Enum MmaPrecision 

pub enum MmaPrecision {
    Fp16Fp32,
    Bf16Fp32,
    Tf32,
    Int8Int32,
    Fp32,
}

Precision mode for tensor core operations.

Variants

Fp16Fp32

fp16 inputs, fp32 accumulation (HMMA)

Bf16Fp32

bf16 inputs, fp32 accumulation

Tf32

fp32 inputs, fp32 accumulation (TF32 on Ampere+)

Int8Int32

int8 inputs, int32 accumulation (IMMA)

Fp32

Full fp32 (no tensor cores, standard GEMM)

Trait Implementations

impl Clone for MmaPrecision

fn clone(&self) -> MmaPrecision

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Copy for MmaPrecision

impl Debug for MmaPrecision

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl PartialEq for MmaPrecision

fn eq(&self, other: &MmaPrecision) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for MmaPrecision