DeepSpeed-MII icon indicating copy to clipboard operation
DeepSpeed-MII copied to clipboard

What is the recommended way of bringing up mii as a service

Open flexwang opened this issue 7 months ago • 1 comments

My understanding is that we have to build a fastAPI wrapper, and during intialized phase we call client = mii.client("mistralai/Mistral-7B-v0.1") and we implement a handler to call client.generate.

flexwang avatar Nov 21 '23 00:11 flexwang

You can use the RESTFul API

Also, I added a PR #317 (still in progress) to implement an OpenAI-compatible RESTful API

PawanOsman avatar Nov 21 '23 06:11 PawanOsman