TorchServe decompress tgz format model

[lxning]

Description

Please read our CONTRIBUTING.md prior to creating your first pull request.

Please include a summary of the feature or issue being fixed. Please also include relevant motivation and context. List any dependencies that are required for this change.

Fixes #(issue)
#2213

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.

• Test A
  Logs for Test A

• Test B
  Logs for Test B

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 #2214 (a6d4c28) into master (237675f) will not change coverage.
The diff coverage is n/a.

❗ Current head a6d4c28 differs from pull request most recent head c1584fe. Consider uploading reports for the commit c1584fe to get more accurate results

@@           Coverage Diff           @@
##           master    #2214   +/-   ##
=======================================
  Coverage   71.52%   71.52%           
=======================================
  Files          73       73           
  Lines        3329     3329           
  Branches       57       57           
=======================================
  Hits         2381     2381           
  Misses        945      945           
  Partials        3        3           

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

[HamidShojanazeri]

Thanks @lxning for the PR, I suggest we add a doc for the usage and link it in the very front page to point users that they would be able to use tgz format instead of mar file.

This can benefit user from a size reduction in the packaged file (mar file) and also its more familiar to the user.

Also, as discussed user is able to pass a path_to_model_checkpoints instead of zip file in the torch-model-archiver --model-name bloom --version 1.0 --handler handler.py --extra-files model.zip