Use fork for multiprocessing mode

[yuzisun]

What this PR does / why we need it:

Which issue(s) this PR fixes (optional, in fixes #<issue number>(, fixes #<issue_number>, ...) format, will close the issue(s) when PR gets merged):
Fixes #2690
Fixes #2694

Type of changes
Please delete options that are not relevant.

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

Feature/Issue validation/testing:

Please describe the tests that you ran to verify your changes and relevent result summary. Provide instructions so it can be reproduced.
Please also list any relevant details for your test configuration.

• Test multi-processing mode with 2 rest workers

python -m model --model_name=custom --worker=2 --enable_rest=true --enable_grpc=true

2023-02-26 19:49:49.687 61502 root INFO [register_model():187] Registering model: custom
2023-02-26 19:49:49.687 61502 root INFO [start():129] Setting max asyncio worker threads as 16
2023-02-26 19:49:49.688 61502 root INFO [serve():139] Starting uvicorn with 2 workers
2023-02-26 19:49:49.760 61502 root INFO [start():62] Starting gRPC server on [::]:8081
2023-02-26 19:49:49.765 61505 uvicorn.error INFO [serve():84] Started server process [61505]
2023-02-26 19:49:49.766 61505 uvicorn.error INFO [startup():45] Waiting for application startup.
2023-02-26 19:49:49 DEBUG [timing_asgi.middleware:40] ASGI scope of type lifespan is not supported yet
2023-02-26 19:49:49.768 61505 uvicorn.error INFO [startup():59] Application startup complete.
2023-02-26 19:49:49.768 61506 uvicorn.error INFO [serve():84] Started server process [61506]
2023-02-26 19:49:49.769 61506 uvicorn.error INFO [startup():45] Waiting for application startup.
2023-02-26 19:49:49 DEBUG [timing_asgi.middleware:40] ASGI scope of type lifespan is not supported yet
2023-02-26 19:49:49.771 61506 uvicorn.error INFO [startup():59] Application startup complete.
^C2023-02-26 19:50:17.428 61502 root INFO [stop():170] Stopping the model server
2023-02-26 19:50:17.428 61502 root INFO [stop():172] Stopping the rest server
2023-02-26 19:50:17.428 61502 root INFO [stop():175] Stopping the grpc server
2023-02-26 19:50:17.428 61502 root INFO [stop():67] Waiting for gRPC server shutdown
2023-02-26 19:50:17.429 61502 root INFO [stop():69] gRPC server shutdown complete
2023-02-26 19:50:17.453 61506 uvicorn.error INFO [shutdown():263] Shutting down
2023-02-26 19:50:17.453 61505 uvicorn.error INFO [shutdown():263] Shutting down
2023-02-26 19:50:17.555 61505 uvicorn.error INFO [shutdown():64] Waiting for application shutdown.
2023-02-26 19:50:17.555 61506 uvicorn.error INFO [shutdown():64] Waiting for application shutdown.
2023-02-26 19:50:17.556 61505 uvicorn.error INFO [shutdown():75] Application shutdown complete.
2023-02-26 19:50:17.556 61506 uvicorn.error INFO [shutdown():75] Application shutdown complete.
2023-02-26 19:50:17.557 61505 uvicorn.error INFO [serve():94] Finished server process [61505]
2023-02-26 19:50:17.557 61506 uvicorn.error INFO [serve():94] Finished server process [61506]

• Test 1 worker with both REST and gRPC server

python -m model --model_name=custom --worker=1 --enable_rest=true --enable_grpc=true

2023-02-26 19:51:34.557 61522 root INFO [register_model():187] Registering model: custom
2023-02-26 19:51:34.557 61522 root INFO [start():129] Setting max asyncio worker threads as 16
2023-02-26 19:51:34.558 61522 root INFO [serve():139] Starting uvicorn with 1 workers
2023-02-26 19:51:34.595 61522 uvicorn.error INFO [serve():84] Started server process [61522]
2023-02-26 19:51:34.596 61522 uvicorn.error INFO [startup():45] Waiting for application startup.
2023-02-26 19:51:34.599 61522 root INFO [start():62] Starting gRPC server on [::]:8081
2023-02-26 19:51:34 DEBUG [timing_asgi.middleware:40] ASGI scope of type lifespan is not supported yet
2023-02-26 19:51:34.600 61522 uvicorn.error INFO [startup():59] Application startup complete.
^C2023-02-26 19:51:35.955 61522 root INFO [stop():170] Stopping the model server
2023-02-26 19:51:35.955 61522 root INFO [stop():172] Stopping the rest server
2023-02-26 19:51:35.955 61522 root INFO [stop():175] Stopping the grpc server
2023-02-26 19:51:35.955 61522 root INFO [stop():67] Waiting for gRPC server shutdown
2023-02-26 19:51:35.956 61522 root INFO [stop():69] gRPC server shutdown complete
2023-02-26 19:51:36.007 61522 uvicorn.error INFO [shutdown():263] Shutting down
2023-02-26 19:51:36.107 61522 uvicorn.error INFO [shutdown():64] Waiting for application shutdown.
2023-02-26 19:51:36.108 61522 uvicorn.error INFO [shutdown():75] Application shutdown complete.
2023-02-26 19:51:36.108 61522 uvicorn.error INFO [serve():94] Finished server process [61522]

• Logs

Special notes for your reviewer:

1. Please confirm that if this PR changes any image versions, then that's the sole change this PR makes.

Checklist:

• Have you added unit/e2e tests that prove your fix is effective or that this feature works?
• Has code been commented, particularly in hard-to-understand areas?
• Have you made corresponding changes to the documentation?

Release note:

[kserve-oss-bot]

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: yuzisun

The full list of commands accepted by this bot can be found here.

The pull request process is described here

Needs approval from an approver in each of these files:

• python/kserve/OWNERS [yuzisun]

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

[rachitchauhan43]

/lgtm