A turnkey, fully-local AI workstation engineered for the AMD Ryzen AI Max+ 395. LLM inference, voice, document parsing, browser automation, agents — a...
Install Dual Monitor Fix via PowerShell — repair second monitor not detected, wrong resolution and extended display issues on Windows 10/11.
🐆 Self-hosted AI workstation stack for @amd
Automatically re-enable your eGPU after hot-plugging on Windows Never manually enable your eGPU from Device Manager again! This tool monitors your ex...
Ultra-high-performance GPU-accelerated text search using Metal compute shaders
The GPT-Fast for Multimodal Models on AMD GPUs
🖥️ AMD Ryzen Chipset Auto Update Utility
Hydra is a RHI which utilizes both Vulkan and DirectX 12 to deliver high-performance graphics and efficient resource management.
CPU clock speed monitor for Linux
Voice-to-voice LLM conversation, Full-local
a tiny docker container for running xmrig-mo
Logic Analyzer IP Core
Fixes: Not able to connect Android Device to ADB and Fastboot
Dynamic schedule management framework for soft-real-time jobs on GPU based architectures
This opencore efi for amd 15h/16. Tested on Catalina 10.15.4, amd fx6300, nvidia gt730. Only for educational purposes.
Unofficial Ryzen Master Bindings for C#
BASH script to toggle between CPU powersave and performance mode in Linux
Python Miner manager for linux
convert es6 to amd
AMD define factory patcher webpack loader.
Uses AST to extract AMD modules, their parts and an optimized output without unused dependencies while keeping the original format.
A styleguide for AngularJS using asynchronous module definition
An Ethereum miner project that auto-discovers GPUs (AMD or NVIDIA) and then runs ethminer. Also provides a metrics solution to monitor the health of m...
Exactness-first batch-1 LLM inference engine for Qwen3.8-27B on AMD MI300X (Rust + HIP)
Plug-and-play eGPU for SteamOS handhelds: auto-switch Game Mode, per-GPU shader caches, safe disconnect. Decky plugin + Desktop app.
Flash a Chinese RX 580 2048SP (8GB, 1002:6FDF) to RX 570 so it works as a native Metal eGPU on Intel Macs. Four bytes, no kexts.
OpenCore EFI and driver status for TongFang AMD Ryzen 7 7840HS + Radeon 780M Hackintosh (macOS 26). SMBIOS credentials removed.
OpenBook: the Googlebook desktop experience as an open operating system for x86_64 laptops, built from AOSP 17, Google's GKI kernel and open drivers (...
Magpie + ReShade dual-runtime neural rendering: lmxxf (HIP) / mochizuki (Vulkan), picked by the Magpie effect group, plus an input bridge that makes t...
Native macOS Wi-Fi 6 driver for MediaTek MT7922 (AMD RZ616): 802.11ax, 2x2, 160 MHz. macOS Sequoia 15.8.1 and Tahoe 26.7.2, OpenCore. Bluetooth setup...
Finite Element Material - AMD Developed Physics Simulation.
Usability benchmark for local LLMs on AMD hardware (RDNA4 + Strix Halo) — agentic throughput, self-repair counts and context-depth decay, all parsed f...
MiniMax H3 video and audio generation on AMD Strix Halo, powered by Loom and HRX.
playtest-graded benchmark for local LLM stacks: a 10-file game build, 19 static checks, a runtime soak, and a human playing it
Measured LLM benchmarks for AMD Strix Halo / Ryzen AI Max+ 395 (Radeon 8060S, 128 GB unified): llama.cpp Vulkan & ROCm — decode pace, TTFA, prompt cac...
Run llama.cpp across two GPUs of different vendors at once (AMD ROCm/HIP or Vulkan + NVIDIA CUDA) in one llama-server process, no RPC server. Windows...
General RDMA transport between two Strix Halo hosts over Thunderbolt/USB4 NHI DMA rings: a native software-verbs provider with a zero-copy data plane,...
Open-source GPU miner with no dev fee. Currently supporting Autolykos2 (Ergo), built to add more algorithms. AMD via Vulkan compute — the first known...
Device-native Qwen3-TTS inference for AMD RX 7900 XTX and NVIDIA RTX 4090 with explicit HIP/CUDA kernels, streaming and Resident execution.
Monitor CPU temperature in the system tray with audio alerts on overheat. Shows per-core temps and logs history to CSV. Under 5 MB RAM usage - always
The face swap that tells you how good it is. Open-source face swap for photos, video and webcam with built-in identity + sharpness scores. Runs locall...
Optimized dual AMD Strix Halo (gfx1151) vLLM MoE inference: TP=2 over USB4, tuned int4 MoE kernel, ~8us interconnect, serialized serving
lightweight Windows gaming optimizer with GPU vendor themes, preset system, and safe system tweaks.
Drop-in amdsmi for AMD GPUs on WSL2 (DirectX/dxgkrnl passthrough) where the native amdsmi is unavailable — unblocks vLLM, PyTorch ROCm, GPU monitoring...
Optimized vLLM setup for Gemma 4 31B NVFP4 with MTP on dual RTX PRO 6000 Blackwell using vllm and docker: native FP4 Tensor Cores, Multi-Token Predi...
Fine-tune your own LLM on an AMD Radeon GPU — the easy, tested way. QLoRA via ROCm on Windows/WSL2 & Linux, a worked Gemma-4 example, a reusable live...
Claude Code skill for AMD Strix Halo (Ryzen AI MAX+ 395) ML setup. Handles PyTorch installation (official wheels don't work with gfx1151), GTT memory...
AMD GPU status monitor web panel written in Go using LLMs
CUDA support on AMD GPUs using HIP and ROCm run and test CUDA-style code natively on AMD hardware.