gemm 开源项目推荐（265 个）

OpenNMT /CTranslate2

Transformer 模型的快速推理引擎

flame /how-to-optimize-gemm

该项目在 GitHub 上没有填写描述

CNugteren /CLBlast

Tuned OpenCL BLAS

NVIDIA /cudnn-frontend

cuDNN 前端是 NVIDIA 现代开源的 cuDNN 库入口，以及一个不断增长的高性能开源内核集合。

flame /blislab

BLISlab: A Sandbox for Optimizing GEMM

Bruce-Lee-LY /cuda_hgemm

Several optimization methods of half-precision general matrix multiplication (HGEMM) using tensor core with WMMA API and MMA PTX instruction.

coderonion /awesome-cuda-and-hpc

🚀🚀🚀 This repository lists some awesome public CUDA, cuda-python, cuBLAS, cuDNN, CUTLASS, TensorRT, TensorRT-LLM, Triton, TVM, MLIR, PTX and High Performance Computing (HPC) projects.

yzhaiustc /Optimizing-SGEMM-on-NVIDIA-Turing-GPUs

Optimizing SGEMM kernel functions on NVIDIA GPUs to a close-to-cuBLAS performance.

salykova /sgemm.c

Multi-Threaded FP32 Matrix Multiplication on x86 CPUs

mratsim /laser

The HPC toolbox: fused matrix multiplication, convolution, data-parallel strided tensor primitives, OpenMP facilities, SIMD, JIT Assembler, CPU detection, state-of-the-art vectorized BLAS for floats and integers

ROCm /Tensile

[DEPRECATED] Moved to ROCm/rocm-libraries repo

ROCm /iris

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

dnv2003 /v100-skinny

Hand-written NVFP4 W4A16 CUDA kernels for Volta

yzhaiustc /Optimizing-DGEMM-on-Intel-CPUs-with-AVX512F

Stepwise optimizations of DGEMM on CPU, reaching performance faster than Intel MKL eventually, even under multithreading.

cp2k /dbcsr

DBCSR: Distributed Block Compressed Sparse Row matrix library

BoooC /CNN-Accelerator-Based-on-Eyeriss-v2

A Flexible and Energy Efficient Accelerator For Sparse Convolution Neural Network

yui0 /slibs

Single file libraries for C/C++

enp1s0 /ozIMMU

FP64 equivalent GEMM by the Ozaki scheme with Int8 Tensor Cores

ROCm /hipBLASLt

[DEPRECATED] Moved to ROCm/rocm-libraries repo

psmarter /CUDA-Practice

CUDA编程练习项目-Hands-on CUDA kernels and performance optimization, covering GEMM, FlashAttention, Tensor Cores, CUTLASS, quantization, KV cache, NCCL, and profiling.