amd
Repositories (1383)
LLM inference engine for AMD RDNA4 — Rust + Vulkan compute shaders, gguf & native FP8.
Browser-based operator console for managing and monitoring Lemonade on Linux inference servers.
PocketTDPControl is a tool for adjusting TDP of AMD Ryzen Mobile Processor.
Reclaiming the ASRock BC-250 as a real, tunable PC - Cachenetics' open-source firmware liberation + tuning suite.
llama.cpp OpenAI-compatible server on Vulkan for AMD Strix Halo (gfx1151), GGUF weights pinned to GTT not VRAM. Serves poolside Laguna S 2.1, Gemma 4...
Headless Steam Big Picture in a rootless Podman container, streamed to a Steam Deck or any Moonlight client. Shares your game library, not your deskto...
Personal NixOS & MacOS Configurations
Object-storage-native KV cache for LLM inference & RL. Cross-restart, cross-conversation, cross-engine via shared S3 bucket.
AMD SMU Reverse Engineering (for AMD BC-250)
A simplified mechanism for revealing GPU & system architecture information on any computer running any OS
Tensor-parallel DeepSeek V4 Flash inference on dual AMD Strix Halo over OdinLink USB4/TB5 RDMA or Mellanox RoCE v2.
I/O Cache-As-Ram + AMD x86_64 cache line locking | Mirror of https://codeberg.org/3itch/icekit
:small_orange_diamond: Webpack configuration manager
Automatically switch miner to the most profitable algorithm for Ethos.
benchmarking miopen
🔥 AI agent that ports CUDA code to AMD ROCm using local LLMs — FastAPI + React + Ollama | Live: rocmporter-agent.vercel.app
📞 Stream phone farms easily with Solumate—your guide to managing and optimizing mobile device resources for various applications.
EFI OpenCore Coffee Lake Refresh Z390M GAMING
AMD Noise Suppression reduces background audio noise from your surrounding environment, providing greater clarity and improved concentration whether y...
vLLM + Qwen3.6-27B (BF16) OpenAI-compatible inference server on AMD Strix Halo (Ryzen AI Max+ 395, gfx1151). Vision input, 256K context, /v1/responses...
A useful ShadowPlay Instant Replay alternative that actually keeps recording.
Emulator for Am2900 Family Microprogramming
a platform for monitoring the chip situation
An experimental ETH miner powered by Vulkan
Frequency-based KV cache pruning for llama.cpp — 25% cache reduction, improved PPL at long context. GPU compaction kernel for HIP/ROCm.
ROCm AMD Infinity Context - a distributed, shared, low-latency KV Cache tier for AI Infernence.
OpenCore EFI for running macOS on Gigabyte B550 Aorus Pro AX
Web sandbox for async pages.
Hybrid RAG over Indonesian legal documents (UU, PP, Perpres, court decisions) with local LLM via Ollama.
Practical applications for the AMD XDNA NPU on Linux — webcam effects (working) + embeddings/audio/ggml roadmap. Built on open-xdna.
WMMA GEMM in ROCm for RDNA GPUs
AMD package for user-agent detection.
Ryzentosh EFI folder for installing macOS 11 Big Sur on 5900X, X570E, RX590.
EFI for Aorus B550M Elite with amd ryzen 5 5600G and amd radeon RX 6600
Linux configurable driver for 2-in-1 Asus laptops. Driver detects change to tablet/laptop using accelerometer data and send appropriate events.
MSI B550I MPG ITX Hackintosh
Multi-seat game streaming on Linux: several people play on one PC at the same time, each in an isolated container with their own Sway, Sunshine and St...
Monitors crypto mining pools in real-time in order to find the most profitable for your machine. Controls any miner that is available via command line...
OpenCore EFI for AMD Ryzen Vega Hackintosh
DeepSeek V4 Flash 284B on AMD Strix Halo (gfx1151) — up to 32 tok/s decode & ~250 tok/s prefill via ROCmFPX, DSpark & ROCm 7.2
AI/ML research project on AMD ROCm
llama.cpp + ROCm + llama-swap
Run Ollama on AMD Ryzen 7 5800H CPU with integrated GPU AMD ATI Radeon Vega (gfx90c) with optimizations
Collections of hackintosh instructions
Useful assemblies of neural network software.
gpumgr is a GPU manager for Linux allowing easy command line/web interface management of GPU power limits, clocks, fan speeds and more. gpumgr is mult...
Configure AMD FSR at runtime with Blueprint nodes & Automated Settings Saving.
Tool for fixing monitor black crush and gamma manually. Auto-switch gamma profiles for HDR and SDR.
REFEREE is a lightweight, local companion application and API designed to bridge the gap between web-based streams and dedicated graphics hardware.
Whisper-large-v3 fine-tune for Indonesian + Javanese + Sundanese ASR. Lhotse + k2 lattice rescoring pipeline.