amd

A high-throughput and memory-efficient inference and serving engine for LLMs

ODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn your PC, Mac, or Linux box into a private AI server.

OptiScaler bridges upscaling/frame gen across GPUs. Supports DLSS2+/XeSS/FSR2+ inputs, replaces native upscalers, enables FSR-FG/XeFG on non-FG titles. Supports Nukem mod for DLSSG-to-FSR3 FG.

Rulith Inference, formerly Strix Llama. Serving a 125B MoE model fast on one AMD Strix Halo machine, on Windows: a patched llama.cpp, a manager, and a desktop app.

Run CUDA-targeted Windows applications on AMD GPUs with ZLUDA + ROCm/HIP.