Skip to content

[Feature]: Implement model_free quantization method (W4A16) #1491

@xin3he

Description

@xin3he

Feature Description

Quantization without model architecture information.

Motivation and Use Case

It allows more flexible behavior and avoid relying on third-party architecture support

Alternatives Considered

No response

Definition of Done

No response

Additional Context

No response

Metadata

Metadata

Assignees

Type

No type

Projects

No projects

Relationships

None yet

Development

No branches or pull requests

Issue actions