20 lines
633 B
Rust
20 lines
633 B
Rust
//! Request management and lifecycle tracking
|
|
//!
|
|
//! This module handles inference requests from submission through completion,
|
|
//! including priority management, SLA tracking, and metrics collection.
|
|
|
|
mod config;
|
|
mod inference_request;
|
|
mod manager;
|
|
mod queue;
|
|
mod result;
|
|
mod tests;
|
|
mod types;
|
|
|
|
pub use config::{CacheStats, RequestManagerConfig, RequestManagerStats};
|
|
pub use inference_request::InferenceRequest;
|
|
pub use manager::RequestManager;
|
|
pub use queue::{OverflowStrategy, PriorityQueue, QueueStats};
|
|
pub use result::{FinishReason, RequestMetrics, RequestResult};
|
|
pub use types::{RequestId, RequestPriority, RequestStatus};
|