static test fix

[shihaobai]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @shihaobai, 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 static test fix by refining the ModelInput structure used in static inference benchmarks. The changes introduce more explicit parameters for sequence and cache lengths in both prefill and decode operations, which is essential for accurate and robust model evaluation. The accompanying profiling logs indicate ongoing efforts to benchmark and debug model performance, particularly in scenarios involving Mixture of Experts (MoE) models and memory management.

Highlights

• ModelInput Parameter Updates: Updated the ModelInput parameters in both the prefill and decode functions within test/benchmark/static_inference/model_infer.py to include more detailed sequence and cache length information.
• Prefill Function Enhancements: Specifically, the prefill function's ModelInput now includes max_q_seq_len, max_kv_seq_len, max_cache_len, b_prefill_start_loc, and prefix_total_token_num.
• Decode Function Enhancements: The decode function's ModelInput has been updated to include max_q_seq_len and max_kv_seq_len.
• New Profiling Logs Added: Three new log files (profile_moe_aligin_fused-new.txt, profile_moe_aligin_origin-new.txt, profile_tmp.txt) have been added, containing static inference benchmark results and memory-related error logs.

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 updates the static inference test to align with changes in the ModelInput API. The modifications in test/benchmark/static_inference/model_infer.py correctly add the new required parameters. However, three large text files containing profiling logs have been added. These files should be removed from the repository to maintain a clean version history.