pub struct KvFp8;Expand description
FP8 KV cache — E4M3 by default. Hopper+ on CUDA, future on Metal.
Trait Implementations§
Auto Trait Implementations§
impl Freeze for KvFp8
impl RefUnwindSafe for KvFp8
impl Send for KvFp8
impl Sync for KvFp8
impl Unpin for KvFp8
impl UnsafeUnpin for KvFp8
impl UnwindSafe for KvFp8
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