Enum Device 

pub enum Device {
    Cpu,
    Cuda(usize),
    Mps,
    CoreMl,
    DirectMl(usize),
    OpenVino,
    Xnnpack,
    TensorRt(usize),
    Rocm(usize),
}

Hardware device for inference.

Variants

Cpu

CPU (Central Processing Unit).

Cuda(usize)

CUDA (Compute Unified Device Architecture) for NVIDIA GPUs. The argument specifies the device index (e.g., 0 for the first GPU).

Mps

MPS (Metal Performance Shaders) for Apple Silicon (macOS).

CoreMl

CoreML (Apple Core Machine Learning).

DirectMl(usize)

DirectML (Direct Machine Learning) for Windows. The argument specifies the device index.

OpenVino

OpenVINO (Open Visual Inference and Neural Network Optimization) for Intel hardware.

Xnnpack

XNNPACK (optimized floating-point neural network inference operators) for CPU.

TensorRt(usize)

TensorRT (NVIDIA TensorRT) for high-performance deep learning inference. The argument specifies the device index.

Rocm(usize)

ROCm (Radeon Open Compute) for AMD GPUs. The argument specifies the device index.

Trait Implementations

impl Clone for Device

fn clone(&self) -> Device

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Device

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

Formats the value using the given formatter.

impl Display for Device

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

Formats the value using the given formatter.

impl FromStr for Device

type Err = String

The associated error which can be returned from parsing.

fn from_str(s: &str) -> Result<Self, Self::Err>

Parses a string s to return a value of this type.

impl PartialEq for Device

fn eq(&self, other: &Device) -> 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 Eq for Device

impl StructuralPartialEq for Device