Repositories list

• FlyDSL

  Public

  ROCm/FlyDSL’s past year of commit activity
  FlyDSL is the Python front‑end of the project: a Flexible Layout Python DSL for expressing tiling, partitioning, data movement, and kernel structure at a high l…

  performancedeep-learninggpu+ 4

  performancedeep-learninggpuamdgpucutemlirpython-dsl

  Python

  •

  Other

  •116116 forks•269269 stars•5151 issues•8080 pull requests•Updated Aug 31, 2026Aug 31, 2026

• llvm-project

  Public

  ROCm/llvm-project’s past year of commit activity
  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 al…

  LLVM

  •

  Other

  •18k18k forks•233233 stars•4848 issues•199199 pull requests•Updated Aug 31, 2026Aug 31, 2026

• aiter

  Public

  ROCm/aiter’s past year of commit activity
  AI Tensor Engine for ROCm

  Python

  •

  MIT License

  •522522 forks•544544 stars•286286 issues•603603 pull requests•Updated Aug 31, 2026Aug 31, 2026

• rocm-systems

  Public
  super repo for rocm systems projects

  C++

  •378378 forks•478478 stars•447447 issues•670670 pull requests•Updated Aug 31, 2026Aug 31, 2026

• rocm-libraries

  Public
  super repo for rocm libraries

  Assembly

  •392392 forks•415415 stars•548548 issues•618618 pull requests•Updated Aug 31, 2026Aug 31, 2026

• spur

  Public

  ROCm/spur’s past year of commit activity
  spur your compute

  Rust

  •

  Apache License 2.0

  •4444 forks•112112 stars•7676 issues•3737 pull requests•Updated Aug 31, 2026Aug 31, 2026

• mori

  Public
  Modular RDMA Interface

  C++

  •

  MIT License

  •8484 forks•174174 stars•2020 issues•4141 pull requests•Updated Aug 31, 2026Aug 31, 2026

• ATOM

  Public

  ROCm/ATOM’s past year of commit activity
  AiTer Optimized Model

  Python

  •

  MIT License

  •139139 forks•168168 stars•8888 issues•229229 pull requests•Updated Aug 31, 2026Aug 31, 2026

• aorta

  Public
  Python

  •

  MIT License

  •66 forks•1010 stars•2626 issues•5252 pull requests•Updated Aug 31, 2026Aug 31, 2026

• rocm-aic

  Public
  ROCm AMD Infinity Context - a distributed, shared, low-latency KV Cache tier for AI Infernence.

  aiamdinference+ 1

  aiamdinferencerocm

  Shell

  •

  MIT License

  •44 forks•1313 stars•55 issues•66 pull requests•Updated Aug 31, 2026Aug 31, 2026

• xla

  Public

  ROCm/xla’s past year of commit activity
  A machine learning compiler for GPUs, CPUs, and ML accelerators

  Python

  •917917 forks•1212 stars•33 issues•153153 pull requests•Updated Aug 31, 2026Aug 31, 2026

• FBGEMM

  Public
  FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/

  C++

  •

  Other

  •778778 forks•11 star•00 issues•1111 pull requests•Updated Aug 31, 2026Aug 31, 2026

• vllm

  Public

  ROCm/vllm’s past year of commit activity
  A high-throughput and memory-efficient inference and serving engine for LLMs

  Python

  •

  Apache License 2.0

  •21k21k forks•123123 stars•22 issues•3838 pull requests•Updated Aug 31, 2026Aug 31, 2026

• Quartz

  Public
  Central CI/CD Data Hub for the ROCm Ecosystem

  Python

  •

  MIT License

  •11 fork•11 star•2626 issues•66 pull requests•Updated Aug 31, 2026Aug 31, 2026

• hip-ep

  Public
  ROCm Execution Provider for ONNX Runtime on AMD GPUs. Compiles ONNX models through MLIR to LLVM bitcode, JIT-loads them at session creation, and dispatches to h…

  C++

  •

  MIT License

  •1515 forks•33 stars•1313 issues•105105 pull requests•Updated Aug 31, 2026Aug 31, 2026

• rocm-cli

  Public

  ROCm/rocm-cli’s past year of commit activity
  ROCm CLI is a command-line tool for setting up and running local AI on AMD GPUs, with a full-screen TUI dashboard for GPU telemetry, model serving, and chat.

  Rust

  •

  MIT License

  •66 forks•3131 stars•3030 issues•4545 pull requests•Updated Aug 31, 2026Aug 31, 2026

• composable_kernel

  Public
  [DEPRECATED] Moved to ROCm/rocm-libraries repo. NOTE: develop branch is maintained as a read-only mirror

  C++

  •

  Other

  •312312 forks•545545 stars•66 issues•77 pull requests•Updated Aug 31, 2026Aug 31, 2026

• TheRock

  Public

  ROCm/TheRock’s past year of commit activity
  The HIP Environment and ROCm Kit - A lightweight open source build system for HIP and ROCm

  Python

  •

  MIT License

  •315315 forks•1.3k1.3k stars•689689 issues•474474 pull requests•Updated Aug 31, 2026Aug 31, 2026

• rocmlirTriton

  Public
  MLIR kernel generator for AMD GPUs (GEMM, conv, attention, fused), built on a Triton compilation backend.

  llvmtritonmlir+ 1

  llvmtritonmlirkernel-generation

  MLIR

  •

  Other

  •11 fork•66 stars•00 issues•3434 pull requests•Updated Aug 31, 2026Aug 31, 2026

• rocminfo

  Public
  [DEPRECATED] Moved to ROCm/rocm-systems repo

  C++

  •

  Other

  •3232 forks•4343 stars•00 issues•33 pull requests•Updated Aug 31, 2026Aug 31, 2026

• rocm-spack-packages

  Public
  Spack's community package recipes

  Python

  •

  Apache License 2.0

  •737737 forks•00 stars•00 issues•1010 pull requests•Updated Aug 31, 2026Aug 31, 2026

• TransferBench

  Public

  ROCm/TransferBench’s past year of commit activity
  TransferBench is a utility capable of benchmarking simultaneous copies between user-specified devices (CPUs/GPUs)

  C++

  •

  MIT License

  •2929 forks•7777 stars•11 issue•1212 pull requests•Updated Aug 31, 2026Aug 31, 2026

• hrx-system

  Public

  ROCm/hrx-system’s past year of commit activity
  HRX: Hip Runtime Extended

  C

  •

  Apache License 2.0

  •1818 forks•2626 stars•2020 issues•2828 pull requests•Updated Aug 31, 2026Aug 31, 2026

• cvs

  Public

  ROCm/cvs’s past year of commit activity
  Python

  •

  MIT License

  •1515 forks•1717 stars•55 issues•5858 pull requests•Updated Aug 31, 2026Aug 31, 2026

• 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+ 15

  cpucomputer-visionhpcamdgpuopenclhistogramcontrastbitwisehip+ 8

  C++

  •

  MIT License

  •5555 forks•7373 stars•55 issues•11 pull request•Updated Aug 31, 2026Aug 31, 2026

• rocm-tests

  Public
  A pytest based system test framework that validates the full AMD ROCm stack across diverse environments.

  Python

  •

  MIT License

  •22 forks•44 stars•00 issues•2020 pull requests•Updated Aug 31, 2026Aug 31, 2026

• Megatron-LM

  Public
  Ongoing research training transformer models at scale

  Python

  •

  Other

  •4.4k4.4k forks•4343 stars•00 issues•99 pull requests•Updated Aug 31, 2026Aug 31, 2026

• TransformerEngine

  Public

  ROCm/TransformerEngine’s past year of commit activity
  Python

  •

  Other

  •3838 forks•7676 stars•88 issues•5555 pull requests•Updated Aug 31, 2026Aug 31, 2026

• hipBLASLt

  Public

  ROCm/hipBLASLt’s past year of commit activity
  [DEPRECATED] Moved to ROCm/rocm-libraries repo

  machine-learningamdassembly+ 6

  machine-learningamdassemblymatrix-multiplicationblashipgpu-computinggemmrocm

  Assembly

  •

  MIT License

  •147147 forks•114114 stars•11 issue•3636 pull requests•Updated Aug 31, 2026Aug 31, 2026

• gfx950-gluon-tutorials

  Public
  A practical guide to high-performance gluon kernel development on AMD GFX9 GPUs.

  Python

  •

  MIT License

  •55 forks•4545 stars•66 issues•11 pull request•Updated Aug 31, 2026Aug 31, 2026