Struct BenchResult 

pub struct BenchResult {
    pub metrics: Vec<(String, f64)>,
    pub iters: usize,
}

Structured output of a single bench run: named metrics (e.g. (“evaltime”, secs), (“pp512”, tok/s)) plus the loop iteration count for the human report line. The bench/llm-bench runners return this so callers — the interactive subcommand or the bench suite — consume data instead of parsing stdout.

Fields

metrics: Vec<(String, f64)>

iters: usize

Implementations

impl BenchResult

pub fn emit_jsonl(&self)

Emit each metric as a {"metric":<name>,"value":<f64>} JSON line on stdout. This is the bench-suite child→orchestrator contract: stdout is pure JSONL (logs go to stderr), so the orchestrator can validate every line and treat anything that does not parse as a hard failure.

Trait Implementations

impl Clone for BenchResult

fn clone(&self) -> BenchResult

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for BenchResult

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

Formats the value using the given formatter.

impl Default for BenchResult

fn default() -> BenchResult

Returns the “default value” for a type.