Popular GitHub Repositories for Rocm

A high-throughput and memory-efficient inference and serving engine for LLMs

Open deep learning compiler stack for cpu, gpu and specialized accelerators

A deep learning package for many-body potential energy representation and molecular dynamics

Large-scale LLM inference engine

Abstraction Library for Parallel Kernel Acceleration :llama:

AUTOMATIC1111/stable-diffusion-webui for CUDA and ROCm on NixOS

AMD OpenVX modules: such as, neural network inference, 360 video stitching, etc.

The Lightning plugin ecosystem provides fast quantum state-vector and tensor network simulators written in C++ for use with PennyLane.

AMD ROCm Installation Guide on RX 6600 XT + TensorFlow and PyTorch

ROCm Machine Learning and HPC Stack installer

A script that automatically installs all the required stuff to run selected AI interfaces on AMD Radeon 7900XTX.

llama.cpp + ROCm + llama-swap

A set of Dockerfiles for images that support Standard Diffusion on AMD 7900XTX Cards (gfx1100)

? Automated deployment stack for AMD MI300 GPUs with optimized ML/DL frameworks and HPC-ready configurations

"Hybrid quantum programming with PennyLane Lightning on HPC platforms" accompanying data and workloads

AMD iGPU AI Setup and Speed Test - GPD Pocket 4 - Linux + ROCm + Vulkan + AgentMake AI

同步AI开发常用的docker镜像到阿里云镜像仓库，便于在国内快速拉取镜像。如：pytorch

Docker image that packages AUTOMATIC1111/stable-diffusion-webui, preconfigured with dependencies to run on AMD Radeon GPUs.

Understanding GPU Architecture Implications on LLM Serving Workloads (Master Thesis, ETH Zürich, 2024)