[ez][ET-VK][partitioner] Allow layout-agnostic ops to accept quantized layouts

[SS-JIA]

Stack from ghstack (oldest at bottom):

• [ET-VK][q8ta_pixel_shuffle] Add fused PixelShuffle custom op for channels-packed int8 tensors #19397
• [ET-VK] Implement aten.pixel_shuffle.default op #19404
• [ez][ET-VK][q8ta_conv2d_pw] Halve accumulator to lift Adreno occupancy #19396
• -> [ez][ET-VK][partitioner] Allow layout-agnostic ops to accept quantized layouts #19395

Two changes that together let the partitioner keep PACKED_INT8 layouts flowing through identity-like ops, eliminating spurious clone dispatches:

1. utils.py: ANY_STORAGE_INCL_PACKED_INT8 (renamed from ALL_STORAGES_REPSET) previously claimed every layout (including PACKED_INT8_*) on the texture side, but PACKED_INT8 is buffer-only by convention — the texture indexing helpers and required_image_extents don't know about quantized layouts. Narrow the texture side to all_memory_layouts (float-only). Every existing call site is either an intersection identity or a wildcard for non-tensor / not-yet-prepacked args, so this narrow is non-breaking; and now the repset can act as a true universal set when intersected against quant-aware repsets. The new name slots cleanly next to ANY_STORAGE / ANY_BUFFER / ANY_TEXTURE and tells the reader exactly what is added: "like ANY_STORAGE, but also admits PACKED_INT8 (on the buffer side)".

2. op_registry.py: switch view_copy / clone / clone_dim_order / alias_copy from inputs_storage=ANY_STORAGE to inputs_storage=ANY_STORAGE_INCL_PACKED_INT8. ANY_STORAGE is float-only, so when one of these no-op identity ops sits between two q8ta ops the BFS in TagMemoryMetaPass.constrain_op*_repset short-circuits (zero overlap with PACKED_INT8_BUFFER) and forces transitions on both sides. With ANY_STORAGE_INCL_PACKED_INT8 they now admit both float and quantized layouts and the redundant-op transform folds them away.

The 31 other ops using ANY_STORAGE are real compute ops (binaryop, comparison, softmax, argreduce, permute_copy, etc.) whose float-only kernels do not accept quantized int8x4 layouts (q8ta_* are separate ops); leaving those alone.

On RefineNet 24feat (1x3x256x144) the 8 _clone_dim_order ops the partitioner had been inserting around the 4 fused q8ta_pixel_shuffle nodes are now folded by the delegate. Runtime q8ta_clone dispatches drop from 11 to 3 (the 3 residuals are unrelated, from the original model graph).

Differential Revision: D103770022

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19395

• 📄 Preview Python docs built from this PR

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

❗ 1 Active SEVs

There are 1 currently active SEVs. If your PR is affected, please view them below:

• Long GPU queue (g5, g6) on LF fleet

❌ 1 New Failure

As of commit aaf89d4 with merge base c564936 ():

NEW FAILURE - The following job has failed:

• pull / unittest / macos / macos-job (gh)
  backends/xnnpack/test/ops/test_conv2d.py::TestConv2d::test_fp16_conv2d

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.