support small bs = 1 or 2

[wangyibo1005]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @wangyibo1005, 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 focuses on enhancing the system's ability to handle and test very small batch sizes, specifically batch size 1. It includes a modification to a core padding constant in the C++ implementation and introduces a new Python test flag and associated logic to validate the behavior of fused deep MoE operations under these specific, low-batch conditions.

Highlights

• Core Logic Adjustment: The PADDING_SIZE constant in csrc/deepep/deep_ep.cpp has been reduced from 3 to 1. This change likely optimizes or adapts the deep learning operations for smaller input dimensions.
• Small Batch Size Testing: New testing logic has been introduced in tests/python/deepep/test_fused_deep_moe.py to specifically test with a batch size of 1. This is activated by a new smallBs_flag.
• Command-line Argument for Testing: A new command-line argument, --smallBs-flag, has been added to the test script, allowing users to easily enable or disable the small batch size test scenario.

Ignored Files

• Ignored by pattern: .github/workflows/** (1)
  • .github/workflows/pr-test-npu.yml

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 aims to add support for small batch sizes (1 or 2) by reducing the padding size in the C++ code and adding a test flag for small batch sizes in the Python test. The change in deep_ep.cpp seems correct for this purpose. In the Python test file, I've suggested several improvements related to Python's PEP-8 naming conventions and code clarity. These changes will improve the readability and maintainability of the test code.