Hardware-aware AI model optimization for AMD MI300X. 7-phase pipeline: architecture search, distillation, pruning, quantization, benchmarking, Pareto...
Planner and portable GEMM fallback for the AMD XDNA GPT-2 NPU offload design
AMD Synology NAS temperature JSON API for ESP32/M5Dial: CPU, board, and disk temps verified against DSM.
Cross-framework A2A purchasing demo on AMD Instinct GPUs: Google ADK concierge + CrewAI agent on vLLM + LangGraph agent on Ollama (local Llama 3.1), G...
The faster way to update, downgrade or reinstall your drivers and AMD Software. Additionally with support for Windows Server.
GGUF Model Manager for llama-swap — browse HuggingFace, download and manage GGUF models in one place.
Local autonomous coding agent stack for AMD RX 6700 XT (RDNA2): OpenCode + LM Studio Vulkan + Gemma 4 E4B Q6_K + oh-my-opencode. Bypasses Ollama Vulka...
Automated scheduler for PBO2 Ryzen Tuner
Experiments, notes, and benchmarks for AMD Ryzen AI (Krackan Point NPU + Radeon iGPU) on Linux
Web app for age-related macular degeneration (AMD) detection from retinal fundus images, with image quality assessment and Grad-CAM visual explanation...
Fix for AMD XDNA NPU driver on Ryzen AI 300 (Strix Point/Halo) — SMU init bypass patch, systemd auto-loader, full root cause analysis
White paper & reproducible benchmark suite for LLM inference optimization on AMD MI300X using ROCm 6.1
MIOpen research for AMD RDNA 3.5 (gfx1150) — whitelist patch and three-bug analysis for Strix Point APU training
Desktop notifications for P-Mode hardware button on GMKtec mini PCs (Sixunited AXB35-02 boards)
Stream music in your browser with a self-hosted Telegram bot that works without Telegram, offering easy access and control over your audio playback.
Complete guide + scripts for training HunyuanVideo 1.5 I2V LoRAs on AMD GPUs (ROCm). Battle-tested on RX 9700 XT.
A ray intersection acceleration library for heterogeneous hardware and software systems That Used AMD developed RadeonRays to help developers make the...
Run Ollama with AMD GPU on Windows -- WSL2, Vulkan, Docker methods. RX 5000/6000/7000/9000 series. The guide that should exist but doesn't.
installs OpenCL.dll into system32 to fix AMD error
Single-precision GEMM in ROCm
A purpose-built PC tailored for an engineering student, prioritising performance and functionality while maintaining a clean aesthetic, with component...
Auto-detect AMD GPU for PyTorch — ROCm, DirectML, CUDA, MPS, CPU. Fixes gfx1010 (RX 5700 XT) HSA_OVERRIDE_GFX_VERSION automatically. Windows/Linux/mac...
Monitoring app shown important rocm-related metrics in a browser window. Provides /metrics endpoint
Get amd pve vbios on linux
Run a private, offline AI on your own hardware with AnythingLLM and an AMD GPU
My Nixos Configurations.
Projects for the Nexys A7 FPGA development board
Setup guide for running Qubic QLI on AMD GPUs with Ubuntu 22.04.
Detect on-chain token dumps by project teams early using AI-driven analysis and Binance Web3 API data for informed investment decisions.
Sentinel: Privacy-First On-Device AI Retail Companion
Universal GPU setup for PyTorch and JAX — DirectML, ROCm, CUDA, MPS, CPU. Auto-detects hardware, fixes HSA_OVERRIDE_GFX_VERSION for AMD RX 5700 XT. Be...
Even on a system with a AMD GPU the blacklisting can prevent the GPU driver from loading at boot. This script fixes that.
Demo to showcase Strix Halo memory QoS under concurrent AI + CPU workloads (Ollama + CMake + Python).
Real-time monitoring for AMD Instinct GPUs. Prometheus metrics and Kubernetes-native.
A terminal-based system resource monitor written in Rust — fast, readable, and GPU-aware. Named after the reforged sword of Aragorn, narsil is built t...
Spark with AMD GPU with ROCm library
Kernel from source customised for my hardware
🚀 Build and explore OpenAI's GPT-OSS model from scratch in Python, unlocking the mechanics of large language models.
Automatically restarts AMD Adrenalin when a game launches. Stops AMD services and processes, then relaunches Adrenalin to fix overlay, performance, an...
Tutorials workstation for MD.
GPU monitoring library for AI inference systems: utilization tracking, bottleneck analysis, and scheduling signals.
Hardware-attested relay for AgentVault — AMD SEV-SNP confidential VM execution
Thuck U Nvidia :(
🧵 Enhance string handling in Go with a Laravel-inspired toolkit, offering rune-safe helpers and expressive transformations beyond the standard librar...
AI-powered image editor with InstructPix2Pix. Modern glassmorphism UI, AMD DirectML support, batch generation, and more.
Building a robust industrial SBC platform starts with two critical decisions: choosing the right CPU architecture and ensuring the system can operate...
Flake that provides an easy way to tweak the power consumption of your Ryzen CPU
finetune models with AMD navi cards like 7700/7800/7900XT
This project implements a LSTM (Long Short-Term Memory) model to predict stock prices of AAPL (Apple Inc.) and AMD (Advanced Micro Devices) using hist...