[ET-VK] Add symint infrastructure to VulkanBackend and ComputeGraph

[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

Extend the Vulkan backend runtime infrastructure to better support symbolic
integer (symint) arguments. This is a prerequisite for operators that need
to handle dynamic shapes via symint values.

Changes:

• VulkanBackend.cpp: Compute output offset from end of args instead of
  assuming outputs follow inputs directly. Add scalar-to-tensor input
  handling so that Int/Bool EValues can populate tensor inputs. Support
  symint inputs provided as raw Int EValues (not just scalar tensors).
  Add symint output handling to write values back as tensor or Int EValue.
• ComputeGraph.h: Add SymInt case to extract_scalar() so operators
  can transparently read symint values as scalars.
• ComputeGraph.cpp: Add Int fallback in read_symint() so values stored
  as plain Int (rather than SymInt objects) can be read uniformly.

Differential Revision: D95970167

cc @manuelcandales @digantdesai @cbilgin

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/18050

• 📄 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 3070b7a with merge base f09bd55 ():

NEW FAILURES - The following jobs have failed:

• Lint / lintrunner (gh)
  >>> Lint for backends/vulkan/runtime/graph/ComputeGraph.cpp:
• pull / test-llama-runner-qnn-linux (fp32, qnn_8a8w, qnn) / linux-job (gh)
  RuntimeError: Command docker exec -t d82dcef5fd92494f326d32518f9488039ac5d78457c5da959515dabbbf1009fb /exec failed with exit code 92
• pull / test-samsung-models-linux / linux-job (gh)
  test_dl3_fp16
• pull / test-static-llama-qnn-linux (stories_110m) / linux-job (gh)
  RuntimeError: Command docker exec -t 114d50ef15213145783488cfbeb2494945c6fa37479ac7b0e2e9580a4e18c3f7 /exec failed with exit code 9
• Test CUDA Builds / test-model-cuda-e2e (openai, whisper-large-v3-turbo, non-quantized) / linux-job (gh)
  RuntimeError: Command docker exec -t bcf53fb58ba5427a7394605852bb6700fe98a2b4c66b07c6fa767686c9e295e9 /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.