Voxtral Realtime: enable CUDA backend with int4 quantization

[mergennachin]

Add CUDA/AOTI backend support for the Voxtral Realtime model alongside
the existing XNNPACK and Metal backends.

Model (model.py):

• CudaSDPA: F.scaled_dot_product_attention with repeat_interleave for
  GQA expansion and boolean attention masks (Triton SDPA requirement)
• StaticKVCache (shared with Metal) for [B,H,S,D] layout with index_copy_
• StandardEncoderRingKVCache/StandardEncoderSDPA for streaming encoder
• _build_causal_mask_bool: 4D boolean mask for Triton compatibility
• Simplified LMAttention.forward to always pass attn_mask (None for XNNPACK)

Export (export_voxtral_rt.py):

• --backend cuda with CudaPartitioner and conv1d_to_conv2d decomposition
• --dtype flag (default fp32, bf16 for CUDA Triton SDPA)
• --qlinear-packing-format / --qlinear-encoder-packing-format for
  tile_packed_to_4d int4 quantization
• CUDA device placement, Dim.AUTO for audio encoder, .ptd output

Runner (main.cpp, voxtral_realtime_runner.cpp/.h):

• --data_path flag for .ptd delegate data (CUDA compiled kernels)
• Module two-arg constructor for pte+ptd loading

Build (CMakePresets.json, Makefile):

• voxtral-realtime-cuda preset
• make voxtral_realtime-cuda target

CI (.github/workflows/cuda.yml, .ci/scripts/):

• Voxtral Realtime in CUDA CI matrix (int4-tile-packed, offline mode)
• Export/test scripts updated for CUDA quantization args and data path

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/17798

• 📄 Preview Python docs built from this PR

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

❌ 7 New Failures, 1 Unrelated Failure

As of commit 1e5399a with merge base 25f2a3f ():

NEW FAILURES - The following jobs have failed:

• Copilot code review / Upload results (gh)
  Process completed with exit code 1.
• pull / test-multimodal-linux (gemma3-4b) / linux-job (gh)
  RuntimeError: Command docker exec -t a91379aad4ad04e948e62993cc99d89b32f31ef347fe6a9d5aea5bafaa9151ca /exec failed with exit code 139
• pull / test-voxtral-realtime-xnnpack-linux / linux-job (gh)
  RuntimeError: Command docker exec -t e10ea2b666f30ba9dc31cdaae0eceb91756c9f0954fd3388413558000f0d5688 /exec failed with exit code 1
• Test CUDA Builds / test-model-cuda-e2e (mistralai, Voxtral-Mini-4B-Realtime-2602, quantized-int4-tile-packed) / linux-job (gh)
  RuntimeError: Command docker exec -t dfc949046625caaa85642f5b79021775ae516d8f221c793eb95d8f238beef90b /exec failed with exit code 134
• Test CUDA Windows Export and E2E / test-model-cuda-windows-e2e (mistralai, Voxtral-Mini-3B-2507, non-quantized) / windows-job (gh)
  Process completed with exit code 1.
• trunk / test-mcu-cortex-m-backend / linux-job (gh)
  RuntimeError: Command docker exec -t ce624419fcb5990050841c36bef7e101d472c956970cf373f36c9d18a6a9c585 /exec failed with exit code 1
• trunk / unittest-release / macos / macos-job (gh)
  backends/xnnpack/test/ops/test_conv2d.py::TestConv2d::test_fp16_conv2d

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

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

• Test CUDA Windows Export and E2E / test-model-cuda-windows-e2e (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only) / windows-job (gh) (trunk failure)
  Process completed 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.

[Copilot]

Copilot encountered an error and was unable to review this pull request. You can try again by re-requesting a review.