TP llama with continuous batching

[mreso]

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.

• New feature (non-breaking change which adds functionality)

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.

• pytest test/pytest/test_tp_llama.py

=========================================================================================================================== test session starts ============================================================================================================================
platform linux -- Python 3.10.12, pytest-7.3.1, pluggy-1.3.0
rootdir: /home/ubuntu/serve
plugins: mock-3.10.0, cov-4.1.0
collected 8 items

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

============================================================================================================================= warnings summary =============================================================================================================================
test/pytest/test_tp_llama.py::test_handler
  /home/ubuntu/serve/ts/torch_handler/base_handler.py:13: DeprecationWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html
    from pkg_resources import packaging

-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
================================================================================================================= 8 passed, 1 warning in 62.65s (0:01:02) ==================================================================================================================

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?

[codecov]

Codecov Report

Merging #2709 (97d5a32) into master (7f4419f) will decrease coverage by 0.08%.
The diff coverage is n/a.

❗ Current head 97d5a32 differs from pull request most recent head b7230ac. Consider uploading reports for the commit b7230ac to get more accurate results

@@            Coverage Diff             @@
##           master    #2709      +/-   ##
==========================================
- Coverage   72.44%   72.36%   -0.08%     
==========================================
  Files          85       85              
  Lines        3963     3963              
  Branches       58       58              
==========================================
- Hits         2871     2868       -3     
- Misses       1088     1091       +3     
  Partials        4        4              

see 1 file with indirect coverage changes

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

[HamidShojanazeri]

thanks @mreso , LGTM, and test ran fine too.

pytest test/pytest/test_tp_llama.py::test_continuous_batching_tp_llama
================================================================================= test session starts ==================================================================================
platform linux -- Python 3.10.13, pytest-7.4.3, pluggy-1.3.0
rootdir: /home/ubuntu/serve
collected 1 item                                                                                                                                                                       

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

================================================================================== 1 passed in 26.15s ==================================================================================