[ET-VK][qconv] Pad weight_sums buffer to multiple-of-4 alignment

[SS-JIA]

Stack from ghstack (oldest at bottom):

• [ET-VK][ez][qconv] Add auto-selection to prefer im2col for q8ta_conv2d #17568
• [ET-VK][q8ta] Fix addmm arg indexing in QuantizedLinearMatch #17567
• [ET-VK][q8ta] Add q8ta_linear_gemv op for batch-1 int8 linear #17566
• [ET-VK][q8ta] Add q8ta_linear operator for int8 quantized linear #17565
• [ET-VK][export] Update tensor representation sync logic to allow for flexibility in memory layouts #17564
• [ET-VK] Support different input layouts in q8ta_binary operator #17563
• [ET-VK][ez] Always partition batch norm as it will be fused #17508
• [ET-VK] Add fused q8ta_relu unary operator for int8x4 tensors #17507
• [ET-VK][qconv] Add apply_relu support to q8ta conv operators #17506
• -> [ET-VK][qconv] Pad weight_sums buffer to multiple-of-4 alignment #17505
• [ET-VK][qconv] Fix depthwise weight_sums sum dimension #17504

The q8ta convolution shaders read weight_sums via ivec4 loads (4 int32 values at once), requiring the buffer to have at least align_up_4(OC) elements. The weight tensor, weight_scales, and bias are all padded via align_width_and_update_state_dict, but weight_sums was created as a 1D tensor of shape (OC,) without any padding.

For OC values that are not a multiple of 4 (e.g. OC=1 in the final pointwise conv of MetaNet GreenScreen), this results in out-of-bounds GPU buffer reads. On host testing with ASAN, this manifests as a heap-buffer-overflow.

Fix by padding sum_per_output_channel to align_up_4(OC) before creating the constant placeholder. Also fix the C++ test utility compute_weight_sums() which was incorrectly shrinking a pre-allocated aligned buffer.

Differential Revision: D93511633

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/17505

• 📄 Preview Python docs built from this PR

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

❌ 6 New Failures

As of commit e7f6b78 with merge base 7b843e4 ():

NEW FAILURES - The following jobs have failed:

• pull / test-openvino-linux / linux-job (gh)
  RuntimeError: Command docker exec -t ce2ed5b415f41f5449a0971f5dd328ced7895d90e0bb390fed652e020731cc7d /exec failed with exit code 1
• pull / unittest / macos / macos-job (gh)
  export/tests/test_target_recipes.py::TestTargetRecipes::test_mv3_model
• pull / unittest-arm-backend-with-no-deps (test_pytest_ops_tosa) / linux-job (gh)
  RuntimeError: Command docker exec -t 79f0ef519cdfe89f813da347cb7b9081f4b35adb9bf5eedc4bb4fef6ee84872d /exec failed with exit code 1
• pull / unittest-nxp-neutron / linux-job (gh)
  RuntimeError: Command docker exec -t f0f1e7f519868f8b558b56a62e83316b0c3fb21d01b61033c0744e18de7e7ee5 /exec failed with exit code 1
• Test CUDA Builds / test-models-cuda (conv1d) / linux-job (gh)
  RuntimeError: Command docker exec -t a7d18173d3a24825e84538de00ab9e1ec6b1986d88bf785402e07074fdcfc2ae /exec failed with exit code 1
• Test Metal Backend / export-model-metal-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-metal) / macos-job (gh)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed 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.