Skip to content

How to accelerate the inference process? #10

@kabutohui

Description

@kabutohui

Thinks for your amazing work! However, the inference latency is too long.

When the steps=128, the inference latency is approximately 10s on single H100.

Reducing the steps can shorten the inference time, but it also degrades the model’s output quality.

Is there any acceleration methods that can improve inference speed without sacrificing model accuracy?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions