Skip to content

Binary quantization? #548

Description

@kishorenc

The README mentions the Binarized Neural Machine Translation paper but does not really elaborate on how one can use AQT to implement one-bit weights and activations using AQT. For example, will the library take care of using LayerNorms as replacement for scaling factor, as mentioned in the paper?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Fields

    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions