List of all items
Structs
- BackendInfo
- BatchProcessor
- BatchProcessorBuilder
- CacheConfig
- CacheConfigBuilder
- EmbeddingConfig
- EmbeddingConfigBuilder
- EmbeddingEngine
- EmbeddingModel
- EngineConfig
- EngineConfigBuilder
- GGUFMetadata
- ModelConfig
- ModelConfigBuilder
- ModelInfo
- RerankResult
- VersionInfo
- cache::CacheStats
- cache::embedding_cache::EmbeddingCache
- cache::memory_monitor::MemoryMonitor
- cache::memory_monitor::MemoryMonitorConfig
- cache::memory_monitor::MemoryStats
- cache::metrics::CacheMetrics
- cache::metrics::MetricsReport
- cache::prefix_cache::PrefixCache
- cache::prefix_cache::PrefixCacheStats
- cache::prefix_cache::PrefixDetector
- cache::prefix_cache::SessionData
- cache::token_cache::TokenCache
- server::FileModelProvider
- server::api_types::CacheClearResponse
- server::api_types::CacheStatsResponse
- server::api_types::CacheWarmRequest
- server::api_types::CacheWarmResponse
- server::api_types::EmbeddingData
- server::api_types::EmbeddingsRequest
- server::api_types::EmbeddingsResponse
- server::api_types::ErrorDetail
- server::api_types::ErrorResponse
- server::api_types::ListModelsResponse
- server::api_types::MemoryInfo
- server::api_types::ModelData
- server::api_types::PrefixInfo
- server::api_types::PrefixListResponse
- server::api_types::PrefixRegisterRequest
- server::api_types::PrefixRegisterResponse
- server::api_types::PrefixStatsResponse
- server::api_types::RerankRequest
- server::api_types::RerankResponse
- server::api_types::RerankResultData
- server::api_types::RerankUsage
- server::api_types::Usage
- server::backpressure::CircuitBreaker
- server::backpressure::CircuitBreakerConfig
- server::backpressure::CircuitBreakerStats
- server::backpressure::HealthStatus
- server::backpressure::LoadShedder
- server::backpressure::SystemHealth
- server::channel::WorkerRequest
- server::channel::WorkerResponse
- server::dispatcher::Dispatcher
- server::inference_worker::InferenceConfig
- server::inference_worker::InferenceWorker
- server::middleware::ApiKeyConfig
- server::rate_limiter::ClientRateLimiter
- server::rate_limiter::RateLimitConfig
- server::state::AppState
- server::state::ServerConfig
- server::state::ServerConfigBuilder
- server::worker::Worker
Enums
- BackendType
- Error
- NormalizationMode
- PoolingStrategy
- TruncateTokens
- server::api_types::EmbeddingValue
- server::api_types::InputType
- server::backpressure::CircuitState
- server::channel::TextInput
Traits
Functions
- clear_metadata_cache
- detect_best_backend
- extract_gguf_metadata
- get_compiled_backend
- init
- init_with_env_filter
- metadata_cache_size
- server::cache_handlers::cache_clear_handler
- server::cache_handlers::cache_stats_handler
- server::cache_handlers::cache_warm_handler
- server::cache_handlers::prefix_clear_handler
- server::cache_handlers::prefix_list_handler
- server::cache_handlers::prefix_register_handler
- server::cache_handlers::prefix_stats_handler
- server::create_router
- server::handlers::embeddings_handler
- server::handlers::list_models_handler
- server::handlers::rerank_handler
- server::metrics::decrement_active_requests
- server::metrics::export_metrics
- server::metrics::increment_active_requests
- server::metrics::init_metrics
- server::metrics::record_inference_time
- server::metrics::record_rate_limited
- server::metrics::record_request_failure
- server::metrics::record_request_success
- server::metrics::update_queue_depth
- server::metrics::update_worker_utilization
- server::middleware::authenticate_api_key
- server::middleware::extract_request_id
- server::middleware::inject_request_id
- server::middleware::limit_request_size
- server::rate_limiter::extract_client_id
- server::rate_limiter::rate_limit_middleware
- server::run_server
- version_info
Type Aliases
Statics
- server::metrics::ACTIVE_REQUESTS
- server::metrics::ERROR_COUNTER
- server::metrics::INFERENCE_DURATION
- server::metrics::QUEUE_DEPTH
- server::metrics::RATE_LIMITED_REQUESTS
- server::metrics::REQUEST_COUNTER
- server::metrics::REQUEST_DURATION
- server::metrics::WORKER_UTILIZATION