Run PyTorch natively on Windows 11 with an AMD RX 9070 XT (RDNA4 / gfx1201) on stable ROCm 7.2.1 — no WSL2, no Linux, no ZLUDA. Exact pinned wheel URL...
RNS8 explores exact integer matrix multiplication on AMD GPU matrix engines.
One-click Linux and WSL2 installer for ComfyUI with auto NVIDIA CUDA / AMD ROCm GPU detection, latest PyTorch setup, and launch script creation.
Connect local tools, databases, and LLMs through a desktop interface for Windows, Linux, and macOS.
Install AMD consumer Ryzen chipset, Radeon graphics, Ryzen AI NPU (XDNA), and the Microsoft inbox Bluetooth PAN driver on Windows Server 2016/2019/202...
Tools for AI/ML Workload Analysis and Characterization
Community-curated guides, benchmarks, and compatibility notes for running LLMs on AMD hardware with ROCm, Vulkan, llama.cpp, vLLM, Ollama, and PyTorch...
Vulkan compute backend for PyTorch — runs on any GPU. PrivateUse1 dispatch, SPIR-V shaders, zero ROCm/CUDA dependency.
⚡ Tu estudio multimedia con IA, entero en tu máquina — reescalado, restauración de audio, karaoke, transcripción, doblaje, generación de imagen/video...
μMCX - GPU-accelerated 3D Monte Carlo photon simulator in less than 1000 lines
🚀 Run 120B AI Models on Spark 2026 - vLLM API & Coding Assistant
llama.cpp HIP vs Vulkan benchmark on AMD Strix Halo (gfx1151) with ROCm 7.2.2 — Ubuntu 26.04
Safe, reversible Linux CPU performance profiles across CPUFreq, intel_pstate, amd-pstate, cpuidle, thermal, hwmon, and future Intel/AMD/ARM backends.
Inference scaling benchmark of Qwen3.5-2B on AMD Instinct MI300X using ROCm and Hugging Face Transformers.
Dungeon Stomp is a dungeon crawler running on DirectX12 Ultimate using DXR
Docker infrastructure for AMD Strix Halo (RDNA 3.5 / gfx1151): PyTorch + ROCm base container and a separate Ollama LLM service. Two folders, two Compo...
Advanced benchmark harness for AI agent inference workloads on AMD GPU and ROCm cloud infrastructure
Wayfinder: Hybrid Token-Efficient Routing Agent for AMD Developer Hackathon ACT II
AMD port of Intel BITS' SMI latency test: real SMI counting via PMC event 0x2B, xHCI BIOS/OS handoff, and FCH SMI source decoding. Four Python files,...
System monitor for Linux AMD CPU + GPU systems
ROCm-first OpenAI-compatible inference gateway for open-weight reasoning models. Single active profile (gpt-oss-20b, deepseek-r1-distill, qwen3-4b), h...
Fork of llama.cpp-mtp with Vulkan backend adaptation (RDNA3/RADV)
Everything you need to run AI/ML on AMD GPUs on Windows — master toolkit hub
⚠️ MIGRATED → https://github.com/bong-water-water-bong/1bit — monorepo
Run ComfyUI on AMD GPU (RDNA1-RDNA4) on Windows -- comfyui-rocm, AMD Portable, and DirectML. Tested on RX 5700 XT.
GPU driver detection and management tool for Fedora 44+
Agentic CUDA-to-ROCm migration loop - translates, compiles, profiles, and iteratively fixes GPU kernels with real hardware feedback.
Drop-in Ollama replacement for AMD RDNA 1 GPUs (RX 5500/5600/5700) using llama.cpp + Vulkan. No ROCm needed.
Local, ternary-weight LLM inference on AMD Strix Halo. Rust above the kernels, HIP below, zero Python at runtime. https://discord.gg/EhQgmNePg
Multi-GPU tensor/context parallel diffusion on AMD ROCm — with the patch that makes it actually work.
AI-assisted MCP server and Python SDK for AMD Vivado FPGA workflows
A curated list of awesome open source projects, tools, and resources for AMD GPUs via ROCm
Local Paperless-ngx + Ollama integration for AI-based document titles, correspondents, document types, tags, review workflows, and backfill.
ROCm nightly monolithic tarball packaged as a Nix flake (gfx1151)
Windows system tray for llama.cpp + ROCm. Optimized for AMD RYZEN AI MAX+ 395 / 8060S.
Working OpenCore EFI for MSI B850M-G Motherboard. Built for macOS Sequoia with AMD Ryzen 5 9600X (6-Core) and Radeon RX 570 GPU - Tahoe with RX 5500 X...
OpenAI-compatible embedding server built on pure ONNX Runtime—fast starts, tiny footprint, GPU/CPU with optional quantization
real-esrgan-ncnn-python image upscale GUI app. runs fast on intel / amd / Nvidia.
Production infrastructure scripts — ROCm setup, multi-GPU config, server hardening, LLM deployment automation
A bash script to automate running Open WebUI on Linux systems with Ollama and Cloudflare via Docker
Production-grade local LLM deployment stack — llama.cpp, Ollama, GGUF/GGML, ROCm AMD, 14B to 80B models
Visualize and monitor ROCm-SMI data locally or remotely via REST API — a more convenient alternative to rocm-smi.
RISC_V x32 enhanced for AI/ML Neural Networking and Signal Processing
Local LLM benchmarks on AMD Strix Halo — 26+ models tested across RADV, AMDVLK, and ROCm with llama.cpp
🌊 Stream enables real-time communications in Go with Server-Sent Events and WebSocket support, ensuring zero dependencies and production-readiness.
A simple bash script for changing the fan curve and other settings on the AMD RX 7900 XTX.
Guide on how to set up PBO using curve optimizer
AI-powered GPU mining optimizer with deep learning tuning, real-time profitability tracking, predictive coin switching, and automated hardware managem...
How I personally got vfio working using many different guides with months of failed attempts
Implementation of the AMD FidelityFX CAS (Contrast Adaptive Sharpening) algorithm on ROCm, for sharpening static images.