Merge Master Changes

[tttennnnn]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello, 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 integrates recent changes, primarily focusing on adjustments to the benchmarking setup and provider interactions. It removes AWSBedrock from streaming VQA comparisons, modifies AWS streaming inference behavior to allow continued event processing past max_tokens limits, and adds cooldown periods in the VQA evaluation workflow to enhance stability during benchmarking runs.

Highlights

• Benchmarking Configuration Update: Removed AWSBedrock from the list of providers included in the streaming VQA benchmarking experiments.
• AWS Streaming Inference Logic: Modified the AWS provider's streaming inference to continue processing events even after a 'max_tokens' stop reason is reported, by removing a break statement.
• VQA Evaluation Stability: Introduced a 15-second delay between the two passes of the VQA evaluation process to enhance stability during benchmarking runs, and updated a related cooldown comment.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Changelog

• benchmarking/experiments/compare_providers_streaming_vqa.json
  • Removed "AWSBedrock" from the list of providers.
• providers/aws_provider.py
  • Removed the break statement that previously exited the streaming inference loop upon encountering a max_tokens stop reason.
• providers/provider_interface.py
  • Added a 15-second time.sleep call between the first and second passes of the VQA iterator loading.
  • Updated the comment for an existing time.sleep call from "Optional cooldown to let VRAM flush and prevent thermal throttling" to "Optional cooldown".

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 merges changes primarily focused on enhancing the VQA (Visual Question Answering) benchmarking capabilities. The key changes include removing AWSBedrock from a specific VQA experiment configuration, fixing a streaming bug in the AWS provider, and adding cooldown periods within the VQA test loop to ensure measurement accuracy. My feedback centers on improving the code's maintainability by addressing a magic number and an overly generic comment introduced in the new cooldown logic.

[gemini-code-assist]

The hardcoded value 15 for the sleep interval is a magic number, which makes the code harder to understand and maintain. This value is also used for a similar purpose later in the function. It would be better to define it as a named constant (e.g., VQA_COOLDOWN_SECONDS = 15) at a shared scope. This would improve readability and make it easier to adjust the cooldown period consistently.

[gemini-code-assist]

The previous comment, "Optional cooldown to let VRAM flush and prevent thermal throttling," was more descriptive and explained the purpose of the time.sleep. The new comment is too generic. Restoring the more detailed explanation would improve code clarity for future maintenance.

Suggested change

	# Optional cooldown
	# Optional cooldown to let VRAM flush and prevent thermal throttling