Skip to content

Difficulty understanding selective scan in Mamba implementation #936

@itsPronay

Description

@itsPronay

I’m trying to understand the selective scan operation in Mamba, but I’m having difficulty connecting the implementation with the underlying math/intuition.

Could someone please share good resources (papers, blog posts, or explanations) that clearly explain:

  • what selective scan is doing mathematically
  • how it relates to state space models
  • and how it is implemented efficiently in Mamba

Thanks

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    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