Prerequisites

• I am running the latest code. Mention the version if possible as well.
• I carefully followed the README.md.
• I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
• I reviewed the Discussions, and have a new and useful enhancement to share.

Feature Description

Dynamically loadable backends framework has been added in PR(#9707). CANN backend needs to adapt to this mechanism.

Motivation

llama.cpp will be refactored to use only the backend registry API, as explained by slaren in PR (#9707). Currently, CUDA and CPU backends has implemented these interfaces.

Possible Implementation

CANN already implement the functions in these interfaces, so this should only require shuffling some code around.