Skip to content

@ROCm AMD ROCm™ Software

Change the repository type filter

All

    Repositories list

    290 repositories

    • aotriton

      Public
      Ahead of Time (AOT) Triton Math Library
      Python
      •
      MIT License
      •15•41•9•2•Updated Nov 25, 2024Nov 25, 2024

    • AMDMIGraphX

      Public
      AMD's graph optimization engine.
      C++
      •
      MIT License
      •87•187•344•40•Updated Nov 25, 2024Nov 25, 2024

    • 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•2•Updated Nov 25, 2024Nov 25, 2024

    • vllm

      Public
      A high-throughput and memory-efficient inference and serving engine for LLMs
      Python
      •
      Apache License 2.0
      •4.7k•45•0•24•Updated Nov 25, 2024Nov 25, 2024

    • flash-attention

      Public
      Fast and memory-efficient exact attention
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •1.3k•141•24•8•Updated Nov 25, 2024Nov 25, 2024

    • hip-python

      Public
      HIP Python Low-level Bindings
      pythonaihpcgpucythoncudamlinteroperabilityhipradeon-instinct-mi-series
      Shell
      •
      MIT License
      •3•17•1•1•Updated Nov 25, 2024Nov 25, 2024

    • 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•123•30•14•Updated Nov 25, 2024Nov 25, 2024

    • tensorflow-upstream

      Public
      TensorFlow ROCm port
      C++
      •
      Apache License 2.0
      •74k•688•88•60•Updated Nov 25, 2024Nov 25, 2024

    • rocm-cmake

      Public
      CMake modules used within the ROCm libraries
      CMake
      •
      MIT License
      •43•59•5•13•Updated Nov 25, 2024Nov 25, 2024

    • triton

      Public
      Development repository for the Triton language and compiler
      C++
      •
      MIT License
      •1.7k•96•10•43•Updated Nov 25, 2024Nov 25, 2024

    • 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
      •47•206•7•42•Updated Nov 25, 2024Nov 25, 2024

    • MIOpen

      Public
      AMD's Machine Intelligence Library
      Assembly
      •
      Other
      •230•1.1k•250•56•Updated Nov 25, 2024Nov 25, 2024

    • rocDecode

      Public
      rocDecode is a high performance video decode SDK for AMD hardware
      C++
      •
      Other
      •16•13•2•3•Updated Nov 25, 2024Nov 25, 2024

    • hipTensor

      Public
      AMD’s C++ library for accelerating tensor primitives
      C++
      •
      MIT License
      •17•35•0•7•Updated Nov 25, 2024Nov 25, 2024

    • rocprofiler-compute

      Public
      Advanced Profiling and Analytics for AMD Hardware
      linuxhpcperformance-analysisprofilinghardware-countersgpu-kernels
      Python
      •
      MIT License
      •50•138•50•15•Updated Nov 25, 2024Nov 25, 2024

    • ROCm

      Public
      AMD ROCm™ Software - GitHub Home
      documentation
      Shell
      •
      MIT License
      •389•4.7k•110•15•Updated Nov 25, 2024Nov 25, 2024

    • pytorch

      Public
      Tensors and Dynamic neural networks in Python with strong GPU acceleration
      pytorchrocm
      Python
      •
      Other
      •23k•219•103•39•Updated Nov 25, 2024Nov 25, 2024

    • rccl

      Public
      ROCm Communication Collectives Library (RCCL)
      C++
      •
      Other
      •122•273•10•19•Updated Nov 25, 2024Nov 25, 2024

    • hipBLAS

      Public
      ROCm BLAS marshalling library
      cudablashiprocm
      C++
      •
      Other
      •78•121•1•4•Updated Nov 25, 2024Nov 25, 2024

    • 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
      •89•63•9•64•Updated Nov 25, 2024Nov 25, 2024

    • rocWMMA

      Public
      rocWMMA
      C++
      •
      MIT License
      •26•92•2•3•Updated Nov 25, 2024Nov 25, 2024

    • HIPIFY

      Public
      HIPIFY: Convert CUDA to Portable C++ Code
      hipifyhipify-clanghipify-perlcuda2hip
      C++
      •
      MIT License
      •75•525•20•0•Updated Nov 25, 2024Nov 25, 2024

    • composable_kernel

      Public
      Composable Kernel: Performance Portable Programming Model for Machine Learning Tensor Operators
      C++
      •
      Other
      •129•321•28•46•Updated Nov 25, 2024Nov 25, 2024

    • rocSPARSE

      Public
      Next generation SPARSE implementation for ROCm platform
      C++
      •
      MIT License
      •56•117•2•0•Updated Nov 25, 2024Nov 25, 2024

    • Tensile

      Public
      Stretching GPU performance for GEMMs and tensor contractions.
      pythonmachine-learningamdgpuassemblyopencldnnmatrix-multiplicationneural-networksgpu-acceleration
      Python
      •
      MIT License
      •151•223•8•7•Updated Nov 25, 2024Nov 25, 2024

    • rocMLIR

      Public
      MLIR
      •40•129•1•17•Updated Nov 25, 2024Nov 25, 2024

    • rocm-docs-core

      Public
      ROCm Documentation Python package for ReadTheDocs build standardization
      CSS
      •
      Other
      •16•13•9•9•Updated Nov 25, 2024Nov 25, 2024

    • HIP

      Public
      HIP: C++ Heterogeneous-Compute Interface for Portability
      hiphip-runtimehipifyhip-kernel-languagehip-portabilitycuda
      C++
      •
      MIT License
      •539•3.8k•30•41•Updated Nov 25, 2024Nov 25, 2024

    • rocAL

      Public
      The AMD rocAL is designed to efficiently decode and process images and videos from a variety of storage formats and modify them through a processing graph programmable by the user.
      C++
      •
      MIT License
      •14•11•8•5•Updated Nov 25, 2024Nov 25, 2024

    • transformers

      Public
      🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.
      Python
      •
      Apache License 2.0
      •27k•4•1•4•Updated Nov 25, 2024Nov 25, 2024