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
pub mod differential;
pub mod flash;
pub mod flash_causal;
pub mod gated;
pub mod gdn;
pub mod gdn_fused;
pub mod gqa;
pub mod native_sparse;
pub mod standard;

// Re-export from standard for backward compat
pub use self::standard::*;