[diffusion] logging: improve peak vram logging

[mickqian]

log mem statistics in perf_dump_path:

  "memory_checkpoints": {
    "before_forward": {
      "allocated_mb": 33905.64,
      "reserved_mb": 34308.0,
      "peak_allocated_mb": 33905.64,
      "peak_reserved_mb": 34308.0
    },
    "after_forward": {
      "allocated_mb": 34838.05,
      "reserved_mb": 62406.0,
      "peak_allocated_mb": 53044.04,
      "peak_reserved_mb": 62406.0
    },
    "mem_analysis": {
      "allocated_mb": 34838.05,
      "reserved_mb": 62406.0,
      "peak_allocated_mb": 53044.04,
      "peak_reserved_mb": 62406.0
    }
  },

Motivation

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.

Review Process

1. Ping Merge Oncalls to start the PR flow. See the PR Merge Process.
2. Get approvals from CODEOWNERS and other reviewers.
3. Trigger CI tests with comments or contact authorized users to do so.
   • /tag-run-ci-label, /rerun-failed-ci, /tag-and-rerun-ci
4. After green CI and required approvals, ask Merge Oncalls to merge.

[gemini-code-assist]

Summary of Changes

Hello @mickqian, 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 enhances the accuracy of VRAM logging within the gpu_worker module. By modifying the peak memory calculation to account for both allocated and reserved GPU memory, it ensures that reported VRAM usage more precisely reflects actual consumption, aiding in better resource monitoring and debugging.

Highlights

• VRAM Logging Improvement: The calculation for peak VRAM usage has been updated to consider both allocated and reserved memory, providing a more accurate representation of GPU memory consumption.

🧠 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.

Changelog

• python/sglang/multimodal_gen/runtime/managers/gpu_worker.py
  • Updated the do_mem_analysis method to calculate peak_memory_bytes as the maximum of allocated_bytes and reserved_bytes.

Activity

• No activity has been recorded for this pull request yet.

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 improves the peak VRAM logging by considering the reserved memory in addition to the allocated memory. This provides a more accurate picture of the memory footprint. My review includes a suggestion to simplify the implementation for calculating the peak memory, as the current logic is slightly redundant.

[mickqian]

/tag-and-rerun-ci