Refreshingly fast LLMs on
GPUs and NPUs
GPUs and NPUs
Install, run LLMs locally, and integrate with apps in minutes
Latest Release
Loading latest release...
Loading latest release...
Operating System | Windows | Linux | |
Installation Type | Server Only | Full SDK | |
Installation Method | GUI .exe | PyPI | From Source |
Inference Engine | OGA | llama.cpp | PyTorch |
Device Support | Hybrid | CPU | GPU |