* add entry point to llm-serving-xpu * manually build * manually build * add entry point to llm-serving-xpu * manually build * add entry point to llm-serving-xpu * add entry point to llm-serving-xpu * add entry point to llm-serving-xpu
* modify Dockerfile * manually build * modify Dockerfile * add chat.py into inference-xpu * add benchmark into inference-cpu * manually build * add benchmark into inference-cpu * add benchmark into inference-cpu * add benchmark into inference-cpu * add chat.py into inference-xpu * add chat.py into inference-xpu * change ADD to COPY in dockerfile * fix dependency issue * temporarily remove run-spr in llm-cpu * temporarily remove run-spr in llm-cpu
* Finished & Tested * Install latest pip from base images * Add blank line * Delete unused comment * fix typos
