Skip to content

[AutoDeploy] Support silu+mul fusion #11094

@galagam

Description

@galagam

🚀 The feature, motivation and pitch

Part of Llama3.1-8b perf optimization effort in AD.
Fuse silu+mul.
PT: silu_and_mul_kernel
AD: elemwise silu + elemwise mul

Image

Alternatives

No response

Additional context

No response

Before submitting a new issue...

  • Make sure you already searched for relevant issues, and checked the documentation and examples for answers to frequently asked questions.

Metadata

Metadata

Assignees

Labels

AutoDeploy<NV> AutoDeploy Backendfeature requestNew feature or request. This includes new model, dtype, functionality support

Type

No type

Projects

Status

Backlog

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions