neura-decoder 0.7.0

Assembling the decoder only models a gguf weighs onto the graph
Documentation
1
2
3
4
5
6
7
8
9
10
11
12
13
mod cache;
mod decoder;
mod layout;
mod op;
mod parameter;
mod rope;

pub use cache::Cache;
pub use decoder::Decoder;
pub use layout::{heads, seat};
pub use op::{flatten, l2, rms, softplus};
pub use parameter::{matrix, vector};
pub use rope::partial;