pub struct PreppedVideo {
pub groups: Vec<PreppedImage>,
pub timestamps: Vec<f32>,
}Expand description
One prepared VIDEO: temporal groups as PreppedImage units (each = one pad run of
gh*gw/4 tokens) + per-group timestamps for the HF placeholder format
(<t.t seconds> before each group’s pad run). Groups forward TOGETHER through
VisionTower::forward_seq — one attention span per video, the HF cu_seqlens law.
Fields§
§groups: Vec<PreppedImage>§timestamps: Vec<f32>Auto Trait Implementations§
impl Freeze for PreppedVideo
impl RefUnwindSafe for PreppedVideo
impl Send for PreppedVideo
impl Sync for PreppedVideo
impl Unpin for PreppedVideo
impl UnsafeUnpin for PreppedVideo
impl UnwindSafe for PreppedVideo
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