boostr 0.1.0

ML framework built on numr - attention, quantization, model architectures
Documentation 
1
2
3
4
5

pub mod kv_cache;
pub mod kv_cache_quant;

pub use kv_cache::KvCacheOps;
pub use kv_cache_quant::{Int4GroupSize, KvCacheQuantOps, KvQuantMode};