Gemm Python Packages

ctranslate2

Fast inference engine for Transformer models

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.

tokenspeed-iris

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

ctranslate2-arty

Fast inference engine for Transformer models

trnblas

BLAS Levels 1–3 for AWS Trainium via NKI (cuBLAS-equivalent) — GEMM with stationary-tile reuse, batched GEMM, TRSM, validated DF-MP2 for quantum chemistry.

pyclblast

Python bindings for CLBlast, the tuned OpenCL BLAS library

sparsemma

INT8 Sparse Tensor Core GEMM for PyTorch — built for Windows