Struct InferenceConfig

pub struct InferenceConfig {
    pub max_concurrent_requests: u32,
    pub request_timeout_sec: u32,
    pub enable_batching: bool,
    pub dynamic_batching: Option<DynamicBatchingConfig>,
    pub caching: CachingConfig,
}

Inference configuration

Fields

max_concurrent_requests: u32

Maximum concurrent requests

request_timeout_sec: u32

Request timeout in seconds

enable_batching: bool

Enable batching

dynamic_batching: Option<DynamicBatchingConfig>

Dynamic batching settings

caching: CachingConfig

Caching configuration

Trait Implementations

impl Clone for InferenceConfig

fn clone(&self) -> InferenceConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for InferenceConfig

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

Formats the value using the given formatter.

impl Default for InferenceConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for InferenceConfig

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for InferenceConfig

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

where __S: Serializer,

Serialize this value into the given Serde serializer.