[Serve] Enable multiple ports in SkyServe replicas

[Conless]

Current implementation of SkyServe only allows the replicas to expose one port. In some cases, services may need to expose multiple ports for custom controller, GUI interface, etc. This PR adds support for it by allowing multiple ports, but use the first one as the main port. For example, when we start a service with resource requirements:

resources:
  ports:
  - 8080-8081
  - 10000
  cpus: 2

The output of sky serve status will look like:

Services
NAME              VERSION  UPTIME  STATUS  REPLICAS  ENDPOINT            
sky-service-xxxx  1        28s     READY   2/2       xxxx:30001  

Service Replicas
SERVICE_NAME      ID  VERSION  ENDPOINT             LAUNCHED     RESOURCES       STATUS  REGION     
sky-service-xxxx  1   1        http://xxxx:8080     50 secs ago  1x AWS(vCPU=2)  READY   us-east-1  
sky-service-xxxx  2   1        http://xxxx:8080     1 min ago    1x AWS(vCPU=2)  READY   us-east-1 

while the other ports (8081, 10000) are still accessible.

Tested (run the relevant ones):

• [x] Code formatting: bash format.sh

• [x] Any manual or new tests for this PR (please specify below)

  • sky serve up, sky serve status and accessing the service with config:

    
    service:
    readiness_probe: /
    replicas: 2

  resources: ports:

  • 8080
  • 10000-10001 cpus: 2

  run: | python -m http.server 8080 & python -m http.server 10000 & python -m http.server 10001 &

• [ ] All smoke tests: pytest tests/test_smoke.py
• [ ] Relevant individual smoke tests: pytest tests/test_smoke.py::test_fill_in_the_name
• [ ] Backward compatibility tests: conda deactivate; bash -i tests/backward_compatibility_tests.sh

[Conless]

Hi @cblmemo ! Would you like to have a look at this?

[cblmemo]

Can we also update the PR description?

[cblmemo]

Also, it will be great if we can test on some real world usage (e.g. deploy an LLM service and expose metric port in vLLM or dashboard in ray