Engine
- Added OpenVINO support. #19
Ipex-LLM Engine
- Model generation does not adhere to the max_tokens params. #20
DOC
- Update
README.mdto include usage of precompiled engine executable.
Installation
- Fixed the
ipex-llmpypi library version.
Engine
- Re-structure the configuration to specify which backend and device to launch the
ipex-llmmodel. - Fixed Non-Streaming Mode of ONNX is returning the Prompt in the Response #12
PyInstaller Executable
- Update the
ellm_api_server.specto support compilation ofipex-llminto executable. #14