pub struct SharedV41 {
pub compress_kv: Option<DevicePtr>,
pub compress_len: usize,
pub index_k: Option<DevicePtr>,
pub topk_idxs: Vec<i32>,
pub topk: usize,
pub candidates: Vec<bool>,
pub cand_width: usize,
}Expand description
2026-09-25: What source layers publish for the layers after them: the
latest kv source’s latent cache (compress_kv) and index-key cache
(index_k); the latest index source’s selection topk_idxs
([queries][topk], offset past the window rows, -1 = absent); the
candidate source’s mask candidates ([queries][cand_width]).
compress_len is the largest group count written so far and only grows.
Fields§
§compress_kv: Option<DevicePtr>§compress_len: usize§index_k: Option<DevicePtr>§topk_idxs: Vec<i32>§topk: usize§candidates: Vec<bool>§cand_width: usizeTrait Implementations§
Auto Trait Implementations§
Blanket Implementations§
Source§impl<T> BorrowMut<T> for Twhere
T: ?Sized,
impl<T> BorrowMut<T> for Twhere
T: ?Sized,
Source§fn borrow_mut(&mut self) -> &mut T
fn borrow_mut(&mut self) -> &mut T
Mutably borrows from an owned value. Read more