Struct WorkerConfigRequest 

pub struct WorkerConfigRequest {

    pub url: String,
    pub api_key: Option<String>,
    pub model_id: Option<String>,
    pub priority: Option<u32>,
    pub cost: Option<f32>,
    pub worker_type: Option<String>,
    pub bootstrap_port: Option<u16>,
    pub runtime: Option<String>,
    pub tokenizer_path: Option<String>,
    pub reasoning_parser: Option<String>,
    pub tool_parser: Option<String>,
    pub chat_template: Option<String>,
    pub labels: HashMap<String, String>,
    pub health_check_timeout_secs: u64,
    pub health_check_interval_secs: u64,
    pub health_success_threshold: u32,
    pub health_failure_threshold: u32,
    pub disable_health_check: bool,
    pub max_connection_attempts: u32,
    pub dp_aware: bool,
}

Worker configuration for API requests

Fields

url: String

Worker URL (required)

api_key: Option<String>

Worker API key (optional)

model_id: Option<String>

Model ID (optional, will query from server if not provided)

priority: Option<u32>

Worker priority (optional, default: 50, higher = preferred)

cost: Option<f32>

Worker cost factor (optional, default: 1.0)

worker_type: Option<String>

Worker type (optional: “regular”, “prefill”, “decode”)

bootstrap_port: Option<u16>

Bootstrap port for prefill workers (optional)

runtime: Option<String>

Runtime type (optional: “sglang”, “vllm”, default: “sglang”) Only relevant for gRPC workers

tokenizer_path: Option<String>

Tokenizer path for gRPC mode

reasoning_parser: Option<String>

Reasoning parser type for gRPC mode

tool_parser: Option<String>

Tool parser type for gRPC mode

chat_template: Option<String>

Chat template for gRPC mode

labels: HashMap<String, String>

Additional labels (optional)

health_check_timeout_secs: u64

Health check timeout in seconds (default: 30)

health_check_interval_secs: u64

Health check interval in seconds (default: 60)

health_success_threshold: u32

Number of successful health checks needed to mark worker as healthy (default: 2)

health_failure_threshold: u32

Number of failed health checks before marking worker as unhealthy (default: 3)

disable_health_check: bool

Disable periodic health checks for this worker (default: false)

max_connection_attempts: u32

Maximum connection attempts during worker registration (default: 20)

dp_aware: bool

Enable data parallelism aware scheduling (default: false)

Trait Implementations

impl Clone for WorkerConfigRequest

fn clone(&self) -> WorkerConfigRequest

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for WorkerConfigRequest

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for WorkerConfigRequest

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for WorkerConfigRequest

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

where __S: Serializer,

Serialize this value into the given Serde serializer.