fix diffusion profile bugs

[yizhang2077]

Motivation

1. avoid race with different ranks in profiling when num_gpus > 1
2. remove code which causes device sync

Modifications

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[bot]]

Summary of Changes

Hello @yizhang2077, I'm Gemini Code Assist[^1]! 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 stability and reliability of the profiling mechanism within a distributed environment. It specifically addresses and resolves potential race conditions that could arise when multiple ranks perform profiling concurrently, ensuring that each process generates unique trace files and that all processes are properly synchronized. The changes also adjust profiling parameters to allow for more comprehensive data capture.

Highlights

• Increased Profiling Timesteps: The default number of active timesteps for profiling (num_profiled_timesteps) has been increased from 2 to 8, allowing for more extensive data collection during profiling sessions.
• Distributed Profiling Race Condition Fixes: Modifications were made to the denoising stage to prevent race conditions in distributed profiling environments. This includes importing get_world_rank to identify individual processes and adjusting profiler parameters.
• Unique Trace File Generation and Synchronization: Profiler trace files now include the process rank in their filenames (-rank{rank}.trace.json.gz) to ensure uniqueness across distributed processes. Additionally, torch.distributed.barrier() has been added to synchronize all processes before profiling completion, enhancing robustness.

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 :thumbsup: and :thumbsdown: 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.

[^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.

[mickqian]

/gemini review

[gemini-code-assist[bot]]

[!WARNING] You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again!