Struct InferenceRequest 

pub struct InferenceRequest {
    pub task: Task,
    pub model: String,
    pub inputs: Vec<String>,
    pub params: InferenceParams,
}

One batch of inputs to run through a model. A request is homogeneous: a single task, a single model, and one input string per row in order.

Fields

task: Task

The task being performed.

model: String

Runtime model identifier — the vendor model id for remote backends, or the weight source for local backends.

inputs: Vec<String>

One input string per row, in row order.

params: InferenceParams

Task-shaping parameters that also version the result cache.

Trait Implementations

impl Clone for InferenceRequest

fn clone(&self) -> InferenceRequest

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for InferenceRequest

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

Formats the value using the given formatter.

impl PartialEq for InferenceRequest

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