tpt-gpu-model-optimizer 0.1.0

Hardware-aware LLM model optimizer: quantization, surgical pruning, and TPTF export
Documentation
1
2
3
4
5
6
7
pub mod detect;
pub mod exl2;
pub mod gguf;

pub use detect::{detect, ModelFormat};
pub use exl2::{Exl2ExportConfig, Exl2Exporter};
pub use gguf::{GgufExportConfig, GgufExporter};