Add zero-copy ByteBuffer image prefill API for Android LlmModule

[psiddh]

The existing prefillImages(int[]) and prefillImages(float[]) APIs perform two full data copies across the JNI boundary: one via getRegion() into a temporary vector, then an element-by-element conversion into the final vector. This adds new prefillImages(ByteBuffer) and prefillNormalizedImages(ByteBuffer) overloads that use GetDirectBytes() on direct ByteBuffers to access the native memory pointer directly, eliminating the JNI array copy overhead.

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/17767

• 📄 Preview Python docs built from this PR

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

❌ 3 New Failures, 2 Unrelated Failures

As of commit 2852bd7 with merge base 5f879ca ():

NEW FAILURES - The following jobs have failed:

• pull / unittest-editable / macos / macos-job (gh)
  examples/models/test/test_export.py::ExportTest::test_mv2_export_to_executorch
• 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

BROKEN TRUNK - The following jobs 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, non-quantized) / windows-job (gh) (trunk failure)
  Process completed with exit code 1.
• 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]

Pull request overview

This PR adds new Android LlmModule image prefill overloads that accept direct ByteBuffers and new corresponding JNI bindings, aiming to reduce JNI overhead compared to the existing int[] / float[] pathways.

Changes:

• Add JNI methods to accept direct ByteBuffer image inputs (uint8 and normalized float).
• Add Java LlmModule.prefillImages(ByteBuffer, ...) and prefillNormalizedImages(ByteBuffer, ...) overloads and register new native methods.
• Deprecate the legacy prefillImages(int[], ...) overload.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 6 comments.

File	Description
extension/android/jni/jni_layer_llama.cpp	Adds new JNI entrypoints that read direct ByteBuffer data for image prefill.
extension/android/executorch_android/src/main/java/org/pytorch/executorch/extension/llm/LlmModule.java	Adds new public ByteBuffer overloads and native declarations; deprecates the int[] overload.

---

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

[Copilot]

Pull request overview

Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.

---

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

[Copilot]

Pull request overview

Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.

---

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