fix: minor updates and fixs for unit_tests to match current code

[WuSiYu]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @WuSiYu, 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 synchronizing various unit tests with recent changes in the codebase. The updates ensure that tests for Triton kernel parameter generation, fused MoE softmax operations, sampling parameter handling, and shared memory request management accurately reflect the current function signatures and object structures. These adjustments are essential for maintaining the integrity and reliability of the test suite.

Highlights

• Triton Kernel Test Updates: The unit tests for gen_decode_params and gen_prefill_params were updated to reflect changes in their function signatures, specifically removing max_q_seq_len and max_kv_seq_len from the expected return values and their corresponding assertions.
• Fused MoE Softmax Test Refinement: The test_softmax_topk.py file was adjusted to remove an unnecessary argument from the sgl_ops.topk_softmax function calls, aligning the test with a simplified API.
• Sampling Parameters Test Adjustment: Assertions for node_id_high and node_id_low in test_sampling_params.py were modified to access these attributes through a nested node_id object, indicating a structural change in how node IDs are managed.
• Shared Memory Request Manager Test Environment Enhancement: The test_shm_req_manager.py now includes a more robust environment setup and teardown, using EasyDict for configuration and adding new FlashInfer related flags, ensuring consistent and isolated test execution.

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 primarily updates unit tests to align with recent code changes. The modifications across the test files correctly reflect new function signatures and data structures. I've identified one issue in test_shm_req_manager.py where the test fixture's teardown logic is incomplete, which could compromise test isolation. A code suggestion is provided to fix this.

[gemini-code-assist]

The teardown logic for the environment variable is incomplete. If LIGHTLLM_START_ARGS was not set before this fixture ran, original will be None, and the if original: check will be false. This causes the environment variable set by the test to leak into other test modules, potentially causing flaky tests. The teardown should ensure the environment variable is removed if it wasn't present initially.

Suggested change

	if original:
	os.environ["LIGHTLLM_START_ARGS"] = original
	if original is not None:
	os.environ["LIGHTLLM_START_ARGS"] = original
	else:
	os.environ.pop("LIGHTLLM_START_ARGS", None)