intel-analytics/ipex-llm

Fastchat serving embeddings?

lnguyen opened this issue · 4 comments

lnguyen commented

Is it possible to support embeddings with BigDL-LLM fastchat worker?

gc-fu commented

Hi, I am working on this issue. We will see if we can support this API

lnguyen commented

awesome!

gc-fu commented

Hi, the embedding API has been added to the ipex_llm_worker. You can try this when the next nightly release is available~

lnguyen commented

I've tried this and it works! thank you