Struct ExecuteBatch 

pub struct ExecuteBatch {
    pub request_id: String,
    pub model: String,
    pub messages: Vec<Message>,
    pub sampling: SamplingParams,
    pub stream: bool,
    pub estimated_tokens: u32,
}

One unit of work handed to a ModelRunner. request_id is the RequestActor’s identifier so completions can be correlated back.

Fields

request_id: String

model: String

messages: Vec<Message>

sampling: SamplingParams

stream: bool

True if the caller wants token-by-token streaming (Tokens chunks). False if a single final Tokens is acceptable.

estimated_tokens: u32

Best-effort estimate of input + max_output tokens, used by RateLimiterActor to acquire a TPM permit before the request hits the wire.

Implementations

impl ExecuteBatch

pub fn estimated_tokens(&self) -> u32

Trait Implementations

impl Clone for ExecuteBatch

fn clone(&self) -> ExecuteBatch

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ExecuteBatch

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for ExecuteBatch

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for ExecuteBatch

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

where __S: Serializer,

Serialize this value into the given Serde serializer.