Stream output using server-sent events

replicate / llama-chat

A boilerplate for creating a Llama 3 chat app

https://llama3.replicate.dev

Apache License 2.0

829 stars 306 forks source link

Closed mattt closed 1 year ago

mattt commented 1 year ago

WIP

zeke commented 1 year ago

Moo!

bfirsh commented 1 year ago

This is fantastic. Does it stream token by token? How fast does first token arrive?

Ideally we want it to feel as snappy as https://labs.perplexity.ai/

bfirsh commented 1 year ago