flexflow / FlexFlow

FlexFlow Serve: Low-Latency, High-Performance LLM Serving
https://flexflow.readthedocs.io
Apache License 2.0
1.73k stars 232 forks source link

Hugging Face Support #409

Closed lockshaw closed 2 years ago

lockshaw commented 2 years ago

@jiazhihao What's the current state of our support for Hugging Face models?

jiazhihao commented 2 years ago

We can support the mt5 model now. I believe that Teresa is trying the bert model.