3416 Add RBLN(Rebellions) accelerator vendor

[rebel-ysseo]

This PR relates to #3416

Description

Although Rebellions provides a guide on how to utilize TorchServe with the RBLN NPU through its official website(https://docs.rbln.ai/), the current implementation of TorchServe does not recognize the RBLN NPU as a valid accelerator vendor. As a result, even when gpu_id is configured in environments using the RBLN NPU, the specified device cannot be properly utilized.

We propose adding RBLN NPU as a recognized accelerator vendor in TorchServe, along with an official user guide. This addition will enable seamless integration and usage of TorchServe in environments equipped with Rebellions NPUs.

Type of change

Please delete options that are not relevant.

• New feature (non-breaking change which adds functionality)
• This change requires a documentation update

Documentation

Added the Rebellions Support page, which includes a description and examples of how to utilize the RBLN NPU with TorchServe.

Feature/Issue validation/testing

Added a new vendor type for RBLN, the NPU manufacturer Rebellions.
Documentation and PyTest for new added feature are added.

• Backend Test with RBLN NPU

$ python3 -m pytest ts/tests/unit_tests ts/torch_handler/unit_tests
============================================================= 113 passed, 30 warnings in 18.72s ==============================================================
$ cd workflow-archiver && python3 -m pytest workflow_archiver/tests/unit_tests workflow_archiver/tests/integ_tests
===================================================================== 20 passed in 0.34s =====================================================================
$ cd model-archiver && python3 -m pytest model_archiver/tests/unit_tests model_archiver/tests/integ_tests
===================================================================== 33 passed in 0.33s =====================================================================

• PyTest for added feature

$ pytest ./test/pytest/test_rbln_serving.py
collected 6 items

test/pytest/test_rbln_serving.py ......                                                                                                                            [100%]

=========================================================================== 6 passed in 35.11s ===========================================================================

Checklist:

• Did you have fun?
• Have you added 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?

[rebel-ysseo]

@agunapal @jakki-amd @smedegaard
I would greatly appreciate it if you could take a moment to review this pull request at your convenience.
Thank you for your time and consideration.