Vulkan: handle a single tensor output arriving as a list

[msluszniak]

Summary

Fixes #22306.

num_tensors_in_node() counts the tensors associated with a node rather than the nesting of meta["val"], so it returns 1 both for a bare FakeTensor and for a one-element list. OpRepSets treats that count as proof of the former and passes meta["val"] straight to filter_invalid_reprs(), which then does tensor_val.shape on a list:

  File "backends/vulkan/utils.py", line 1203, in filter_invalid_reprs
    extents = required_image_extents(tensor_val.shape, memory_layout)
AttributeError: 'list' object has no attribute 'shape'

Any op declared to return Tensor[] hits this whenever it happens to produce exactly one tensor. aten.split_with_sizes_copy.default is the case seen in the wild (lowering RF-DETR nano). Because the exception escapes the partitioner, one such node aborts partitioning for the whole model instead of the node being reported unsupported.

Unwrap the single element before filtering, matching what the multiple-output branch immediately below already does per element.

Test plan

New case in backends/vulkan/test/test_vulkan_tensor_repr.py building an OpRepSets for split_with_sizes_copy whose meta["val"] is a one-element list. It reproduces the AttributeError on main and passes with this change.

pytest backends/vulkan/test/test_vulkan_tensor_repr.py
88 passed

pytest backends/vulkan/test/test_vulkan_passes.py backends/vulkan/test/test_serialization.py
15 passed

cc @SS-JIA @manuelcandales @digantdesai @cbilgin

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/22308

• 📄 Preview Python docs built from this PR

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

⚠️ 15 Awaiting Approval

As of commit 4cd0217 with merge base c27baa8 ():

AWAITING APPROVAL - The following workflows need approval before CI can run:

• Build documentation (gh)
• Build Presets (gh)
• Lint (gh)
• periodic (gh)
• pull (gh)
• Test ARM Backend (gh)
• Test CoreML Backend (gh)
• Test Cortex-M Backend (gh)
• Test NXP Backend (gh)
• Test QNN Backend (gh)
• Test QNN Windows MSVC build (gh)
• Test Vulkan Backend (gh)
• Test Vulkan Backend (specialized runners) (gh)
• Test WebGPU Backend (gh)
• Test XNNPACK Backend (gh)

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.