Here is dashboard about CGI and our blog...
A Babel plugin to make re-export modules more compact
Whisper ASR on the AMD Ryzen AI NPU — zero-dependency Bash wrapper over FastFlowLM, plus a RAPL power/latency benchmark harness. RTF ≈ 0.17.
Fixes Wan2GP on AMD systems where the integrated GPU takes device 0: wrong VRAM readout, HIP invalid device function, and the CUDA-instead-of-ROCm tor...
AM5 DDR5 SPD hub diagnostics collection for ghost DIMM
Практичный и безопасный гайд по оптимизации Windows 11 и игрового ПК: BIOS, драйверы, GPU, PowerShell, диагностика и стабильность.
Fresh-host qualified AMD ROCm 7.2 / RDNA4 gfx1201 port and public installer for 2D Gaussian Splatting (2DGS), verified on Radeon AI PRO R9700.
AMD consumer/eGPU local-AI benchmarks: measured configs, negative results, and the footguns nobody documents
Warcraft-faction-themed GPU driver updater for Windows - checks NVIDIA, AMD and Intel for new drivers, downloads from vendor servers, slim driver-only...
Local-first multi-agent orchestrator for AMD APU. Multi-agent pipeline, GBNF constrained decoding, asymmetric KV quantization, Wasmtime sandbox — all...
AMD ROCm & NVIDIA CUDA GPU-accelerated manga upscaling
Lightweight ROCm inference toolkit for AMD GPUs — FP16/INT8 quantization, batch processing, benchmarking, HuggingFace integration
Multi-agent fine-tuning pipeline for Indonesian LLMs on AMD Instinct MI300X with ROCm
Text-to-PBR material generator on AMD GPU (ROCm + SDXL) with live Three.js preview
Measured energy cost of on-prem LLM inference on AMD ROCm: 8.7× tokens-per-joule from batching, with a cost-governance gateway and agent built on the...
AMD ROCm/RDNA4 and CUDA/Blackwell 3D-AI porting portfolio.
An unofficial interactive 3D atlas of AMD's compute portfolio - open any product, pull it apart layer by layer, and keep going: into a compute die, an...
Private Agentic Evidence Investigator for Time-Coded Media Archives on AMD Radeon/ROCm
Automated PowerShell utility designed to fix AMD GPU stutters, black screens, and stability issues on Windows by configuring ULPS, MPO, and TDR settin...
Production-grade HIP kernel optimization lab — matrix ops, reductions, shared memory patterns
vLLM on ROCm 7.2.2 for AMD Strix Halo (gfx1151): source-build recipe, upstream patches, environment lockfile, systemd unit — and both the failed ROCm...
Enterprise AI Operations Copilot with Explainable Hybrid AI Routing optimized for AMD AI PCs.
AI orchestration for Portuguese-speaking healthcare: routes medical conversations between local and cloud LLMs, cutting inference cost ~84% while pres...
Turn-based geopolitical simulator where 5 AI civilizations — militarist, mercantile, theocratic, democratic, and authoritarian — reason via LLM (Llama...
System tuner with hardware-aware profiles
Lightweight web dashboard for live CPU, memory (per-DIMM), and GPU temperature & usage monitoring on Linux — no build, runs offline.
Collection of optimized ROCm HIP kernels for matrix operations on AMD GPUs
Custom HIP/ROCm kernel examples — matrix ops, attention, flash-attention optimized for AMD CDNA architecture
GemmaRoute frontend — Next.js 16 chat interface and live metrics dashboard for the 4-layer AI routing engine. Pulsing live indicator, tier badges, cos...
Lightweight Linux terminal monitor for CPU, memory, GPU, VRAM, and temperature metrics.
Meridian — An AI-first project management platform featuring a serverless architecture powered by React and an AMD MI300X Inference Endpoint.
Trismegistus AMD ACT III AI Expert Partner with Mirror Architecture, Gemma/Fireworks lanes, receipts, and AMD Cloud proof path
Production-oriented Docker Compose stack serving openai/gpt-oss-20b via vLLM on AMD Strix Halo (gfx1151, ROCm 7.2). OpenAI Responses API, host-mounted...
Local speech-to-text toolkit for Arch Linux. Transcribes audio/video to clean Markdown via whisper.cpp (Vulkan/RADV). CLI-first: local files, YouTube,...
Automatic RealESRGAN and Real-CUGAN installer and video upscaling framework with NVIDIA, AMD, Intel and Vulkan support.
Bilingual EN/ES root cause, diagnosis, and safe repair for AMD LoadLibrary error 87 after switching from NVIDIA.
Interactive demo showing agent memory poisoning attacks and a trust-partitioned defense using provenance-aware memory.
High-throughput LLM inference engine optimized for AMD Instinct MI300X GPUs
ESLint plugin for JavaScript AMD module syntax.
This repository contains information on running a virtual machine with GPU passthrough for systems with a single AMD GPU.
Autonomous Legal Operating System with model-driven matter setup & high-fidelity ONLYOFFICE/MS Word ribbon editor
AMD Chipset Drivers 6.02.07.2300 Latest Secure Toolkit 2026
PRL token mining on AMD GPU — alpha-miner setup, pool monitoring, hashrate optimization for MI300X
Open-source LLM inference benchmarking toolkit for AMD Instinct MI300X GPUs — ROCm, vLLM, PyTorch
A professional-grade, stateful provisioning system for building high-performance AMD GPU-accelerated DevSecOps labs on Linux. Optimized for AMD hardwa...
The files I had to download from baidu for a FPGA board from "black hawk technologies"
Span-cited English investor memos from Japanese 有価証券報告書, produced by a 14B nekomata-qfin fine-tune on a single AMD Instinct MI300X.
AMD Chipset Drivers 2026 Download | Latest Setup Installer | Full Version Pro | Premium Loader Mod | Latest Build Updated | Get Desktop Windows 10/11...
Community port of NVlabs/tiny-cuda-nn for AMD RDNA4 / gfx1201, validated on Radeon AI PRO R9700 with ROCm 7.2.