Upgrade to use CUDA 11.8

[agunapal]

Description

Upgrade TorchServe to use CUDA 11.8 as default

Fixes #(issue)

Type of change

Please delete options that are not relevant.

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

Feature/Issue validation/testing

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

• Auto-tested by Regression Tests

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?

[codecov]

Codecov Report

Merging #2489 (c7ac944) into master (48fe78f) will not change coverage.
The diff coverage is n/a.

❗ Current head c7ac944 differs from pull request most recent head c8da525. Consider uploading reports for the commit c8da525 to get more accurate results

@@           Coverage Diff           @@
##           master    #2489   +/-   ##
=======================================
  Coverage   72.66%   72.66%           
=======================================
  Files          78       78           
  Lines        3669     3669           
  Branches       58       58           
=======================================
  Hits         2666     2666           
  Misses        999      999           
  Partials        4        4           

📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more

[msaroufim]

We also need to update the GHA runners and ensure our requirements.txt are using CUDA 11.8

[agunapal]

@msaroufim Requirements were updated a while ago.

Also, opened this for updating runners
#2487

But, since PyTorch uses its own CUDA bundle, it should be ok ?