pub struct EmbedOverlay {
pub rows: DevicePtr,
pub ids_dev: DevicePtr,
pub slot_map: DevicePtr,
pub n_override: u32,
pub vocab: u32,
pub lmhead: Option<LmHeadOverlay>,
}Expand description
2026-09-25: One adapter slot’s embed overlay: rows ([n_override, h]
BF16) in the order of ids_dev (ascending u32 vocab ids), and slot_map
(i32 [vocab], the row index for an overridden id, else -1), which the
embed kernel indexes by token id. lmhead is Some only for an untied head
with its own overlay tensors.
Fields§
§rows: DevicePtr§ids_dev: DevicePtr§slot_map: DevicePtr§n_override: u32§vocab: u322026-09-25: The length of slot_map, the served vocab; the embed
kernel skips token ids >= vocab (token_overlay.cu).
lmhead: Option<LmHeadOverlay>Trait Implementations§
Auto Trait Implementations§
impl Freeze for EmbedOverlay
impl RefUnwindSafe for EmbedOverlay
impl Send for EmbedOverlay
impl Sync for EmbedOverlay
impl Unpin for EmbedOverlay
impl UnwindSafe for EmbedOverlay
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