#[non_exhaustive]pub enum NaxStatus {
Active {
forced: bool,
},
Off(NaxReason),
}Expand description
Whether products run on the Neural Accelerator kernels (crate::Device::nax).
Variants (Non-exhaustive)§
This enum is marked as non-exhaustive
Non-exhaustive enums could have additional variants added in future. Therefore, when matching against variants of non-exhaustive enums, an extra wildcard arm must be added to account for any future variants.
Active
They run where MLX would route to its NAX kernels; forced when NUVEC_NAX=on
enabled them on a GPU MLX would not (TensorOps run on every Apple GPU of macOS 26.2,
not on matrix units).
Off(NaxReason)
They do not run.
Implementations§
Trait Implementations§
impl Copy for NaxStatus
impl Eq for NaxStatus
impl StructuralPartialEq for NaxStatus
Auto Trait Implementations§
impl Freeze for NaxStatus
impl RefUnwindSafe for NaxStatus
impl Send for NaxStatus
impl Sync for NaxStatus
impl Unpin for NaxStatus
impl UnsafeUnpin for NaxStatus
impl UnwindSafe for NaxStatus
Blanket Implementations§
impl<T> AutoreleaseSafe for Twhere
T: ?Sized,
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