How severe does this issue affect your experience of using Ray?
- Medium: It contributes to significant difficulty to complete my task, but I can work around it.
I want to serve gRPC server and http server as part of single deployment. Currently when i implement gRPC server, we get three service running.
- Ray Dashboard on 8265 port
- HTTP Proxy on 8000 port
- gRPC on 9000 port
But we are not able to use http in this case. I want to deploy fastapi on port 8000 to replace http proxy with fastapi.
- How can i do so , any pointer will help alot ?
- Is it possible to deploy with two ingress (one for gRPC, one for HTTP) ?
2023-02-10 11:35:15,210 INFO worker.py:1529 -- Started a local Ray instance. View the dashboard at http://127.0.0.1:8265 (pid=6683) (ServeController pid=6707) INFO 2023-02-10 11:35:18,948 controller 6707 http_state.py:129 - Starting HTTP proxy with name 'SERVE_CONTROLLER_ACTOR:SERVE_PROXY_ACTOR-891db486d37f056d75209dfe018d57eab7bb1cc75854a211babebdd7' on node '891db486d37f056d75209dfe018d57eab7bb1cc75854a211babebdd7' listening on '127.0.0.1:8000' (pid=6685) (HTTPProxyActor pid=6710) INFO: Started server process  (pid=6684) (ServeReplica:Predictor pid=6712) INFO 2023-02-10 11:35:23,016 Predictor Predictor#XCaKeA drivers.py:143 - Starting gRPC server with on node:127.0.0.1 listening on port 9000