Struct CompareConfig 

pub struct CompareConfig {
    pub model_ids: Vec<i64>,
    pub prompt: String,
    pub system_prompt: Option<String>,
    pub inference: Option<InferenceConfig>,
    pub ctx_size: Option<u64>,
}

Configuration for a compare benchmark run.

Fields

model_ids: Vec<i64>

Models to benchmark (by database ID), run sequentially.

prompt: String

Prompt text to send to every model.

system_prompt: Option<String>

Optional system prompt.

inference: Option<InferenceConfig>

Per-request inference overrides (temperature, max_tokens, etc.).

ctx_size: Option<u64>

Override the llama-server context window size for this run.

When None the benchmark service falls back to the app-wide default_context_size setting (same fallback the proxy uses).

Trait Implementations

impl Clone for CompareConfig

fn clone(&self) -> CompareConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for CompareConfig

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for CompareConfig

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for CompareConfig

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.