gianlucamazza/xllama

Local LLM inference on Xbox Series S in Developer Mode: llama.cpp (GGUF) + ONNX Runtime GenAI, an OpenAI-compatible LAN endpoint (off by default), SD-Turbo image generation and experimental on-device fine-tuning. Not yet tested on Series X. Independent project, not affiliated with Microsoft.

语言：C++ · GitHub 星标：77 · Fork：10

话题：cpp · directml · game-console · gguf · huggingface · llama-cpp · llm · local-inference

在 GitHub 上查看原仓库