Add sewing kit and utilities used for pruning scoring - pruning scoring is self-contained now

[danielkorzekwa]

What does this PR do?

Add sewing kit and utilities used for pruning scoring - pruning scoring is self-contained now - no dependency on internal Nvidia code.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 74.37%. Comparing base (f10be0d) to head (5a84ec9).
⚠️ Report is 1 commits behind head on feature/compress.

Additional details and impacted files

@@                Coverage Diff                @@
##           feature/compress     #584   +/-   ##
=================================================
  Coverage             74.37%   74.37%           
=================================================
  Files                   182      182           
  Lines                 18219    18219           
=================================================
  Hits                  13550    13550           
  Misses                 4669     4669           

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[AAnoosheh]

This folder is empty other than this?

[danielkorzekwa]

Deleted this empty module. Note that later some content can be added here. Currently, we only add required modules from sewing_kit to support llama 3.1 8B ffn/att pruning scenario.

[kevalmorabia97]

Minor comments. Feel free to merge after addressing these

[kevalmorabia97]

modelopt only supports python 3.10+ so no need for if-else or from __future__ import annotations in any file

[danielkorzekwa]

removing from __future__ import annotations will fail on self-referencing, e.g.,

modelopt/torch/_compress/sewing_kit/passage/core.py:57: in InputArgs
    def __add__(self, other: Any) -> InputArgs:
E   NameError: name 'InputArgs' is not defined

but I removed:

if sys.version_info[1] < 9: # if less than pytorch 3.9
    from typing import Sequence, Iterable
else:

[danielkorzekwa]

removed from __future__ import annotations from tests/gpu/torch/export/test_fsdp2_export.py

[kevalmorabia97]

All of this could be removed later by just using Nemo AutoModel's PP implementation

[danielkorzekwa]

Created an internal NVidia issue to replace validate_runtime_pipeline.py with Nemo AutoModel's PP implementation: issues/70

[kevalmorabia97]

please remove this

[danielkorzekwa]

done