Tune and monitor the ASRock BC-250 from Steam Game Mode — 8-core unlock, UMA/VRAM control, per-game fixes. A Decky Loader plugin for Bazzite and Steam...
Run Gemma-4-31B at full 256K context on a $1,400 AMD RDNA4 GPU (gfx1201): TurboQuant KV cache + HIP-graph-safe Flash-Attention for llama.cpp, fully me...
Whisper-large-v3 fine-tune for Indonesian + Javanese + Sundanese ASR. Lhotse + k2 lattice rescoring pipeline.
Multimodal document QA: vision + retrieval over PDFs (LLaVA + LlamaIndex)
AI/ML research project on AMD ROCm
Tools and documentation related to the AMD Strix-Halo AGU family (Ryzen AI Max 395) of systems. Tested on GMKtec EVO-2
A toolkit for accessing RAMs SPD. Primarily used for reading temperature and data from SPD.
Tool for fixing monitor black crush and gamma manually. Auto-switch gamma profiles for HDR and SDR.
One-click AI agent setup for NVIDIA DGX Spark, Jetson, and RTX hardware. OpenClaw + Ollama, fully local.
AmdRyzenMaster PrivateCHEAT LEAKED
A CUDA renderer for the Buddhabrot fractal
Modular Graphical Simulator for Teaching Microprogramming
GameNative-x64 (GameNativeX64 / GameNative x86): native x86_64 GameNative for Intel and AMD Android, Googlebook, Bliss OS and Android-x86 - Steam, Epi...
AION 2 graphics settings reference for Windows: quality profiles, visual settings checklists and FPS comparison workflow.
Windows utility for Castlevania: Belmont's Curse focused on gpu driver, driver crash, and graphics stability.
Multi-GPU tensor-parallel vLLM on AMD Radeon RX 7900 XT / XTX / GRE (7900XT, 7900XTX, RX7900XT, gfx1100, RDNA3, ROCm): root cause and fix for the RCCL...
Run Tencent's Hunyuan3D 2.1 image-to-3D model without CUDA — natively on Apple Silicon (MPS) and AMD GPUs (ROCm), now with PBR texturing
Adjust power management settings for Ryzen CPUs on Linux, Windows, and macOS
Decky Loader plugin for SteamOS eGPU display switching. Tested on Lenovo Legion Go S + AMD RX 9070 eGPU + ASMedia USB4 setup.
Indonesian news summarization with IndoBART / mT5 (headline + paragraph summary).
A TurboQuant implementation with Llama.cpp for AMD with Vulkan runtime
Easy guides to set up and test TEEs: SGX, TrustZone, CCA, TDX, AMD SEV-SNP, PMP
AMD 5600g hackintosh
C++ wrapper for the Nvidia/HIP C libraries (e.g. CUDA driver, nvrtc, hiprtc, cuFFT, hipFFT, etc.)
Docker images for Stable Diffusion WebUI (AUTOMATIC1111) for AMD Radeon RX5500XT and similar boards
AST helpers for recognizing CommonJS, AMD, and ES6 module types
The repo is obsolete. Use at your own risk.
An Instant Replay/ReLive-like program for Linux
llama.cpp fork for GSQ-quantized Qwen3.8-Flash-Next on AMD Strix Halo (gfx1151): faster ROCm prefill, MTP and 4×256K chats with Q8_0 KV and one KV str...
Adaptive Disaggregated Inference on a Role-free Fleet!
The newcomer's bible for the ASRock AMD BC-250 — a PS5-derived APU board turned into a budget Linux gaming & AI mini PC. 15 languages.
Experimental Windows 7 local-segment scanout fix for Renoir/Lucienne AMD APUs
ROCmFPX llama.cpp fork for Windows 🏆 — native build, headless OpenAI-compatible server & benchmarks. Tested on AMD Strix Halo (gfx1151), runs on othe...
Fix internal speakers on the ASUS ProArt PX13 (HN7306, Strix Halo) under Linux: TAS2783 firmware + ALSA UCM Speaker profile + ACP/SoundWire reset for...
Windows platform manager for ephemeral ComfyUI+ROCm instances optimized for AMD GPUs via PowerShell.
Xian-VL monorepo - Multilingual Assistant for Gaming Environments 🧙♂️ and other AI translation/research tools. Powered by Lemonade. 🍋
AMD-first Linux AI video enhancer using C++, MiGraphX, ROCm, Vulkan and FFmpeg — with measured GPU optimizations submitted upstream to ROCm.
Proxmox cluster using 3 servers interconnected by USB4/Thunderbolt
Miscellaneous things and projects for my ZYBO and ZYNQ devices.
GUI version of waifu2x-ncnn-vulkan.
A super simple, lightweight ~0.5kB (minified & gzipped) and flexible module container.
A very small library for more flexible error catching in JavaScript.
Measured runtime tuning for ComfyUI: per-architecture kernel selection, int8 linear tiles, butterfly convrot rotation, attention kernels (gfx906 first...
One binary to rule them all: model-agnostic local LLM inference for AMD Strix Halo (Ryzen AI MAX+ 395) on Linux. Radeon 8060S iGPU (gfx1151) via HRX +...
Async compute for the AMD BC-250 (GFX1013) on Bazzite / Fedora atomic. Patched RADV as a separate Vulkan driver.
Clean-room spec of halogen's HGN weight format and quants, with test vectors and porting guides.
GNOME top-bar indicator for the AMD Strix Halo power level on the Bosgame M5 (Sixunited AXB35-02, Ryzen AI Max+ 395) — reads the hardware power button...
豆芽 Douya — 基于 llama.cpp 的隐私优先本地 AI 桌面助手 · 完全离线 · 多后端(CUDA/HIP/SYCL/Vulkan/OpenVINO/CPU) · GPU 加速 · 多模态 · RAG · OpenAI 兼容...
Dashboard for AI Studio, Open Source Continuous Inference | Deepseek-R1, Qwen2.5, Llama3.1 | 4xRTX-5090 inside PRU2500, 2xH100 inside PRU2500, 8xMI210...
LLM benchmarking, GPU workload orchestration backend server | Deepseek-R1, Qwen2.5, Llama3.1 | 4xRTX-5090 inside PRU2500, 2xH100 inside PRU2500, 8xMI2...