Repository navigation

请问下int4 kvcache在做mma的时候是如何反量化的？ #3320

Closed

opened

on Mar 24, 2025

如题，我想知道int4 kvcache是如何做高效反量化的，做了kv cache的重排吗，还是先ldsm后做warp内的shuffle

to join this conversation on GitHub. Already have an account? Sign in to comment

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