 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00