vlm: fix tiny multimodal cache bug

[yhyang201]

Motivation

Modifications

Accuracy Tests

Benchmarking and Profiling

Checklist

• Format your code according to the Format code with pre-commit.
• Add unit tests according to the Run and add unit tests.
• Update documentation according to Write documentations.
• Provide accuracy and speed benchmark results according to Test the accuracy and Benchmark the speed.

[gemini-code-assist]

Summary of Changes

Hello @yhyang201, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request addresses a subtle bug within the multimodal caching logic, specifically ensuring that the cache keys are accurately constructed for each request. By rectifying the source of item hashes, the change aims to improve the reliability and correctness of cache operations for multimodal embeddings, preventing potential cache misses or incorrect data retrieval.

Highlights

• Multimodal Cache Bug Fix: Corrected a bug in the _get_chunked_prefill_embedding function where the item_hashes for multimodal cache lookups were being generated from the wrong list of embedding items. The fix ensures that item_hashes are derived from embedding_items_per_req instead of the broader embedding_items.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request fixes a bug in the multimodal cache key generation. The original code incorrectly used all embedding items in the batch to generate a hash for a single request's embedding, which could lead to cache misses or incorrect cache hits. The change correctly uses the per-request embedding items (embedding_items_per_req) to generate the hash. This is a correct and necessary fix.

[mickqian]

@ZhengWG Could you add it back later, since the cache class is changed in a previous PR (with a server-level cache)?

[ZhengWG]

@ZhengWG Could you add it back later, since the cache class is changed in a previous PR (with a server-level cache)?

Sure, I will add it this week.