ferrum-kv 0.7.1

KV cache management with PagedAttention for Ferrum inference
Documentation
1
2
3
4
5
6
7
pub mod default;
pub mod eviction;
pub mod paged;

pub use default::DefaultKvCacheManager;
pub use eviction::{EvictionPolicy, FIFOEviction, LRUEviction};
pub use paged::{PagedKvCacheConfig, PagedKvCacheHandle, PagedKvCacheManager};