LitServe server doesn't crash when there is a failure in setup

[tchaton]

🐛 Bug

To Reproduce

Attach a Lightning Studio which is fully reproducible (code, dependencies, environment, etc...) to reproduce this:

1. Create a Studio.
2. Reproduce the issue in the Studio.
3. Publish the Studio.
4. Paste the Studio link here.

from litserve import LitAPI, LitServer

class DebugLitAPI(LitAPI):
    def setup(self, device):
        raise Exception

    def predict(self, inputs):
        return None

if __name__ == "__main__":
    api = DebugLitAPI()
    server = LitServer(api, accelerator='auto', devices='auto', workers_per_device=2)
    server.run(port=8000)

Instead, it should return exit code error 1.

Code sample

Expected behavior

Environment

If you published a Studio with your bug report, we can automatically get this information. Otherwise, please describe:

• PyTorch/Jax/Tensorflow Version (e.g., 1.0):
• OS (e.g., Linux):
• How you installed PyTorch (conda, pip, source):
• Build command you used (if compiling from source):
• Python version:
• CUDA/cuDNN version:
• GPU models and configuration:
• Any other relevant information:

Additional context

[Borda]

seems to be the same as #293

[grumpyp]

I'd like to improve that, @aniketmaurya, anything I should take into account when working on it?

[aniketmaurya]

sure go ahead @grumpyp!! we call lit_api.setup here. Probably we can do a check if the started workers successfully called setup or not here.