amd

Lightweight ROCm inference toolkit for AMD GPUs — FP16/INT8 quantization, batch processing, benchmarking, HuggingFace integration

AMD ROCm & NVIDIA CUDA GPU-accelerated manga upscaling

Local-first multi-agent orchestrator for AMD APU. Multi-agent pipeline, GBNF constrained decoding, asymmetric KV quantization, Wasmtime sandbox — all...

Warcraft-faction-themed GPU driver updater for Windows - checks NVIDIA, AMD and Intel for new drivers, downloads from vendor servers, slim driver-only...

AMD consumer/eGPU local-AI benchmarks: measured configs, negative results, and the footguns nobody documents

Fresh-host qualified AMD ROCm 7.2 / RDNA4 gfx1201 port and public installer for 2D Gaussian Splatting (2DGS), verified on Radeon AI PRO R9700.