Repositories list

• composable_kernel

  Public
  Composable Kernel: Performance Portable Programming Model for Machine Learning Tensor Operators

  C++

  •

  Other

  •137•330•26•49•Updated Jan 4, 2025Jan 4, 2025

• llvm-project

  Public
  This is the AMD-maintained fork of the LLVM git repository. This repository accepts pull requests and issues related to AMD fork-specific topics (amd/*). For all other issues/PRs, please submit upstream at https://github.com/llvm/llvm-project.

  LLVM

  •

  Other

  •12k•126•31•17•Updated Jan 4, 2025Jan 4, 2025

• rocPyDecode

  Public
  rocPyDecode is a set of Python bindings to rocDecode C++ library which provides full HW acceleration for video decoding on AMD GPUs.

  C++

  •

  MIT License

  •7•3•0•5•Updated Jan 4, 2025Jan 4, 2025

• rccl

  Public
  ROCm Communication Collectives Library (RCCL)

  C++

  •

  Other

  •128•286•14•21•Updated Jan 4, 2025Jan 4, 2025

• TransformerEngine

  Public
  Python

  •

  Other

  •5•14•9•5•Updated Jan 4, 2025Jan 4, 2025

• flang

  Public
  Mirror of flang repo: The source repo is https://github.com/flang-compiler/flang . Once a day the master branch is updated from the upstream source repo and then locked. AOMP or ROCm developers may commit or create PRs on branch aomp-dev.

  C++

  •

  Other

  •8•6•0•10•Updated Jan 4, 2025Jan 4, 2025

• rocRAND

  Public
  RAND library for HIP programming language

  randomrnghip+ 3rocmgpucuda

  C++

  •

  MIT License

  •70•114•1•6•Updated Jan 4, 2025Jan 4, 2025

• rpp

  Public
  AMD ROCm Performance Primitives (RPP) library is a comprehensive high-performance computer vision library for AMD processors with HIP/OpenCL/CPU back-ends.

  cpucomputer-visionhpc+ 15amdgpuopenclhistogramcontrastbitwisehip+ 8

  C++

  •

  MIT License

  •41•57•4•8•Updated Jan 4, 2025Jan 4, 2025

• AMDMIGraphX

  Public
  AMD's graph optimization engine.

  C++

  •

  MIT License

  •88•193•350•51•Updated Jan 4, 2025Jan 4, 2025

• rocprofiler-sdk

  Public
  C++

  •

  MIT License

  •10•17•8•6•Updated Jan 4, 2025Jan 4, 2025

• bitsandbytes

  Public
  8-bit CUDA functions for PyTorch

  Python

  •

  MIT License

  •644•42•8•3•Updated Jan 4, 2025Jan 4, 2025

• Tensile

  Public
  Stretching GPU performance for GEMMs and tensor contractions.

  pythonmachine-learningamd+ 15gpuassemblyopencldnnmatrix-multiplicationneural-networksgpu-acceleration+ 8

  Python

  •

  MIT License

  •152•228•5•8•Updated Jan 3, 2025Jan 3, 2025

• rocSPARSE

  Public
  Next generation SPARSE implementation for ROCm platform

  C++

  •

  MIT License

  •56•116•2•0•Updated Jan 3, 2025Jan 3, 2025

• xla

  Public
  A machine learning compiler for GPUs, CPUs, and ML accelerators

  C++

  •

  Apache License 2.0

  •459•3•0•18•Updated Jan 3, 2025Jan 3, 2025

• MIOpen

  Public
  AMD's Machine Intelligence Library

  Assembly

  •

  Other

  •232•1.1k•248•64•Updated Jan 3, 2025Jan 3, 2025

• onnxruntime

  Public
  ONNX Runtime: cross-platform, high performance scoring engine for ML models

  C++

  •

  MIT License

  •3k•6•0•6•Updated Jan 3, 2025Jan 3, 2025

• rocm-cmake

  Public
  CMake modules used within the ROCm libraries

  CMake

  •

  MIT License

  •43•63•4•13•Updated Jan 3, 2025Jan 3, 2025

• pytorch

  Public
  Tensors and Dynamic neural networks in Python with strong GPU acceleration

  pytorchrocm

  Python

  •

  Other

  •23k•220•76•40•Updated Jan 3, 2025Jan 3, 2025

• ROCm

  Public
  AMD ROCm™ Software - GitHub Home

  documentation

  Shell

  •

  MIT License

  •393•4.8k•114•17•Updated Jan 3, 2025Jan 3, 2025

• flash-attention

  Public
  Fast and memory-efficient exact attention

  Python

  •

  BSD 3-Clause "New" or "Revised" License

  •1.4k•150•24•12•Updated Jan 3, 2025Jan 3, 2025

• rocBLAS

  Public
  Next generation BLAS implementation for ROCm platform

  blashiprocm

  C++

  •

  Other

  •169•354•4•1•Updated Jan 3, 2025Jan 3, 2025

• hipTensor

  Public
  AMD’s C++ library for accelerating tensor primitives

  C++

  •

  MIT License

  •20•37•0•2•Updated Jan 3, 2025Jan 3, 2025

• aotriton

  Public
  Ahead of Time (AOT) Triton Math Library

  Python

  •

  MIT License

  •16•47•10•1•Updated Jan 3, 2025Jan 3, 2025

• apex

  Public
  A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

  Python

  •

  BSD 3-Clause "New" or "Revised" License

  •1.4k•19•13•8•Updated Jan 3, 2025Jan 3, 2025

• hip-python

  Public
  HIP Python Low-level Bindings

  pythonaihpc+ 7gpucythoncudamlinteroperabilityhipradeon-instinct-mi-series

  Shell

  •

  MIT License

  •3•17•2•2•Updated Jan 3, 2025Jan 3, 2025

• dyninst

  Public
  DyninstAPI: Tools for binary instrumentation, analysis, and modification.

  C

  •

  GNU Lesser General Public License v2.1

  •157•1•0•0•Updated Jan 3, 2025Jan 3, 2025

• rocprofiler-systems

  Public
  ROCm Systems Profiler

  C++

  •

  MIT License

  •6•12•0•2•Updated Jan 3, 2025Jan 3, 2025

• rocWMMA

  Public
  rocWMMA

  C++

  •

  MIT License

  •26•96•2•2•Updated Jan 3, 2025Jan 3, 2025

• triton

  Public
  Development repository for the Triton language and compiler

  C++

  •

  MIT License

  •1.7k•100•9•43•Updated Jan 3, 2025Jan 3, 2025

• rocm-docs-core

  Public
  ROCm Documentation Python package for ReadTheDocs build standardization

  CSS

  •

  Other

  •17•13•6•12•Updated Jan 3, 2025Jan 3, 2025