[Android] Add API to use new config

[kirklandsign]

No description provided.

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/10346

• 📄 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

As of commit c38ccd3 with merge base dfd3dbe ():

NEW FAILURE - The following job has failed:

• Lint / lintrunner / linux-job (gh)
  >>> Lint for backends/cadence/aot/tests/test_replace_ops_passes.py:

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[Copilot]

Pull Request Overview

This PR introduces a new API for configuring and using LLM modules on Android by adding a new constructor that accepts a configuration object (LlmModuleConfig) and a new generate method that takes an LlmGenerationConfig for token generation.

• Introduces a new constructor for LlmModule that initializes the module using LlmModuleConfig.
• Adds an overloaded generate method to support generation with configuration options via LlmGenerationConfig.

Comments suppressed due to low confidence (1)

extension/android/executorch_android/src/main/java/org/pytorch/executorch/extension/llm/LlmModule.java:62

• [nitpick] Consider updating the Javadoc reference to LlmModuleConfig using {@link LlmModuleConfig} instead of #LlmModuleConfig for improved documentation linking and clarity.

/** Constructs a LLM Module for a model with given #LlmModuleConfig */

[Copilot]

Pull Request Overview

This PR introduces an API update to support new configuration options for LLM modules on Android, enabling easier configuration via dedicated config objects.

• Introduces a new constructor accepting LlmModuleConfig.
• Adds an overloaded generate method that takes an LlmGenerationConfig.

Comments suppressed due to low confidence (1)

extension/android/executorch_android/src/main/java/org/pytorch/executorch/extension/llm/LlmModule.java:62

• [nitpick] Consider updating the Javadoc comment to remove the '#' symbol from '#LlmModuleConfig'. Using '{@code LlmModuleConfig}' or including an '@param config' for clarity would improve its readability.

/** Constructs a LLM Module for a model with given #LlmModuleConfig */

[Copilot]

Pull Request Overview

This PR adds new APIs for integrating configuration objects when constructing the LLM module and generating tokens.

• Introduces a new constructor that accepts a LlmModuleConfig object.
• Adds an overloaded generate() method that takes a LlmGenerationConfig object.

Comments suppressed due to low confidence (1)

extension/android/executorch_android/src/main/java/org/pytorch/executorch/extension/llm/LlmModule.java:62

• [nitpick] Consider using the {@link LlmModuleConfig} Javadoc tag instead of '#LlmModuleConfig' for clearer documentation and better IDE support.

/** Constructs a LLM Module for a model with given #LlmModuleConfig */

[Copilot]

Pull Request Overview

This PR introduces a new API that supports configuration objects to initialize and generate outputs in LlmModule.

• Added a new constructor accepting LlmModuleConfig.
• Added an overloaded generate method that uses LlmGenerationConfig.

[facebook-github-bot]

@kirklandsign has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

[facebook-github-bot]

@kirklandsign has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.