[diffusion]: add E2E correctness tests for image and video models

[Ratish1]

Motivation

This PR introduces a dedicated functional correctness suite for SGlang Diffusion, complementing the existing performance tests. #12987

Modifications

• testcase_configs.py: added CORRECTNESS_1_GPU_CASES and CORRECTNESS_2_GPU_CASES
• test_server_correctness.py: Implemented a 1-GPU suite featuring bit-identical seed determinism and API error code (400/422) verification.
• test_server_2_gpu_correctness.py: Added a 2-GPU suite for Wan 14B
• Used get_generate_fn and DiffusionServerBase to reuse existing API calling, polling, and binary validation logic.

Accuracy Tests

Benchmarking and Profiling

Checklist

• Format your code according to the Format code with pre-commit.
• Add unit tests according to the Run and add unit tests.
• Update documentation according to Write documentations.
• Provide accuracy and speed benchmark results according to Test the accuracy and Benchmark the speed.
• Follow the SGLang code style guidance.
• Work with maintainers to merge your PR. See the PR Merge Process

[gemini-code-assist]

Summary of Changes

Hello @Ratish1, 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 significantly enhances the testing infrastructure for SGlang Diffusion by introducing a comprehensive end-to-end functional correctness suite. This new suite verifies the expected behavior of image and video generation models, ensuring their reliability through checks for successful output generation, deterministic results with identical seeds, and robust handling of API errors across both single and multi-GPU environments.

Highlights

• New Correctness Test Suite: Introduced a dedicated functional correctness test suite for SGlang Diffusion, complementing existing performance tests.
• 1-GPU Test Cases: Added "test_server_correctness.py" for 1-GPU scenarios, including bit-identical seed determinism and API error code verification.
• 2-GPU Test Cases: Added "test_server_2_gpu_correctness.py" for 2-GPU scenarios, specifically for the Wan 14B model.
• Test Case Configuration: Updated "testcase_configs.py" to define "CORRECTNESS_1_GPU_CASES" and "CORRECTNESS_2_GPU_CASES" for various image and video models.
• Code Reusability: Leveraged "get_generate_fn" and "DiffusionServerBase" to reuse existing API calling, polling, and binary validation logic across the new tests.

🧠 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 introduces a suite of end-to-end correctness tests for image and video diffusion models, which is a great addition to ensure functional reliability. The implementation is well-structured, with new test cases for both 1-GPU and 2-GPU setups, and a shared mixin for test logic. My review focuses on improving the test implementation to prevent redundant executions and enhance maintainability. I've identified a high-severity issue where a test is run twice and a couple of medium-severity issues related to hardcoded values that could be made more dynamic.

[mickqian]

duplicate with #20139, thanks for your contribution