Voxtral Realtime: enable bf16 for Metal backend with quantization

[mergennachin]

The Metal AOTI backend already handles bf16 correctly (fp32 attention
masks, fp32 RoPE upcast, dtype-agnostic KV caches and SDPA). Enable
--dtype bf16 as the default recipe for Metal CI and update all
documentation to recommend bf16 with fpa4w quantization.

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/17845

• 📄 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, 1 Cancelled Job, 4 Unrelated Failures

As of commit 52027ff with merge base 6db7f4c ():

NEW FAILURES - The following jobs have failed:

• Test Metal Backend / test-model-metal-e2e (mistralai, Voxtral-Mini-4B-Realtime-2602, quantized-int4-metal) / macos-job (gh)
  program_source:4450:24: error: assigning to '\''bfloat'\'' from inco
• trunk / test-arm-backend-vkml (test_pytest_ops_vkml) / linux-job (gh)
  RuntimeError: Command docker exec -t 849b2fd1e74edbd359aefe0803fac60bb57daba2342e2aaa59495a0c67d361a4 /exec failed with exit code 1

CANCELLED JOB - The following job was cancelled. Please retry:

• trunk / test-models-macos-mps / macos-job (gh)
  ##[error]The operation was canceled.

FLAKY - The following job failed but was likely due to flakiness present on trunk:

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

BROKEN TRUNK - The following jobs failed but was 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 / test-mcu-cortex-m-backend / 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.

[Copilot]

Pull request overview

Enables and recommends bf16 for Voxtral Realtime exports on Metal when using quantization, updating CI export arguments and user-facing docs to reflect the preferred configuration for memory/throughput.

Changes:

• Update Voxtral Realtime docs to include bf16 memory footprint numbers and recommend --dtype bf16 for Metal quantized exports.
• Adjust example Metal export command(s) to include --dtype bf16 alongside fpa4w.
• Update Metal CI export script to pass --dtype bf16 for the quantized-int4-metal configuration.

Reviewed changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated 3 comments.

File	Description
examples/models/voxtral_realtime/model.md	Updates memory calculations and guidance around bf16 + quantization for Metal/CUDA.
examples/models/voxtral_realtime/export_voxtral_rt.py	Updates usage example to show Metal export with bf16 + fpa4w.
examples/models/voxtral_realtime/README.md	Updates Metal backend table and export examples to recommend bf16 with fpa4w.
.ci/scripts/export_model_artifact.sh	Ensures Metal int4 quantized CI export passes --dtype bf16.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.