alice-llm 2.0.0

Pure Rust LLM inference engine — GGUF v3 parser, K-quants, hybrid CPU/GPU DeltaNet+Attention, wgpu compute shaders, speculative decoding, OpenAI-compatible HTTP server.
Documentation
1
2
3
4
5
6
7
8
9
10
11
//! Prelude re-exports.

pub use crate::attention::*;
pub use crate::batch_inference::*;
pub use crate::kv_cache::*;
pub use crate::linalg::*;
pub use crate::matrix::{dot_flat, Matrix};
pub use crate::quantization::*;
pub use crate::rope::*;
pub use crate::sampling::*;
pub use crate::tokenizer::*;