[Nested Tensor]Clean up offsets

[drisspg]

Summary

• Document contiguous offset construction
• Expand offsets by 1 so that storage offsets for ntensor[i] = offsets[i+1] - offsets[i]

Another simple one. While looking into this issue #84082 I noticed that the kernels essentially rebuild the offsets but with the added last element. I added this and also cleaned up the code a little

[facebook-github-bot]

🔗 Helpful links

• 🧪  See artifacts and rendered test results at hud.pytorch.org/pr/84145
• ✖️ Python docs build was skipped
• ✖️ C++ docs build was skipped
• ❓Need help or want to give feedback on the CI? Visit our office hours

✅ No Failures (0 Pending)

As of commit b396bb2 (more details on the Dr. CI page):

Expand to see more

---

💚 💚 Looks good so far! There are no failures yet. 💚 💚

---

This comment was automatically generated by Dr. CI (expand for details).

Please report bugs/suggestions to the (internal) Dr. CI Users group.

Click here to manually regenerate this comment.

[albanD]

Sure.
No kernel needs changing?

[drisspg]

Sure. No kernel needs changing?

Yeah this is a little surprising but since all offset use cases so far have been only using the start position this essentially had no change. No kernel was using ranged based looping on the offsets. This will also potentially come in handy for triton kernels.

[drisspg]

@pytorchbot merge -l

[pytorchmergebot]

@pytorchbot successfully started a merge job. Check the current status here and land check progress here.
The merge job was triggered with the land checks (-l) flag. If you did not specify this flag yourself, you are likely enrolled in the land checks rollout. This means that your change will be merged once all checks on your PR and the land checks have passed (ETA 4 Hours). If you need to coordinate lands between different changes and cannot risk a land race, please add the ciflow/trunk label to your PR and wait for signal to complete, and then land your changes in proper order. Having trunk, pull, and Lint pre-run on a PR will bypass land checks and the ETA should be immediate. If this is not the intended behavior, feel free to use some of the other merge options in the wiki.
Please reach out to the PyTorch DevX Team with feedback or questions!