Skip to content

Add operator fusion pass into E2E pipeline but cause perfomance decline #595

@GuoningHuang

Description

@GuoningHuang

Describe the bug
When I trying to add operator fusion pass such as flashattention or RMsNorm into E2E pass, the performance declined.
before I using norm opt, the E2E performance is:

Image

after i using norm opt, the performance is:

Image

To Reproduce
Reproduce this issue by #596 or #553.

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