[ET-VK][qconv] Add dynamic PACKED_INT8_CONV2D memory layout for device-adaptive conv2d

[SS-JIA]

Stack from ghstack (oldest at bottom):

• [ET-VK][testing] Add GPU device name override for on-device model tests #17795
• -> [ET-VK][qconv] Add dynamic PACKED_INT8_CONV2D memory layout for device-adaptive conv2d #17794
• [ET-VK][qconv] Enable im2col to handle grouped convolution #17793
• [ET-VK][ez] Use tree reduction in q8ta_linear_gemv shader #17792

Performance testing of quantized int8 convolutions reveals that different
algorithms perform better on different GPU architectures: im2col is faster on
Mali while direct convolution is faster on Adreno. The optimal memory layout
differs per algorithm (4C for im2col, 4C1W for direct convolution).

This introduces a new "dynamic" memory layout PACKED_INT8_CONV2D that is
serialized at export time and resolved to a concrete layout at runtime based
on the device's GPU architecture. The resolution logic in ResolveLayouts.cpp
mirrors the im2col vs direct convolution decision in Q8taConv2d.cpp.

Differential Revision: D94949134

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/17794

• 📄 Preview Python docs built from this PR

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

❌ 14 New Failures, 4 Unrelated Failures

As of commit 31f1d0b with merge base ae41854 ():

NEW FAILURES - The following jobs have failed:

• pull / test-coreml-bc-macos (macos-m2-stable) / macos-job (gh)
  An action could not be found at the URI 'https://api.github.com/repos/actions/checkout/tarball/11bd71901bbe5b1630ceea73d27597364c9af683' (D97F:3CC34C:108B8B:1405EE:69A5FB4D)
• pull / test-multimodal-linux (gemma3-4b) / linux-job (gh)
  An action could not be found at the URI 'https://api.github.com/repos/aws-actions/amazon-ecr-login/tarball/062b18b96a7aff071d4dc91bc00c4c1a7945b076' (DA48:273D84:100A33:138348:69A5FB51)
• pull / unittest-editable / macos / macos-job (gh)
  export/tests/test_target_recipes.py::TestTargetRecipes::test_mv3_model
• Test Metal Backend / export-model-metal-artifact (mistralai, Voxtral-Mini-3B-2507, non-quantized) / macos-job (gh)
  An action could not be found at the URI 'https://api.github.com/repos/actions/checkout/tarball/11bd71901bbe5b1630ceea73d27597364c9af683' (EEEB:3715E:11A3C7:151BE2:69A5FB41)
• Test Metal Backend / export-model-metal-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-metal) / macos-job (gh)
  An action could not be found at the URI 'https://api.github.com/repos/actions/checkout/tarball/11bd71901bbe5b1630ceea73d27597364c9af683' (D703:350925:FA7CA:13208D:69A5FB49)
• Test Metal Backend / export-model-metal-artifact (mistralai, Voxtral-Mini-4B-Realtime-2602, quantized-int4-metal) / macos-job (gh)
  An action could not be found at the URI 'https://api.github.com/repos/actions/checkout/tarball/11bd71901bbe5b1630ceea73d27597364c9af683' (D6F8:364F9A:FE65B:1360E7:69A5FB45)
• Test Metal Backend / export-model-metal-artifact (nvidia, parakeet-tdt, non-quantized) / macos-job (gh)
  An action could not be found at the URI 'https://api.github.com/repos/actions/checkout/tarball/11bd71901bbe5b1630ceea73d27597364c9af683' (EEF6:171855:102244:139C85:69A5FB45)
• Test Metal Backend / export-model-metal-artifact (nvidia, parakeet-tdt, quantized-int4-metal) / macos-job (gh)
  An action could not be found at the URI 'https://api.github.com/repos/actions/checkout/tarball/11bd71901bbe5b1630ceea73d27597364c9af683' (D4DD:350925:FA70D:131FA7:69A5FB45)
• Test Metal Backend / export-model-metal-artifact (openai, whisper-large-v3-turbo, non-quantized) / macos-job (gh)
  An action could not be found at the URI 'https://api.github.com/repos/actions/checkout/tarball/11bd71901bbe5b1630ceea73d27597364c9af683' (D4E8:23578:10D85D:1452FA:69A5FB49)
• Test Metal Backend / export-model-metal-artifact (openai, whisper-large-v3-turbo, quantized-int4-metal) / macos-job (gh)
  An action could not be found at the URI 'https://api.github.com/repos/actions/checkout/tarball/11bd71901bbe5b1630ceea73d27597364c9af683' (D968:3266E:1089D9:140388:69A5FB46)
• Test Metal Backend / export-model-metal-artifact (openai, whisper-small, non-quantized) / macos-job (gh)
  An action could not be found at the URI 'https://api.github.com/repos/actions/checkout/tarball/11bd71901bbe5b1630ceea73d27597364c9af683' (D973:2E87DE:109BC3:1416C4:69A5FB49)
• Test Metal Backend / export-model-metal-artifact (openai, whisper-small, quantized-int4-metal) / macos-job (gh)
  An action could not be found at the URI 'https://api.github.com/repos/actions/checkout/tarball/11bd71901bbe5b1630ceea73d27597364c9af683' (EF03:3CC34C:108AA6:1404D4:69A5FB49)
• Test Metal Backend / test-executorch-metal-build / macos-job (gh)
  An action could not be found at the URI 'https://api.github.com/repos/actions/checkout/tarball/11bd71901bbe5b1630ceea73d27597364c9af683' (D6EC:381148:100819:1362AA:69A5FB41)
• Test Metal Backend / test-metal-backend-modules / macos-job (gh)
  An action could not be found at the URI 'https://api.github.com/repos/actions/checkout/tarball/11bd71901bbe5b1630ceea73d27597364c9af683' (D4D2:193E62:FB86D:1332B6:69A5FB41)

FLAKY - The following jobs failed but were likely due to flakiness present on trunk:

• pull / test-models-linux (emformer_join, portable, linux.4xlarge.memory) / linux-job (gh) (detected as infra flaky with no log or failing log classifier)
• pull / test-models-linux (emformer_join, xnnpack-quantization-delegation, linux.4xlarge.memory) / linux-job (gh) (detected as infra flaky with no log or failing log classifier)

BROKEN TRUNK - The following jobs failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

• Test CUDA Windows Export and E2E / test-model-cuda-windows-e2e (mistralai, Voxtral-Mini-3B-2507, non-quantized) / windows-job (gh) (trunk failure)
  Process completed with exit code 1.
• Test CUDA Windows Export and E2E / test-model-cuda-windows-e2e (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only) / windows-job (gh) (trunk failure)
  Process completed with exit code 1.

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.