[ET-VK][qconv] Add layout-agnostic general shader for quantized conv

[SS-JIA]

Stack from ghstack (oldest at bottom):

• [ET-VK][qconv] Add flexible layout impl for quantized pointwise conv #17221
• [ET-VK][testing] Create dedicated test binary for pointwise convolutions #17220
• -> [ET-VK][qconv] Add layout-agnostic general shader for quantized conv #17219
• [ET-VK][quantization] Add layout-flexible clone for int8x4 tensors #17171
• [ET-VK][qconv] Add layout-flexible impl of quantized depthwise conv2d #17108
• [ET-VK][ez] Implement helper functions to get fastest moving dim #17107
• [ET-VK][quantization] Implement layout-flexible quantize/dequantize operators #17106
• [ET-VK] Add alignment fields to PackedDimInfo for padded size calculation #17170
• [ET-VK][testing] Add per-shader timing breakdown to benchmark output #17105

The existing quantized conv2d implementation (conv2d_q8ta_q8csw_q8to) only
supports the 4W4C memory layout. This limits its use when models require
different tensor layouts. This change introduces a new general-purpose
quantized conv2d shader (q8ta_conv2d) that works with any memory layout
by using BufferMetadata for tensor indexing.

The routing logic determines which implementation to use based on input/output
layouts: when both are 4W4C, the existing optimized path is used; otherwise,
the new general shader handles the computation. This enables quantized conv2d
to work seamlessly across 4C1W, 4W4C, and 4C memory layouts.

Key changes:

• New GLSL shader q8ta_conv2d.glsl using layout specialization constants
• New Q8taConv2d.cpp with operator registration and workgroup size heuristics
• Refactored routing in QuantizedConvolution.cpp to dispatch based on layout
• Extended test coverage to validate all three memory layouts

Authored with Claude.

Differential Revision: D92307252

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/17219

• 📄 Preview Python docs built from this PR

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

❌ 2 New Failures, 2 Unrelated Failures

As of commit e1d06ed with merge base 477867a ():

NEW FAILURES - The following jobs have failed:

• pull / test-vulkan-operators-linux / linux-job (gh)
  RuntimeError: Command docker exec -t c5b769d47bc0f904cd6d10075e4cb6f1da23646f56f11fbe5fd4a0202d0fe48e /exec failed with exit code 134
• Test CUDA Builds / export-model-cuda-artifact (openai, whisper-small, non-quantized) / linux-job (gh)
  RuntimeError: Command docker exec -t 3437aac416a29f4a05b2652e57e3c01ba095c01570b4ad7e39a3113f15426e49 /exec failed with exit code 1

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

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

• pull / test-samsung-models-linux / linux-job (gh) (trunk failure)
  ##[error]The operation was canceled.
• pull / test-samsung-quantmodels-linux / linux-job (gh) (trunk failure)
  ##[error]The operation was canceled.

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.