Struct BenchConfig 

pub struct BenchConfig {
    pub label: String,
    pub model_path: String,
    pub quantization: String,
    pub prompt: String,
    pub decode_tokens: u32,
    pub warm_repeats: u32,
}

One benchmark case: a model + prompt to drive through the real path.

Fields

label: String

Human-readable row label, e.g. “SmolLM2-360M Q8”.

model_path: String

Path to the GGUF on disk.

quantization: String

Descriptive quantization tag for the report (e.g. “Q8_0”).

prompt: String

Prompt to run.

decode_tokens: u32

Fixed decode-token count for a bounded, comparable measurement (0 = production default).

warm_repeats: u32

Warm repeats to average over (≥1). Cold is always a single fresh run.

Implementations

impl BenchConfig

pub fn new( label: impl Into<String>, model_path: impl Into<String>, quantization: impl Into<String>, prompt: impl Into<String>, ) -> Self

Trait Implementations

impl Clone for BenchConfig

fn clone(&self) -> BenchConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for BenchConfig

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

Formats the value using the given formatter.