Support W16A16 quantization #391

Open

Labels

opened

on Mar 28, 2025

Hi Authors,

Some of our models need to be quantized as int16 (w16a16) to achieve better accuracy. Looks tinynn currently does not support that. Please kindly evaluate the fessibility of implementation. Big thanks.

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

Metadata

Assignees

No one assigned

Labels

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests