Tensor statistic collection via NVIDIA-DLFW-Inspect & TE debug modules

[paul-gibbons]

What does this PR do ?

Adds support for NVIDIA DLFW Inspect into Megatron training loop, which enables the user to collect tensor statistics from TransformerEngine's debug modules.

Contribution process

Pre-checks

• I have added relevant unit tests
• I have added relevant functional tests
• I have added proper typing to my code Typing guidelines
• I have added relevant documentation
• I have run the autoformatter.sh on my PR

Code review

Feel free to message or comment the @mcore-oncall to help accelerate your merge into main. The less complex your PR is, the faster it will be approved and merged!

All PRs start as draft. If you open a non-draft PR, it will be automatically converted to draft.

Step 1: Mark PR as "Ready for Review"

1. When your PR is ready, click Ready for Review.
2. An oncall reviewer is auto-assigned and expert reviewers are notified based on your changes.
   • Some PRs may jump straight to step 2. This is determined by .github/CODEOWNERS.

⚠️ Only mark as ready once merge-conflicts are resolved and the CI is passing.
Final Review might get declined if these requirements are not fulfilled.

Step 2: Final Review

For PRs that change megatron/core, once all expert reviewers have approved, the Final Review label is applied automatically and final reviewers are assigned.

For PRs outside megatron/core, this step is skipped.

Step 3: Approved

Once all required reviewers have approved, the Approved label is applied automatically.

Merge

Any member of mcore-engineers will be able to merge your PR.

For MRs into `dev` branch

The proposed review process for `dev` branch is under active discussion.

MRs are mergable after one approval by either eharper@nvidia.com or zijiey@nvidia.com.

[copy-pr-bot]

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

[ericharper]

How does this PR relate to what's in bridge? https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/6d8a1c547d2fc0a9d2812c3d6477fb0fca4d3714/src/megatron/bridge/training/tensor_inspect.py#L4

[paul-gibbons]

How does this PR relate to what's in bridge? https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/6d8a1c547d2fc0a9d2812c3d6477fb0fca4d3714/src/megatron/bridge/training/tensor_inspect.py#L4

Brings the same functionality to MLM training loop.

Needed in MLM for further development of additional set of MRs to add tensor inspect modules inside of mcore

[ericharper]

How does this PR relate to what's in bridge? https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/6d8a1c547d2fc0a9d2812c3d6477fb0fca4d3714/src/megatron/bridge/training/tensor_inspect.py#L4

Brings the same functionality to MLM training loop.

Needed in MLM for further development of additional set of MRs to add tensor inspect modules inside of mcore

Can consolidate this? @maanug-nv ? Maybe bridge gets this from mcore?

[deepakn94]

@paul-gibbons Can you add some documentation on what the output of this looks like? You can add it somewhere here: https://github.com/NVIDIA/Megatron-LM/tree/main/docs. Screenshots, etc. useful!