[ET-VK] Add conv1d shaders and dispatch for 1D convolution

[SS-JIA]

Stack from ghstack (oldest at bottom):

• [ET-VK] Buckify parakeet #18062
• [ET-VK][qlinear] Add bias support to q4gsw and dq8ca_q4gsw quantized linear ops #18061
• -> [ET-VK] Add conv1d shaders and dispatch for 1D convolution #18060
• [ET-VK] Implement missing Vulkan operators for Parakeet TDT model #18059
• [ET-VK] Add ANY_STORAGE support to argmax and argmin #18058
• [ET-VK] Add ANY_STORAGE support to embedding #18057
• [ET-VK] Add ANY_STORAGE support to repeat #18056
• [ET-VK] Add ANY_STORAGE support to native_layer_norm #18055
• [ET-VK] Add ANY_STORAGE support to softmax and log_softmax #18054
• [ET-VK] Add ANY_STORAGE support to expand_copy #18053
• [ET-VK] Add ANY_STORAGE support to arange and full #18052
• [ET-VK] Generalize constant_pad_nd to support any storage type and packed dimension #18051
• [ET-VK] Add symint infrastructure to VulkanBackend and ComputeGraph #18050
• [ET-VK] Add Vulkan backend support for Parakeet runner and export #18049
• [ET-VK][ez] Fix IndexError in Vulkan partitioner DtypeSetList/TensorRepSetList #18048

Add dedicated GLSL shaders and C++ dispatch for 1D convolution operations.
The new implementation introduces three execution paths:

1. Buffer path (general and depthwise): conv1d.glsl and conv1d_dw.glsl operate
   on width-packed buffer tensors, with one shader invocation per output element
   at (n, out_c, out_l). Uses sizes_ubo/strides_ubo and tidx_to_bufi() for
   layout-agnostic index computation.

2. Buffer path (pointwise): conv1d_pw.glsl specializes the kernel_size=1 case
   to skip the spatial loop for efficiency.

3. Texture path (pointwise): conv1d_pw_texture.glsl handles the pointwise case
   for width-packed texture3d tensors, computing one output texel (4 values)
   per invocation using a scalar weight from a buffer.

The legacy conv1d_texture.glsl (renamed from conv1d.glsl) preserves the
original channels-packed texture path for backward compatibility.

Convolution.cpp is updated to route 1D convolutions to the appropriate
specialized dispatch (add_conv1d_buf_node or add_conv1d_pw_texture_node)
based on the input storage type and packed dim, falling back to the legacy
texture path for channels-packed inputs.

op_registry.py gains a pick_conv_storage function that selects:

• WIDTH_PACKED_TEXTURE for pointwise 1D conv (kernel_size=1)
• CONTIGUOUS_BUFFER for non-pointwise 1D conv
• CHANNELS_PACKED_TEXTURE for 2D conv (unchanged)

Differential Revision: D95970166

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/18060

• 📄 Preview Python docs built from this PR

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

❌ 5 New Failures

As of commit c8d484d with merge base f09bd55 ():

NEW FAILURES - The following jobs have failed:

• Test CUDA Builds / export-model-cuda-artifact (google, gemma-3-4b-it, quantized-int4-tile-packed) / linux-job (gh)
  RuntimeError: Command docker exec -t 3cd154494f8f99554758a28573d5330e39f412e4134d8e0b8f30ff386c55d99c /exec failed with exit code 1
• Test CUDA Builds / export-model-cuda-artifact (openai, whisper-large-v3-turbo, non-quantized) / linux-job (gh)
  RuntimeError: Command docker exec -t 6854986763c9d89cd1c9aa37fd128cd30bfe77b468c6044cd2fef4144339c277 /exec failed with exit code 1
• Test CUDA Builds / export-model-cuda-artifact (Qwen, Qwen3-0.6B, non-quantized) / linux-job (gh)
  RuntimeError: Command docker exec -t c9c90cc1a47466773db39aab104513c0a12b1a5545197b2fc851709c6eb47f1a /exec failed with exit code 1
• Test CUDA Builds / export-model-cuda-artifact (Qwen, Qwen3-0.6B, quantized-int4-weight-only) / linux-job (gh)
  RuntimeError: Command docker exec -t fc16d70a60a386307c7b29051af59bccc66b3c4ca920a713c5fa0f4ae5e94d19 /exec failed with exit code 1
• Test CUDA Windows Export and E2E / export-model-cuda-windows-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only) / linux-job (gh)
  RuntimeError: Command docker exec -t 6d7e5705f19f2d35dcce573f12f077a5b0f4214da5b971f8934235779d751362 /exec 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.