lattice-inference 0.2.2

Pure Rust transformer inference engine — safetensors loading, SIMD matmul, BGE/Qwen3 embeddings
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14

pub mod bert;
pub mod bitnet_config;
pub mod cross_encoder;
pub mod qwen;
pub mod qwen35;
pub mod qwen35_config;

// Re-export everything from bert (was top-level `model` module)
pub use self::bert::*;
pub use self::cross_encoder::CrossEncoderModel;
// Re-export key types from other model modules
pub use self::qwen::{LayerTimings, ProfileTimings, QwenConfig, QwenModel};
pub use self::qwen35::Qwen35Model;
pub use self::qwen35_config::GenerateConfig;