add omp in env for torchrun and update doc

[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)

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 #2320 (4377f9e) into master (2f1f52f) will increase coverage by 0.02%.
The diff coverage is 0.00%.

❗ Current head 4377f9e differs from pull request most recent head c42bafe. Consider uploading reports for the commit c42bafe to get more accurate results

@@            Coverage Diff             @@
##           master    #2320      +/-   ##
==========================================
+ Coverage   69.37%   69.39%   +0.02%     
==========================================
  Files          77       77              
  Lines        3438     3441       +3     
  Branches       57       57              
==========================================
+ Hits         2385     2388       +3     
  Misses       1050     1050              
  Partials        3        3              

Impacted Files	Coverage Δ
ts/model_service_worker.py	64.33% <0.00%> (-1.38%)	⬇️

... and 1 file with indirect coverage changes

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

[chauhang]

Thanks Li for the updates. Few comments:

1. Will be good to move the Download_models.py one level up as a common file after Pippy deferred init #2310 is merged.

2. For the Large model best practices, we should expand and provide more details for model packaging, threads and other configs and troubleshooting tips. This can be done as a separate PR

[HamidShojanazeri]

@lxning added some minor suggestions.

[chauhang]

Is there a reason for pinning the version numbers? Can we do >= instead?

[lxning]

The version combination of DS and transformer is not stable. Some combination does not work. So far this combination works for all the models we have tested.

[chauhang]

Left few comments please check

[chauhang]

For OMP_NUM_THREADS, please add documentation for how user can set this value