fix: use sync for offloading in the cpu cache

[blueswhen]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @blueswhen, 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 refines the management of the multi-level KV cache by standardizing the synchronization behavior for CPU cache operations. By removing a conditional environment variable and simplifying the grid_num calculation, it ensures that offloading and loading of KV cache data to and from the CPU are always synchronized, aiming for a more predictable and potentially stable execution flow.

Highlights

• Forced Synchronization for CPU KV Cache: The logic for CPU KV cache offloading and loading operations has been updated to unconditionally enforce synchronization with the compute stream, removing previous conditional checks.
• Simplified Grid Number Calculation: The grid_num parameter used in KV cache load and offload functions is now consistently set to 16, eliminating prior conditional logic based on need_sync_compute_stream or enable_fa3.
• Removal of disable_cpu_kvcache_sync: The disable_cpu_kvcache_sync environment variable and its corresponding utility function have been removed, streamlining the configuration for CPU cache synchronization.

🧠 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.

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 enforces synchronization for CPU cache offloading by removing the async path, which likely fixes a correctness issue. The changes are consistent across the modified files. My feedback includes a suggestion to refactor the code for better clarity by removing the now-redundant flag and conditional checks related to synchronization.

[gemini-code-assist]

Given that self.need_sync_compute_stream is now hardcoded to True, consider a follow-up refactoring to improve clarity. You could remove this attribute entirely and directly call synchronize() where it's used (e.g., lines 72, 162, 175), removing the now-redundant if checks. This would make it explicit that synchronization is always performed for CPU cache operations.

Additionally, the comments mentioning that synchronization is for fa3 (e.g., line 71, 161, 174) could be updated to reflect that this is now a general requirement for CPU cache, not specific to fa3.