Convert jni_layer_llama.cpp from fbjni to pure JNI

[Copilot]

Summary

Removes fbjni dependency from the LLM Android JNI layer, enabling broader compatibility and simpler builds without Facebook's JNI wrapper library.

Changes:

• LlmModule.java: Replace HybridData with native handle pattern (long pointer)
• jni_layer_llama.cpp: Complete rewrite using pure JNI
  • New ExecuTorchLlmNative class holds native state
  • New CallbackHelper manages JNI callback lifecycle with proper global refs
  • All methods now extern "C" JNI functions with explicit RegisterNatives
• jni_helper.h/cpp: Add pure JNI overload for throwExecutorchException(JNIEnv*, ...)
• jni_layer.cpp: Pass JNIEnv* to register_natives_for_llm()

The fbjni-based codepath is preserved behind EXECUTORCH_HAS_FBJNI macro for backward compatibility.

Test plan

Existing Android JNI tests cover the LlmModule interface. The behavioral contract is unchanged—only the underlying JNI implementation differs.

Warning

Firewall rules blocked me from connecting to one or more addresses (expand for details)

I tried to connect to the following addresses, but was blocked by firewall rules:

• dl.google.com
  • Triggering command: /usr/lib/jvm/temurin-17-jdk-amd64/bin/java /usr/lib/jvm/temurin-17-jdk-amd64/bin/java --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.prefs/java.util.prefs=ALL-UNNAMED --add-exports=jdk.compiler/com.sun.tools.javac.api=ALL-UNNAMED --add-exports=jdk.compiler/com.sun.tools.javac.util=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.prefs/java.util.prefs=ALL-UNNAMED --add-opens=java.base/java.nio.charset=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.xml/javax.xml.namespace=ALL-UNNAMED -XX:MaxMetaspaceSize=384m -XX:+HeapDumpOnOutOfMemoryError -Xms256m -Xmx512m -Dfile.encoding=UTF-8 -Duser.country -Duser.language=en (dns block)
  • Triggering command: /usr/lib/jvm/temurin-17-jdk-amd64/bin/java /usr/lib/jvm/temurin-17-jdk-amd64/bin/java --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.prefs/java.util.prefs=ALL-UNNAMED --add-opens=java.base/java.nio.charset=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED -Xmx2048m -Dfile.encoding=UTF-8 -Duser.country -Duser.language=en -Duser.variant -cp /home/REDACTED/.gradle/wrapper/dists/gradle-8.2-bin/bbg7u40eoinfdyxsxr3z4i7ta/gradle-8.2/lib/gradle-launcher-8.2.jar -javaagent:/home/REDACTED/.gradle/wrapper/dists/gradle-8.2-bin/bbg7u40eoinfdyxsxr3z4i7ta/gradle-8.2/lib/agents/gradle-instrumentation-agent-8.2.jar org.gradle.launcher.daemon.bootstrap.GradleDaemon 8.2 (dns block)

If you need me to access, download, or install something from one of these locations, you can either:

• Configure Actions setup steps to set up my environment, which run before the firewall is enabled
• Add the appropriate URLs or hosts to the custom allowlist in this repository's Copilot coding agent settings (admins only)

Original prompt

Submit a new PR using the changes from the git history (commits b5bc13d and 2660810

---

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16519

• 📄 Preview Python docs built from this PR

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

❌ 1 New Failure, 5 Unrelated Failures

As of commit bd5034e with merge base 806c8e8 ():

NEW FAILURE - The following job has failed:

• Lint / lintrunner / linux-job (gh)
  >>> Lint for extension/android/jni/jni_layer_llama.cpp:

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 / export-model-cuda-windows-artifact (openai, whisper-large-v3-turbo, non-quantized) / linux-job (gh) (trunk failure)
  /opt/conda/lib/python3.10/site-packages/torch/include/ATen/core/PhiloxRNGEngine.h:135:79: error: ‘M_PI’ was not declared in this scope
• Test CUDA Windows Export / export-model-cuda-windows-artifact (openai, whisper-large-v3-turbo, quantized-int4-weight-only) / linux-job (gh) (trunk failure)
  /opt/conda/lib/python3.10/site-packages/torch/include/ATen/core/PhiloxRNGEngine.h:135:79: error: ‘M_PI’ was not declared in this scope
• Test CUDA Windows Export / export-model-cuda-windows-artifact (openai, whisper-small, non-quantized) / linux-job (gh) (trunk failure)
  /opt/conda/lib/python3.10/site-packages/torch/include/ATen/core/PhiloxRNGEngine.h:135:79: error: ‘M_PI’ was not declared in this scope
• Test CUDA Windows Export / export-model-cuda-windows-artifact (openai, whisper-small, quantized-int4-weight-only) / linux-job (gh) (trunk failure)
  /opt/conda/lib/python3.10/site-packages/torch/include/ATen/core/PhiloxRNGEngine.h:135:79: error: ‘M_PI’ was not declared in this scope

UNSTABLE - The following job is marked as unstable, possibly due to flakiness on trunk:

• pull / android / run-emulator (gh) (#16137)
  Timeout waiting for emulator to boot.

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.

[github-actions]

Looks like this PR hasn't been updated in a while so we're going to go ahead and mark this as Stale.
Feel free to remove the Stale label if you feel this was a mistake.
If you are unable to remove the Stale label please contact a maintainer in order to do so.
If you want the bot to never mark this PR stale again, add the no-stale label.
Stale pull requests will automatically be closed after 30 days of inactivity.