Baoyuantop commented on issue #12735:
URL: https://github.com/apache/apisix/issues/12735#issuecomment-3509843646

   The `ai-proxy-multi` plugin proxies requests to multiple large models based 
on weights and priorities, similar to load balancing in this scenario, so 
specifying model names is neither necessary nor supported. If you need to pass 
the name of the model to be accessed in the request, you can create a separate 
route for each large model.
   
   APISIX by default returns all response headers from the upstream to the 
client, unless you configure additional rules.
   


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]

Reply via email to