Struct InferenceParams 

pub struct InferenceParams {
    pub max_tokens: u32,
    pub temperature: f32,
    pub context_size: u32,
    pub n_threads: u32,
}

Inference parameters for a single generation request.

Fields

max_tokens: u32

Maximum number of tokens to generate in the response.

temperature: f32

Sampling temperature (0.0 = deterministic, higher = more random).

context_size: u32

Context window size in tokens to allocate for this request.

n_threads: u32

Number of CPU threads to use for inference.

Trait Implementations

impl Clone for InferenceParams

fn clone(&self) -> InferenceParams

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for InferenceParams

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

Formats the value using the given formatter.

impl Default for InferenceParams

fn default() -> Self

Returns the “default value” for a type.