Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Did you consider to apply xDiT for parallel inference #34

Open
feifeibear opened this issue Nov 12, 2024 · 2 comments
Open

Did you consider to apply xDiT for parallel inference #34

feifeibear opened this issue Nov 12, 2024 · 2 comments

Comments

@feifeibear
Copy link

feifeibear commented Nov 12, 2024

Hello Allegro Team,

I hope this message finds you well. I would like to propose the integration of xDiT, a scalable inference engine for Diffusion Transformers (DiTs), into the Allegro ecosystem. xDiT offers several compelling benefits that could significantly enhance the performance and scalability of inference tasks within Allegro.

Key Benefits of xDiT:

  1. Ease of Transformation into Sequence Parallel + USP Version:

    • xDiT can be easily adapted to support sequence parallelism combined with Unified Scaling Policy (USP), making it highly flexible and efficient for various inference scenarios.
  2. Compatibility with huggingfacee diffusers Ecosystem and ComfyUI:

    • xDiT is designed to be compatible with the diffuser ecosystem and ComfyUI, ensuring seamless integration and interoperability with existing tools and workflows.
  3. Scalability with PipeFusion and Hybrid Parallelism:

    • xDiT's support for PipeFusion and hybrid parallelism allows it to scale to very large-scale inference tasks, providing substantial performance improvements.

Additional Highlights:

  • Efficient Inference for Video Models:

    • xDiT has demonstrated significant success in reducing inference latency for video models, such as CogVideX-5B and mochi1-10B, achieving notable speedups.
  • Performance Gains:

    • The mochi-xdit project has shown a 3.54X reduction in inference latency compared to the official open-source implementation.

References:

Thank you for considering this proposal. I look forward to your thoughts and feedback.

@maazel-rhymes
Copy link

Hi Feifeibear,

Your xDiT looks amazing, and I've starred. However, we're currently really short-handed and do not have enough time for the integration ourselves. If you can help us with the integration, we'd love to make a joint announcement to our developer community! p.s. Allegro will receive an I2V upgrade soon

Best Regards,
Maazel

@feifeibear
Copy link
Author

Hi Feifeibear,

Your xDiT looks amazing, and I've starred. However, we're currently really short-handed and do not have enough time for the integration ourselves. If you can help us with the integration, we'd love to make a joint announcement to our developer community! p.s. Allegro will receive an I2V upgrade soon

Best Regards, Maazel

Thanks! Feel free to contact us if you need parallel inference solutions.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants