Run LLMs and Ollama Qwen across AMD XDNA1 NPU, CPU, and GPU on Ryzen AI Linux systems.
GPU-accelerated neural network operations using Vulkan compute shaders.
🐱💻 GPU Info API is an API that provides detailed information about Nvidia, AMD, and Intel GPUs. The information is extracted from Wikipedia and sto...
PYNQ bindings for C and C++ to avoid requiring Python or Vitis to execute hardware acceleration.
Latest Bazzite Deck, GNOME, and KDE images for AMD BC-250 boards with cyan-skillfish-governor-smu, GPU frequency scaling, MangoHud/radeontop 655% tele...
AMD FidelityFX Super Resolution plugin for Flax Engine
Wake and Break: a PSP exploit for AMD navi31 (RX 7900) that makes the card accept unsigned IP firmware. Not persistent: a cold power cycle restores st...
Strata 0.2.3 (engine 0.1.48) for AMD gfx906 (MI50/MI60/Radeon VII): rocBLAS solution table, Qwen3.6/Ornith engine restored, DFlash2 build fix, web con...
One-click AI agent setup for NVIDIA DGX Spark, Jetson, and RTX hardware. OpenClaw + Ollama, fully local.
An open source implementation of an AMD-V Secure Loader.
ROCm Machine Learning and HPC Stack installer
Native macOS driver for AMD RDNA 3 GPUs (Navi 32 RX 7800 XT first): display, Vulkan (RADV) and Metal. Research prototype, contributors welcome.
Dominator est le cheat externe ultime pour Call of Duty: Warzone 4.0 (Saison 5)
Unlock and manage DLSS 5 on any NVIDIA or AMD graphics card. The ultimate one-click frame gen tool.
A working Comfy UI with AMD GPUs. Works with RDNA 3/3.5/4
A modern AMD GPU control panel for Linux, inspired by AMD Adrenalin on Windows.
DeepSeek-V4-Flash inference for AMD Strix Halo
Self-hosted LLM/RAG stack in one command — AMD Strix Halo / x86_64 (ROCm/Vulkan, Docker Compose)
In-browser Ryzen BIOS SMU version checker (AM4 & AM5) with ZIP support and Markdown export.
AMD iGPU AI Setup and Speed Test - GPD Pocket 4 - Linux + ROCm + Vulkan + AgentMake AI
Customizable D3.js choropleth map of Romania
Native Rust support for AMD Zynq 7000 SoC bare-metal programming
Universal Render Pipeline + Application SpaceWarp + Mobile Optimized 16-bit AMD FidelityFX™ Super Resolution 1.0.2 example project for Oculus Quest /...
A from-scratch Rust inference stack for AMD GPUs that talks straight to the Linux kernel driver. No ROCm, HIP, or HSA runtime. Serves OLMo 2 on MI355X...
[DEPRECATED] Moved to ROCm/rocm-systems repo
A "standard library" of Triton kernels.
Reclaiming the ASRock BC-250 as a real, tunable PC - Cachenetics' open-source firmware liberation + tuning suite.
A project repository for work on improving local LLMs on my personal AMD devices
A cross-platform GPU-accelerated physics engine with support for HIP/ROCm and HIP/CUDA.
whisper.cpp Windows binary w/ Vulkan GPU support
esl-hot-update: Hot update esl modules(AMD、CMD) when modifed. JS, LESS, tpl, component is all supported!
Configuration for on AMD
Makes Crimson Desert run on AMD Polaris (RX 470-590), which the game otherwise refuses to launch on. A D3D12 shim plus patched vkd3d-proton, with the...
Multi-seat game streaming on Linux: several people play on one PC at the same time, each in an isolated container with their own Sway, Sunshine and St...
LLM inference engine for AMD RDNA4 — Rust + Vulkan compute shaders, gguf & native FP8.
AMD SMU Reverse Engineering (for AMD BC-250)
Automated bottleneck detection and solution orchestration
Performance optimization guides for Bethesda games and more.
Example on how to use pytorch/yolov8 object detection on computers with AMD integrated GPUs
Retrieve current Solar PV data from the Solarman API and publish to mqtt
Declarative MVVM Web Engine based on HTML 5, CSS 3, ECMAScript 5, AMD specification & jQuery API
AMD Package Manager, APM Package Manager
Ensure that a system-compatible OpenGL driver is available for `nix-shell`-encapsulated programs.
Fast vLLM on AMD Strix Halo: one docker command for Qwen, Gemma, LFM and more, up to 31x faster prefill and ~2x decode vs stock vLLM at long context.
Qwen3.8-27B EXL3 + DFlash2 speculative decoding on an AMD RX 7900 XTX (exllamav3-rocm): recipe, patches, benchmarks
OptiScaler ILION — Community fork with bilingual ES/EN interface, FSR 4 version switching, live performance metrics and benchmarking tools.
Tensor-parallel DeepSeek V4 Flash inference on dual AMD Strix Halo over OdinLink USB4/TB5 RDMA or Mellanox RoCE v2.
Browser-based operator console for managing and monitoring Lemonade on Linux inference servers.
GPU monitor for Linux terminal supporting single or multiple gpu's in realtime
OpenCore configuration to run macOS on Lenovo Legion 5 laptops.