Free, open-source PC gaming optimizer for Windows. Every setting is measured on your real matches, kept if it helps, rolled back if not.
One open-source platform to schedule, serve, benchmark and observe LLMs on NVIDIA and AMD GPUs (Run:ai, Dynamo, AIPerf)
llama.cpp fork: Qwen3.8-Flash-Next at 1M context on AMD Strix Halo (Ryzen AI Max+ 395), Vulkan
Free one-click installer for local AI music (YuE2) on Windows PCs with AMD graphics
Independent EXL3/QTIP trellis-quantization inference library for AMD Strix Halo (gfx1151): CPU reference, HIP decode kernels and a C ABI. Developed an...
Waybar power-mode controller for Ryzen/Radeon on MangoWM (Eco/Balanced/Max)
GUI builder for the classic PC edition of Resident Evil 1 - applies the community HD texture, audio, FMV and engine mod archives to your disc image an...
AMD Radeon Cloud multi-key rotation plugin for DeepSeek Harness
Virtual Greenscreen R9700 Broadcast Studio: AI green screen, background blur and virtual camera for AMD Radeon AI PRO R9700 (ROCm, Linux)
Live, translated subtitles for anything playing on your PC - fully local. Confucius4-R2T2 speech recognition + LLM translation in a click-through over...
Restore, test, and use both AMD FirePro GPUs in the 2013 Mac Pro on Linux. I made this for Omarchy Linux. running on the "Trash Can" Mac Pro.
Community validation and upstreaming workspace for SGLang NVFP4 on AMD CDNA3 and RDNA4.
🟠 Gara Facile · Public tenders, made easy. Finds EU tenders that fit your company, reads the 100-page PDF and shows where you meet or miss every requ...
Type-2 SVM Hypervisor for Windows with NPT Split-page hooking
A hypervisor you bring yourself, for x86 hosts that do not have one. NVMM on macOS for AMD processors, with a tiny VMM that runs Docker.
Gestion CPU pour ROTK / Z1BR · CPU management for ROTK / Z1BR
Milvus GPU ANN on AMD ROCm (HIP)
Trust-gated maintenance assistant: a nightly gate on one AMD Instinct MI300X measures what robot telemetry can support, and gpt-oss-120b answers only...
Run official Qwen3-TTS on AMD Ryzen AI / Radeon with ROCm — zero upstream patches, one-command setup, voice cloning & voice design.
Hi3DGen / Stable3DGen runner for AMD Strix Halo (gfx1151) on Windows ROCm. Pure-torch replacements for spconv and xformers.
YMM4向けAMD Radeon AMF H.264/HEVCハードウェア動画出力プラグイン
openPangu Flash92 — C++/CUDA & C++/HIP ROCm Engines. Fully resident, Blackwell tensor cores, no Python. Powered by openPangu.
System monitor that reports real GPU memory on unified-memory AMD parts (Strix Halo / Ryzen AI Max), where other tools show only the firmware carve-ou...
Self-hosted AI image and video generation for AMD Ryzen AI APUs on Linux: Vulkan (Mesa RADV) via stable-diffusion.cpp, no ROCm. Web UI with queue, mod...
DLSS 5 on AMD — even in games that never had DirectX 12. Built and first tested on Radeon RX 7600 with GTA San Andreas.
Lightweight filter program that allows you to create, save and load custom filters
Analyse any text or ebook on 82 calibrated dimensions (genre, mood, themes, style) with the Laya model — ~1 s per page on Strix Halo with ROCm 10. Mod...
Qwen3.8-27B EXL3 on AMD gfx1201: RX 9070 XT (16 GB, tested) and Radeon AI PRO R9700 (32 GB). vLLM plugin with custom kernels: ~80 tok/s with MTP specu...
Get internal audio (TAS2783 speakers + RT712 mic on AMD SoundWire) working on the HP OmniBook X Flip 14 (board 8EA1) under Linux
Lightweight Windows systray utility for AMD Radeon GPU fan control (core-temp target curve, .NET Framework 4.8, no admin)
Reproducible AMD ROCm reference for Qwen3.8-27B (gfx1151 validated): vLLM + llama.cpp dual-path, 20-cell benchmark matrix, UX-first verdicts
See exactly where your LM Studio model weights & KV-cache live — GPU (VRAM) or system RAM. Real per-process measurement, GGUF-aware KV math (GQA/MLA/S...
Whisper encoder on the AMD XDNA1 NPU (Ryzen AI, Phoenix) under Linux — open toolchain only: XRT, MLIR-AIE/IRON, peano. Includes an HTTP service speaki...
Reproducible Windows ROCm deployment kit + validated ComfyUI workflows for AMD RX 9070 XT. No GPU required to verify.
PowerShell tool for reading, enabling, or disabling AMD Core Performance Boost in BIOS on supported HP commercial PCs using HPCMSL. Includes real-worl...
A lightweight Windows batch script that disables optional AMD background services, scheduled tasks, startup entries, and processes, then verifies thei...
Lightweight terminal dashboards for monitoring ComfyUI on Ubuntu with AMD ROCm or NVIDIA CUDA GPUs. Tracks VRAM, system RAM, ComfyUI RSS and swap, mem...
Comparative benchmark of 4 LLM inference engines (HuggingFace, vLLM, AWQ, Speculative Decoding) on AMD GPU. Streamlit dashboard with real-time GPU tel...
LingChat 内置 IndexTTS 的 Windows AMD ROCm 运行时与官方模型安装器
[BETA] CLI utility for reading, dumping, comparing and analyzing AMD Polaris (RX 400/500) VBIOS ROMs. Parses real AtomBIOS structures - and outputs pl...
TUI PCI register viewer — scan GPU devices, read config space, mmap BAR registers (NVIDIA/AMD/Intel)
Reproducible TRELLIS.2 INT8 ConvRot patches for ComfyUI on AMD ROCm gfx1100
Легковесная идиоматичная системная утилита на Rust для тонкого управления питанием, лимитами и частотами процессоров AMD Ryzen (архитектура **Zen 4 /...
Open, reproducible AMD XDNA1 + Strix Point XDNA2 compute on Linux: pinned builds, CPU-reference checks, persistent C/Python runners, and an LLM roadma...
GPU-accelerated stem separation deck for DJs - Tauri + Demucs/BS-Roformer on AMD ROCm for Windows. Drop a track, pull acapellas, drums, bass & synths...
llama-swap config for MTP speculative decoding on AMD RX 7900 XTX (ROCm). Qwen3.6-35B-A3B-MTP and Gemma 4 26B-A4B-MTP with VRAM-tuned context sizing.
HIPIFY-first AI agent for CUDA2ROCm migration, compiled and test-verified on AMD MI300X with Gemma 4.
Single-file bash system dashboard for Linux workstations. Hardware telemetry, containers, process management, security audit -> zero cloud depe...
Voxen: Assembly-Aware CAD Generation System Powered by Fine-Tuned Qwen3-8B on AMD MI300X
Windows-native MCP server for local audio transcription — GPU accelerated via Vulkan, works with Claude Desktop