[Vulkan] Make expand_copy resizable and fully delegate dynamic transformer blocks

[mergennachin]

The dynamic transformer reproductions now lower to one Vulkan delegate across changing sequence lengths. This final PR makes expand_copy resizable and adds the eager-attention and SDPA integration tests, including fully masked rows on devices with 8-bit storage buffers.

Fixes #23156.

This is part 15 of a linear ghstack series. Review each PR against its selected base branch; this PR contains only the final expansion and transformer changes. The scalar-tensor issue #23158 is owned by part 10.

Part	PR	Change
1	#23240	Hardware Vulkan CI
2	#23241	Scalar cache type and signed-zero keys
3	#23242	Vulkan-local signed-zero serialization
4	#23243	GELU modes and view kwargs
5	#23244	Reduction clamp, NaN, and FP16 rounding
6	#23245	Reduction dimension guards
7	#23246	Bool staging and logical_not
8	#23247	Scalar representability and symbolic guards
9	#23248	64-bit dtype and fusion policy
10	#23249	scalar_tensor with exact integer values
11	#23250	Typed, resizable full
12	#23251	Power special values and logical FP16 dtype
13	#23252	mul.Scalar
14	#23253	any.dim
15	#23254	Dynamic expand and transformer integration

The stack retains the FACTO and ATen conformance fixes and their regression tests: typed integer fills, NaN and signed-zero behavior, reduction range and accumulation fixes, safe scalar fallbacks, and the FP16 power contract. On native FP16 devices, the scalar-tensor, full texture, single-dimension texture reduction, and binary scalar shaders round their FP16 outputs to nearest-even. The binary scalar shaders also preserve the requested FP16 dtype when storage is emulated with FP32. Other operators retain their existing FP32 intermediate behavior on those devices. PR4 introduces test_vulkan_dynamic.py and its CI/Buck references.

Each code patch was linted and tested before its original publication. Prior validation of the operator changes passed 116 FACTO cases against both ATen and portable kernels, plus 144 boundary cases against ATen, with texture and buffer preferences: all 520 Vulkan-configuration executions matched ATen, including CPU fallback where unsupported. The additional 239-case sweep covers all 91 available FACTO specifications for registered ATen overloads and 57 targeted examples. Exact-input replays of every candidate Vulkan failure on a separately built main at a31838280f9309f04af1b375147375b702d29339 found no new regressions or unresolved comparisons.

Validation uses the shared backends/test/ harness on Apple M1 Pro / MoltenVK with Release portable CPU kernels and Vulkan; optimized kernels and XNNPACK are disabled. Buffer preference uses texture_limits=(1,1,1), with actual storage and fallback recorded separately. Single-texel tensors can still select textures. FACTO revision: 3b8c778c99766a8b4d0d04563ae0b16cbb276829, seed 0.

The complete native regression run on the previously published head a2543b8a82 passed 50 tests with one expected SwiftShader-only skip on MoltenVK, covering all 35 dynamic tests, graph-builder and serialization tests, and PT2E quantized linear with downcasting disabled. The subsequent serializer refinement confines --force-defaults to Vulkan and restores the shared exir FlatBuffers API. That revised source tree passed 26 focused tests, including shared/Vulkan serialization, signed-zero execution, and power special values. All other code patches are unchanged, and every replacement PR was checked against the tested source trees. Lintrunner and git diff --check passed.

The prior Vulkan NVIDIA, SwiftShader, and Windows checks have completed successfully. CI validation of the new exponent-conversion and chained-multiplication tests is pending on the updated ghstack heads.

Recreates #23162 through ghstack. Prior review discussion remains on that PR.

Follow-up regression coverage adds scalar exponents 2.0001 and 2049 and a two-node FP16 mul.Scalar chain. The power test and chained-multiplication/signed-zero tests pass individually on MoltenVK; the full dynamic suite on the restacked tip passed 35 tests with one expected SwiftShader-only skip on MoltenVK. Lintrunner and git diff --check passed. These changes preserve the existing runtime and shader implementation.

Authored with OpenAI Codex; split planned with Claude Code.

cc @SS-JIA @manuelcandales @digantdesai @cbilgin

[mergennachin]

Stack from ghstack (oldest at bottom):

• -> [Vulkan] Make expand_copy resizable and fully delegate dynamic transformer blocks #23254
• [Vulkan] Add aten.any.dim #23253
• [Vulkan] Delegate aten.mul.Scalar #23252
• [Vulkan] Match ATen special values in pow.Tensor_Scalar #23251
• [Vulkan] Pass typed fill values to full and make it resizable #23250
• [Vulkan] Delegate aten.scalar_tensor with exact integer values #23249
• [Vulkan] Honor downcast_64_bit=False in the partitioner #23248
• [Vulkan] Keep unrepresentable and symbolic scalars out of the delegate #23247
• [Vulkan] Stage bool tensors without 8-bit storage and register logical_not #23246
• [Vulkan] Keep reductions the reduce shaders cannot handle on CPU #23245
• [Vulkan] Stop clamping per-row reductions and propagate NaN #23244
• [Vulkan] Honor GELU approximate='none' and keep kwargs off inserted views #23243
• [Vulkan] Preserve signed zero within the Vulkan serializer #23242
• [Vulkan] Key serialized scalar constants by type and value #23241
• [Vulkan] Require a hardware GPU in the NVIDIA Vulkan CI job #23240

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/23254

• 📄 Preview Python docs built from this PR

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

❌ 1 Pending, 1 Unclassified Failure

As of commit b82ffd0 with merge base a318382 ():

UNCLASSIFIED FAILURE - DrCI could not classify the following job because the workflow did not run on the merge base. The failure may be pre-existing on trunk or introduced by this PR:

• Test CoreML Backend (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)

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