Add Windows CUDA CI coverage for Voxtral Realtime

[larryliu0820]

Summary

This PR adds mistralai/Voxtral-Mini-4B-Realtime-2602 coverage to Windows CUDA CI by following the existing cuda-windows.yml pattern (Linux export artifact + Windows runner E2E).

cuda-windows CI previously covered Voxtral 3B and Parakeet, but not Voxtral Realtime.
Voxtral Realtime also needed explicit cuda-windows export support in its exporter to generate Windows-targeted CUDA artifacts.

What changed

• Updated Windows CUDA workflow matrix to include Voxtral Realtime with supported quantization:
  • quantized-int4-tile-packed
• Kept Voxtral Realtime in offline mode for CI:
  • passes vr-offline in export job
• Extended Windows E2E script support for Voxtral Realtime:
  • builds voxtral_realtime_runner
  • runs with --preprocessor_path, tokenizer, audio, and CUDA --data_path
  • validates expected runtime output string
• Added cuda-windows backend support in export_voxtral_rt.py:
  • accepts --backend cuda-windows
  • lowers using CUDA partitioner with Windows compile spec (platform=windows)
  • normalizes model/export logic to CUDA internals where appropriate
• Added export artifact validation:
  • asserts aoti_cuda_blob.ptd exists for Voxtral Realtime on cuda/cuda-windows

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/17852

• 📄 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, 3 Cancelled Jobs, 3 Unrelated Failures

As of commit f45642a with merge base 5ddbab2 ():

NEW FAILURES - The following jobs have failed:

• Test Metal Backend / export-model-metal-artifact (nvidia, parakeet-tdt, quantized-int4-metal) / macos-job (gh)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 1
• Test Metal Backend / export-model-metal-artifact (openai, whisper-small, non-quantized) / macos-job (gh)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 1

CANCELLED JOBS - The following jobs were cancelled. Please retry:

• trunk / test-mcu-cortex-m-backend / linux-job (gh)
  ##[error]The operation was canceled.
• trunk / test-models-macos-cpu (llama3_2_vision_encoder, portable) / macos-job (gh)
  ##[error]The operation was canceled.
• trunk / test-models-macos-cpu (mv3, xnnpack-quantization-delegation) / macos-job (gh)

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

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

• pull / unittest / macos / macos-job (gh) (trunk failure)
  AttributeError: '_OpNamespace' 'mkldnn' object has no attribute '_is_mkldnn_acl_supported'
• pull / unittest-editable / macos / macos-job (gh) (trunk failure)
  AttributeError: '_OpNamespace' 'mkldnn' object has no attribute '_is_mkldnn_acl_supported'
• trunk / unittest-release / macos / macos-job (gh) (trunk failure)
  AttributeError: '_OpNamespace' 'mkldnn' object has no attribute '_is_mkldnn_acl_supported'

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.