Enum InferenceBackend 

pub enum InferenceBackend {
    CandleCpu,
    CandleCuda,
    OnnxRuntime,
    Mock,
}

The compute backend used for local inference.

Variants

CandleCpu

CPU-only inference via candle (no GPU required).

CandleCuda

GPU inference via candle + CUDA.

OnnxRuntime

ONNX Runtime (CPU or GPU via execution provider).

Mock

Mock backend for tests — deterministic, no model files.

Implementations

impl InferenceBackend

pub fn as_str(&self) -> &'static str

Trait Implementations

impl Clone for InferenceBackend

fn clone(&self) -> InferenceBackend

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for InferenceBackend

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

Formats the value using the given formatter.

impl Eq for InferenceBackend

impl PartialEq for InferenceBackend

fn eq(&self, other: &InferenceBackend) -> 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 InferenceBackend