Enum PrecisionPolicy 

pub enum PrecisionPolicy {
    Fp32,
    Fp16,
    Int8 {
        calibration_table: PathBuf,
    },
}

TensorRT precision policy — controls EP optimization flags.

Variants

Fp32

FP32 only — maximum accuracy, baseline performance.

Fp16

FP16 mixed precision — 2× throughput on Tensor Cores.

Int8

INT8 quantized with calibration table — 4× throughput. Requires a pre-generated calibration table path.

Fields

calibration_table: PathBuf

Trait Implementations

impl Clone for PrecisionPolicy

fn clone(&self) -> PrecisionPolicy

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for PrecisionPolicy

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

Formats the value using the given formatter.

impl Default for PrecisionPolicy

fn default() -> PrecisionPolicy

Returns the “default value” for a type.