Skip to content

@ROCm AMD ROCm™ Software

Change the repository type filter

All

    Repositories list

    288 repositories

    • xla

      Public
      A machine learning compiler for GPUs, CPUs, and ML accelerators
      C++
      •
      Apache License 2.0
      •434•2•0•12•Updated Nov 15, 2024Nov 15, 2024

    • HIP

      Public
      HIP: C++ Heterogeneous-Compute Interface for Portability
      hiphip-runtimehipifyhip-kernel-languagehip-portabilitycuda
      C++
      •
      MIT License
      •538•3.8k•31•49•Updated Nov 15, 2024Nov 15, 2024

    • ROCm

      Public
      AMD ROCm™ Software - GitHub Home
      documentation
      Shell
      •
      MIT License
      •386•4.6k•109•13•Updated Nov 15, 2024Nov 15, 2024

    • AMDMIGraphX

      Public
      AMD's graph optimization engine.
      C++
      •
      MIT License
      •86•185•342•41•Updated Nov 15, 2024Nov 15, 2024

    • triton

      Public
      Development repository for the Triton language and compiler
      C++
      •
      MIT License
      •1.6k•93•10•44•Updated Nov 15, 2024Nov 15, 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•122•28•13•Updated Nov 15, 2024Nov 15, 2024

    • HIPIFY

      Public
      HIPIFY: Convert CUDA to Portable C++ Code
      hipifyhipify-clanghipify-perlcuda2hip
      C++
      •
      MIT License
      •75•523•20•1•Updated Nov 15, 2024Nov 15, 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
      •87•62•8•65•Updated Nov 15, 2024Nov 15, 2024

    • rocMLIR

      Public
      C++
      •40•128•1•17•Updated Nov 15, 2024Nov 15, 2024

    • pytorch

      Public
      Tensors and Dynamic neural networks in Python with strong GPU acceleration
      pytorchrocm
      Python
      •
      Other
      •23k•219•105•31•Updated Nov 15, 2024Nov 15, 2024

    • rocWMMA

      Public
      rocWMMA
      C++
      •
      MIT License
      •26•91•2•3•Updated Nov 15, 2024Nov 15, 2024

    • flash-attention

      Public
      Fast and memory-efficient exact attention
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •1.3k•138•27•9•Updated Nov 15, 2024Nov 15, 2024

    • MIOpen

      Public
      AMD's Machine Intelligence Library
      Assembly
      •
      Other
      •228•1.1k•249•48•Updated Nov 15, 2024Nov 15, 2024

    • FBGEMM

      Public
      FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/
      C++
      •
      Other
      •501•1•0•10•Updated Nov 15, 2024Nov 15, 2024

    • ROCR-Runtime

      Public
      ROCm Platform Runtime: ROCr a HPC market enhanced HSA based runtime
      C++
      •
      Other
      •109•224•12•26•Updated Nov 15, 2024Nov 15, 2024

    • clr

      Public
      C++
      •
      MIT License
      •49•100•12•15•Updated Nov 15, 2024Nov 15, 2024

    • ROCgdb

      Public
      This is ROCgdb, the ROCm source-level debugger for Linux, based on GDB, the GNU source-level debugger.
      C
      •
      GNU General Public License v2.0
      •10•50•5•1•Updated Nov 15, 2024Nov 15, 2024

    • hip-tests

      Public
      C++
      •
      MIT License
      •31•30•2•23•Updated Nov 15, 2024Nov 15, 2024

    • rocm_smi_lib

      Public
      ROCm SMI LIB
      sysadmintrace
      C++
      •
      MIT License
      •50•123•11•24•Updated Nov 15, 2024Nov 15, 2024

    • amdsmi

      Public
      AMD SMI
      sysadmin
      C++
      •
      MIT License
      •26•41•6•6•Updated Nov 15, 2024Nov 15, 2024

    • tensorflow-upstream

      Public
      TensorFlow ROCm port
      C++
      •
      Apache License 2.0
      •74k•688•93•59•Updated Nov 15, 2024Nov 15, 2024

    • tensorflow-serving

      Public
      TensorFlow Serving dockerfiles for ROCM
      Shell
      •
      Apache License 2.0
      •2•0•1•0•Updated Nov 15, 2024Nov 15, 2024

    • Tensile

      Public
      Stretching GPU performance for GEMMs and tensor contractions.
      pythonmachine-learningamdgpuassemblyopencldnnmatrix-multiplicationneural-networksgpu-acceleration
      Python
      •
      MIT License
      •150•222•9•3•Updated Nov 15, 2024Nov 15, 2024

    • vllm

      Public
      A high-throughput and memory-efficient inference and serving engine for LLMs
      Python
      •
      Apache License 2.0
      •4.6k•45•0•24•Updated Nov 15, 2024Nov 15, 2024

    • rocDecode

      Public
      rocDecode is a high performance video decode SDK for AMD hardware
      C++
      •
      Other
      •16•13•4•5•Updated Nov 15, 2024Nov 15, 2024

    • transformers

      Public
      🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.
      Python
      •
      Apache License 2.0
      •27k•4•0•3•Updated Nov 15, 2024Nov 15, 2024

    • TransformerEngine

      Public
      Python
      •
      Other
      •3•12•9•5•Updated Nov 15, 2024Nov 15, 2024

    • composable_kernel

      Public
      Composable Kernel: Performance Portable Programming Model for Machine Learning Tensor Operators
      C++
      •
      Other
      •128•311•32•44•Updated Nov 15, 2024Nov 15, 2024

    • rccl

      Public
      ROCm Communication Collectives Library (RCCL)
      C++
      •
      Other
      •120•268•9•17•Updated Nov 14, 2024Nov 14, 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•8•38•Updated Nov 14, 2024Nov 14, 2024