Skip to content

@ROCm AMD ROCm™ Software

Change the repository type filter

All

    Repositories list

    295 repositories

    • MIOpen

      Public
      AMD's Machine Intelligence Library
      Assembly
      •
      Other
      •235•1.1k•248•60•Updated Jan 11, 2025Jan 11, 2025

    • rccl-tests

      Public
      RCCL Performance Benchmark Tests
      Cuda
      •
      Other
      •41•53•3•13•Updated Jan 11, 2025Jan 11, 2025

    • rccl

      Public
      ROCm Communication Collectives Library (RCCL)
      C++
      •
      Other
      •128•288•12•17•Updated Jan 11, 2025Jan 11, 2025

    • Tensile

      Public
      Stretching GPU performance for GEMMs and tensor contractions.
      pythonmachine-learningamdgpuassemblyopencldnnmatrix-multiplicationneural-networksgpu-acceleration
      Python
      •
      MIT License
      •154•229•5•8•Updated Jan 11, 2025Jan 11, 2025

    • jax

      Public
      Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
      Python
      •
      Apache License 2.0
      •2.8k•19•0•14•Updated Jan 11, 2025Jan 11, 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•127•24•11•Updated Jan 11, 2025Jan 11, 2025

    • flash-attention

      Public
      Fast and memory-efficient exact attention
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •1.4k•151•24•12•Updated Jan 11, 2025Jan 11, 2025

    • pytorch

      Public
      Tensors and Dynamic neural networks in Python with strong GPU acceleration
      pytorchrocm
      Python
      •
      Other
      •23k•220•76•39•Updated Jan 11, 2025Jan 11, 2025

    • rocDecode

      Public
      rocDecode is a high performance video decode SDK for AMD hardware
      C++
      •
      Other
      •17•21•3•0•Updated Jan 11, 2025Jan 11, 2025

    • rocJPEG

      Public
      rocJPEG is a high-performance jpeg decode SDK for decoding jpeg images using a hardware-accelerated jpeg decoder on AMD’s GPUs.
      C++
      •
      MIT License
      •8•3•1•0•Updated Jan 11, 2025Jan 11, 2025

    • aomp

      Public
      AOMP is an open source Clang/LLVM based compiler with added support for the OpenMP® API on Radeon™ GPUs. Use this repository for releases, issues, documentation, packaging, and examples.
      amdllvmopenmpclangfortran-compilerrocm
      Fortran
      •
      Apache License 2.0
      •48•210•1•45•Updated Jan 11, 2025Jan 11, 2025

    • hipCUB

      Public
      Reusable software components for ROCm developers
      C++
      •
      Other
      •41•81•2•7•Updated Jan 11, 2025Jan 11, 2025

    • composable_kernel

      Public
      Composable Kernel: Performance Portable Programming Model for Machine Learning Tensor Operators
      C++
      •
      Other
      •139•331•24•52•Updated Jan 11, 2025Jan 11, 2025

    • triton

      Public
      Development repository for the Triton language and compiler
      C++
      •
      MIT License
      •1.7k•102•9•45•Updated Jan 11, 2025Jan 11, 2025

    • hipSOLVER

      Public
      ROCm SOLVER marshalling library
      C++
      •
      MIT License
      •25•24•0•2•Updated Jan 11, 2025Jan 11, 2025

    • vllm

      Public
      A high-throughput and memory-efficient inference and serving engine for LLMs
      Python
      •
      Apache License 2.0
      •5.1k•53•1•16•Updated Jan 11, 2025Jan 11, 2025

    • xformers

      Public
      Hackable and optimized Transformers building blocks, supporting a composable construction.
      Python
      •
      Other
      •634•22•8•3•Updated Jan 11, 2025Jan 11, 2025

    • torch_migraphx

      Public
      Libraries integrating migraphx with pytorch
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •2•6•13•3•Updated Jan 11, 2025Jan 11, 2025

    • rocBLAS

      Public
      Next generation BLAS implementation for ROCm platform
      blashiprocm
      C++
      •
      Other
      •170•354•5•1•Updated Jan 11, 2025Jan 11, 2025

    • ROCm

      Public
      AMD ROCm™ Software - GitHub Home
      documentation
      Shell
      •
      MIT License
      •395•4.8k•112•14•Updated Jan 11, 2025Jan 11, 2025

    • hipBLASLt

      Public
      hipBLASLt is a library that provides general matrix-matrix operations with a flexible API and extends functionalities beyond a traditional BLAS library
      machine-learningamdassemblymatrix-multiplicationblashipgpu-computinggemmrocm
      Assembly
      •
      MIT License
      •97•71•7•62•Updated Jan 11, 2025Jan 11, 2025

    • rocThrust

      Public
      ROCm Thrust - run Thrust dependent software on AMD GPUs
      C++
      •
      Apache License 2.0
      •47•104•3•5•Updated Jan 11, 2025Jan 11, 2025

    • rocPRIM

      Public
      ROCm Parallel Primitives
      amdgpuparallelcudaprimitivehiprocm
      C++
      •
      MIT License
      •72•167•1•7•Updated Jan 11, 2025Jan 11, 2025

    • rocprofiler-compute

      Public
      Advanced Profiling and Analytics for AMD Hardware
      linuxhpcperformance-analysisprofilinghardware-countersgpu-kernels
      Python
      •
      MIT License
      •51•139•49•9•Updated Jan 11, 2025Jan 11, 2025

    • rocRAND

      Public
      RAND library for HIP programming language
      randomrnghiprocmgpucuda
      C++
      •
      MIT License
      •70•114•1•6•Updated Jan 11, 2025Jan 11, 2025

    • ROCmValidationSuite

      Public
      A system validation and diagnostics tool for monitoring, stress testing, detecting, and troubleshooting issues impacting AMD GPUs in high-performance computing environments
      C++
      •
      MIT License
      •39•66•0•8•Updated Jan 11, 2025Jan 11, 2025

    • hipRAND

      Public
      Random number library that generate pseudo-random and quasi-random numbers.
      C++
      •
      MIT License
      •24•25•0•5•Updated Jan 11, 2025Jan 11, 2025

    • hipfort

      Public
      Fortran interfaces for ROCm libraries
      fortrangpurandomsolvercudainteroperabilitygpgpusparseblasfft
      Fortran
      •
      Other
      •39•72•15•7•Updated Jan 11, 2025Jan 11, 2025

    • TransferBench

      Public
      TransferBench is a utility capable of benchmarking simultaneous copies between user-specified devices (CPUs/GPUs)
      C++
      •
      MIT License
      •14•38•0•2•Updated Jan 11, 2025Jan 11, 2025

    • rocprofiler-sdk

      Public
      C++
      •
      MIT License
      •10•17•8•6•Updated Jan 10, 2025Jan 10, 2025