kevinintel

please update supported data types in https://github.com/intel/neural-speed/blob/main/docs/advanced_usage.md

It's not high priority task. Oracle Cloud is on roadmap, but not ARM based machine

I prefer entire text. Btw, OPEA is microservice-based, please think how to contribute to OPEA.

Please try to create PR first, Late Chunk may not better than current embedding, but you are welcome to expand the functionalities

fixed

we can add info in docs to remind user close bf16 on specific machines.

We add bf16 in Readme of docker

will assign to Zhihao

TGI-Gaudi and vllm supports Falcon 40B and Flacon 7B. We will validate Falcon-11B

TGI-Gaudi did not support this model: https://huggingface.co/tiiuae/falcon-11B-vlm we need to wait for TGI-Gaudi