pub struct ResidentReplicatedDeviceRows { /* private fields */ }Expand description
One token-major F32 batch replicated across a native-P2P rank group.
Every allocation is owned by its matching rank CUDA context. This is the generic handoff substrate between independently sharded operators; it carries no model or topology claim.
Implementations§
Auto Trait Implementations§
impl Freeze for ResidentReplicatedDeviceRows
impl RefUnwindSafe for ResidentReplicatedDeviceRows
impl Send for ResidentReplicatedDeviceRows
impl Sync for ResidentReplicatedDeviceRows
impl Unpin for ResidentReplicatedDeviceRows
impl UnsafeUnpin for ResidentReplicatedDeviceRows
impl UnwindSafe for ResidentReplicatedDeviceRows
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