List of all items
Structs
- BatchId
- BatchPlan
- EngineConfig
- EngineStatus
- GreedySampler
- InferenceRequest
- InferenceResponse
- RequestId
- StreamChunk
- builder::EngineBuilder
- continuous_engine::ContinuousBatchEngine
- continuous_engine::SequenceState
- embedding_engine::EmbeddingEngine
- parallel::config::LayerDistribution
- parallel::config::LayerRange
- parallel::config::ParallelConfig
- parallel::device::DeviceCapability
- parallel::device::DeviceInfo
- parallel::device::DeviceManager
- parallel::executor::ParallelExecutorFactory
- parallel::executor::ParallelStrategySelector
- parallel::executor::SimulatedParallelExecutor
- parallel::executor::SingleGpuExecutor
- parallel::tensor_parallel::TensorParallelConfig
- parallel::tensor_parallel::TensorParallelGroup
- parallel::tensor_parallel::TransformerParallelMapping
- parallel::tensor_parallel::WeightShard
- pipeline::chunked_prefill::ChunkedPrefillConfig
- pipeline::chunked_prefill::ChunkedPrefillExecutor
- pipeline::chunked_prefill::ChunkedPrefillState
- pipeline::executor::PipelineConfig
- pipeline::executor::PipelineExecutor
- pipeline::executor::PipelineSequence
- pipeline::executor::PipelineStatsSnapshot
- recurrent_state::InMemoryRecurrentStateConfig
- recurrent_state::InMemoryRecurrentStateHandle
- recurrent_state::InMemoryRecurrentStateManager
- registry::ComponentConfig
- registry::ComponentMetadata
- registry::ComponentRegistry
- registry::ContinuousBatchSchedulerFactory
- registry::DefaultKvCacheFactory
- registry::FifoSchedulerFactory
- registry::GreedySampler
- registry::GreedySamplerFactory
- registry::HuggingFaceTokenizerFactory
- registry::LlmExecutorFactory
- registry::MultinomialSamplerFactory
- registry::PagedKvCacheFactory
- registry::PrioritySchedulerFactory
- registry::StubExecutorFactory
- registry::StubTokenizer
- registry::StubTokenizerFactory
- speculative::Speculation
- speculative::SpeculationOutcome
- speculative::SpeculativeDecodingConfig
- speculative::SpeculativeRunner
- speculative::SpeculativeStepOutcome
- tensor_factory::candle::CandleTensor
- tensor_factory::candle::CandleTensorFactory
- tensor_factory::candle::CandleTensorOps
- transcription_engine::TranscriptionEngine
- tts_engine::TtsService
Enums
- FerrumError
- parallel::config::ParallelismType
- parallel::tensor_parallel::LayerParallelType
- pipeline::executor::ExecutionPhase
Traits
- EmbedEngine
- IncrementalTokenizer
- InferenceEngineInterface
- KvCacheManager
- LlmInferenceEngine
- ModelExecutor
- Sampler
- Scheduler
- Tokenizer
- TranscribeEngine
- TtsEngine
- parallel::executor::ParallelExecutor
- registry::ComponentFactory
Functions
- builder::create_engine
- builder::create_prepared_product_engine
- builder::create_product_engine
- create_default_engine
- modality_stubs::inert_health
- modality_stubs::inert_metrics
- modality_stubs::inert_status
- parallel::device::global_device_manager
- registry::global_registry
- registry::set_global_registry
- speculative::verify_speculation