[psiddh]

Avoid constant-name collisions when lifting tensors

A program with a buffer already named _lifted_tensor_constant1 could lift a new scalar into the same name. The resulting signature has duplicate buffer names and can lose a folded constant. Reserve existing names before assigning names to newly lifted tensors.

Review order: the name allocation in lift_constant_tensor_pass, then test_lift_constant_tensor_pass_avoids_buffer_name_collision. This is PR 2 of the Stack 2 series. Its local parent is stack2/pr01-partitioner-transforms; the GitHub base is main, so it includes PR 1's commits followed by this constant-name fix.

Test Plan

On this PR's branch:

python -m pytest -q exir/tests/test_partitioner_transform_passes.py exir/tests/test_passes.py \
  -k 'partitioner_transform or caller_transform or pass_manager_argument or lift_constant_tensor_pass'
6 passed, 80 deselected in 6.81s

Against unmodified main, the collision regression fails with AssertionError: 2 != 1 (duplicate buffer names). After the fix, buffer names are unique and the original [2,2,2,2] buffer is unchanged.

No external memory-planning changes are carried in this PR. The reachable base is 5f72739cf26ed53df21a746fb5b022fb8e4266d9; GitHub main fetch returned proxy 403.

Stack (review in order)

1. Partitioner: run backend-contributed edge transform passes #24566 Partitioner: run backend-contributed edge transform passes
2. Export: avoid reused lifted-constant names #24567 Export: avoid reused lifted-constant names
3. LLM runner: select I/O contracts and accept custom buffer allocators #24568 LLM runner: select I/O contracts and accept custom buffer allocators
4. QNN: construct partitioners from options and allocate LLM I/O in rpcmem #24569 QNN: construct partitioners from options and allocate LLM I/O in rpcmem
5. QNN: bind delegate outputs in exported program order #24570 QNN: bind delegate outputs in exported program order
6. Export hf_static float-cache programs and register their Python runner #24571 Export hf_static float-cache programs and register their Python runner
7. LLM runner: validate and drive hf_static float-cache programs #24572 LLM runner: validate and drive hf_static float-cache programs
8. Document the version-1 hf_static I/O contract #24573 Document the version-1 hf_static I/O contract

Each PR includes the commits of the ones above it; review only its own top commits.

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/24567

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

✅ No Failures

As of commit 33eee76 with merge base 5f72739 ():
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[github-actions]

This PR needs a release notes: label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.