List of all items

Structs

• auto_config::AutoConfigDecision
• auto_config::CompiledKernelFeatures
• auto_config::CompiledNativeOperatorArtifact
• auto_config::FerrumConfigBuilder
• auto_config::HardwareCapabilities
• auto_config::ModelCapabilities
• auto_config::MoeCapabilities
• auto_config::RejectedCandidate
• auto_config::ResolvedFerrumConfig
• auto_config::WorkloadProfile
• config::BackendConfig
• config::BatchConfig
• config::EngineConfig
• config::EngineModelConfig
• config::KvCacheConfig
• config::MemoryCapacityBudget
• config::MemoryConfig
• config::MonitoringConfig
• config::PaddingConfig
• config::ReusableExecutionCaptureConfig
• config::RuntimeKnobs
• config::SamplingConfig
• config::SchedulerConfig
• config::SecurityConfig
• config::TokenizerConfig
• config::TruncationConfig
• config::VNextCheckpointCaptureConfig
• config::VNextTeacherForcingConfig
• execution_policy::ExecutorAdmissionLimits
• execution_policy::ExecutorAdmissionSnapshot
• ids::BatchId
• ids::ClientId
• ids::ModelId
• ids::RequestId
• ids::SessionId
• ids::TaskId
• ids::TokenId
• metrics::AllocationInfo
• metrics::BatchingMetrics
• metrics::BuildInfo
• metrics::CacheStats
• metrics::ComponentHealth
• metrics::ComponentStatus
• metrics::DetailedResourceUsage
• metrics::DiagnosticsReport
• metrics::DiskMetrics
• metrics::EngineMetrics
• metrics::EngineRequestProgress
• metrics::EngineRequestState
• metrics::EngineState
• metrics::EngineStatus
• metrics::ErrorEvent
• metrics::ErrorStats
• metrics::GpuMemoryDetails
• metrics::GpuMetrics
• metrics::HardwareConstraints
• metrics::HealthStatus
• metrics::LatencyMetrics
• metrics::LatencyRequirements
• metrics::MemoryUsage
• metrics::ModelMetrics
• metrics::NetworkIODetails
• metrics::NetworkMetrics
• metrics::PerformanceAnalysis
• metrics::PerformanceBottleneck
• metrics::PerformanceBreakdown
• metrics::PerformanceRecommendation
• metrics::PerformanceTrends
• metrics::PhaseMetrics
• metrics::PrefixCacheStats
• metrics::QueueMetrics
• metrics::RequestCharacteristics
• metrics::RequestMetrics
• metrics::ResourceMetrics
• metrics::RuntimeInfo
• metrics::SchedulerStats
• metrics::SpeculationConfig
• metrics::SystemInfo
• metrics::SystemMetrics
• metrics::ThroughputMetrics
• metrics::WarmupResult
• models::AttentionConfig
• models::ModelConfig
• models::ModelInfo
• models::ModelMemoryRequirements
• models::RopeScaling
• models::TokenUsage
• native_operator::CompiledNativeOperatorIdentity
• native_operator::NativeOperatorAbiContract
• native_operator::NativeOperatorAbiField
• native_operator::NativeOperatorBinding
• native_operator::NativeOperatorBuildSummary
• native_operator::NativeOperatorContractVersion
• native_operator::NativeOperatorManifest
• native_operator::NativeOperatorProviderCatalog
• native_operator::NativeOperatorProviderCatalogRow
• native_operator::NativeOperatorRequirement
• native_operator::NativeOperatorResolution
• native_operator::NativeOperatorSourcePackage
• observability_profile::FerrumObservabilityConfig
• observability_profile::FerrumProfileEvent
• observability_profile::MemorySnapshot
• observability_profile::ProfileError
• observability_profile::ReplayReference
• process_memory::ProcessMemoryObservation
• process_memory::ProcessMemorySample
• process_memory::ProcessMemorySampler
• reasoning::ParsedReasoningResponse
• requests::ApiChatMessage
• requests::ApiChatRequest
• requests::ApiChatResponse
• requests::ApiCompletionRequest
• requests::ApiCompletionResponse
• requests::ApiFunction
• requests::ApiFunctionCall
• requests::ApiJsonSchema
• requests::ApiResponseFormat
• requests::ApiStreamOptions
• requests::ApiTool
• requests::ApiToolCall
• requests::ApiToolChoiceFunction
• requests::BatchRequest
• requests::EngineDecodeStageInterval
• requests::EngineTokenTimingEvidence
• requests::InferenceEvidenceRequest
• requests::InferenceExecutionEvidence
• requests::InferenceRequest
• requests::InferenceResponse
• requests::ScheduledRequest
• requests::StreamChunk
• resource_trace::ResourceTraceEvent
• runtime_config::RuntimeConfigEntry
• runtime_config::RuntimeConfigSnapshot
• sampling::MirostatParams
• sampling::ResponseCompletionEnvelope
• sampling::SamplingParams
• sampling::SamplingPresets
• sampling::SpecialTokens

Enums

• auto_config::AutoConfigError
• auto_config::AutoConfigSource
• auto_config::WorkloadPriority
• config::BackendType
• config::KvCacheDtype
• config::KvCacheType
• config::PaddingStrategy
• config::SchedulingPolicy
• config::SequenceFitPolicy
• config::TokenizerType
• config::TruncationStrategy
• config::VNextDiagnosticFault
• devices::DataType
• devices::Device
• errors::FerrumError
• execution_policy::AttentionExecutionPolicy
• execution_policy::ExecutionResourceAuthority
• metrics::HealthStatusType
• metrics::TrendDirection
• models::Activation
• models::ModelSource
• models::ModelType
• models::NormType
• models::QuantizationConfig
• native_operator::NativeOperatorBackend
• native_operator::NativeOperatorLinkage
• observability_profile::ObservabilityProfileDetail
• observability_profile::ProfileEntrypoint
• observability_profile::ProfileEventKind
• observability_profile::ProfileStatus
• requests::ApiFunctionCallChoice
• requests::ApiMessageRole
• requests::ApiRequest
• requests::ApiResponse
• requests::ApiToolCallProtocol
• requests::ApiToolChoice
• requests::EngineDecodeStage
• requests::RequestState
• resource_trace::ResourceAction
• runtime_config::EnvTriState
• runtime_config::RuntimeConfigEffect
• runtime_config::RuntimeConfigSource
• sampling::FinishReason
• sampling::Priority
• sampling::ResponseCompletionBoundary
• sampling::ResponseFormat
• sampling::StructuredOutputStart

Functions

• native_operator::is_sha256_digest
• native_operator::resolve_native_operator_manifest
• observability_profile::engine_token_timing_profile_attributes
• process_memory::sample_process_memory
• reasoning::has_unclosed_thinking_block
• reasoning::parse_reasoning_response
• reasoning::parse_reasoning_response_for_prompt
• reasoning::parse_reasoning_response_started_in_think
• requests::api_response_from_generated_text
• requests::chat_api_may_emit_tool_or_function_call
• requests::chat_api_response_from_generated_text
• runtime_config::active_runtime_snapshot
• runtime_config::install_runtime_snapshot
• runtime_config::parse_bool_env_value
• runtime_config::parse_path_env_value
• runtime_config::parse_tri_state_env_value
• runtime_config::parse_usize_env_value

Type Aliases

• BlockId
• Result
• metrics::ComponentHealthStatus

Constants

• auto_config::M3_QWEN3_30B_A3B_INT4_PRESET
• auto_config::QWEN25_72B_GPTQ_INT4_2X4090_LAYER_SPLIT_PRESET
• config::DEFAULT_MAXIMUM_AUTOMATIC_EXACT_DECODE_WIDTH
• config::MAXIMUM_REUSABLE_EXECUTION_STARTUP_CAPTURE_WIDTH
• config::MAX_VNEXT_TEACHER_FORCED_TOKENS
• execution_policy::CUDA_NATIVE_ADAPTIVE_V1_MAX_SEQUENCE_TOKENS
• native_operator::DEFAULT_NATIVE_OPERATOR_ABI_VERSION
• native_operator::FERRUM_NATIVE_OPERATOR_ABI_VERSION
• native_operator::LEGACY_FERRUM_NATIVE_OPERATOR_ABI_VERSION
• native_operator::LEGACY_NATIVE_OPERATOR_MANIFEST_SCHEMA_VERSION
• native_operator::NATIVE_OPERATOR_ABI_CONTRACT_SCHEMA_VERSION
• native_operator::NATIVE_OPERATOR_MANIFEST_SCHEMA_VERSION
• native_operator::NATIVE_OPERATOR_PROVIDER_CATALOG_SCHEMA_VERSION
• native_operator::PROVIDER_BOUND_NATIVE_OPERATOR_MANIFEST_SCHEMA_VERSION
• observability_profile::DEFAULT_OBSERVABILITY_PROFILE_SAMPLE_RATE
• observability_profile::ENGINE_RUNTIME_TRACE_PRESET_HASH
• observability_profile::OBSERVABILITY_PROFILE_SCHEMA_VERSION
• observability_profile::SYNTHETIC_RUNTIME_PRESET_HASH
• reasoning::THINK_END_TAG
• reasoning::THINK_START_TAG
• requests::DEFAULT_MAX_TOKENS_METADATA_KEY
• requests::PROMPT_TOKENS_METADATA_KEY
• sampling::DEFAULT_CHAT_REPETITION_PENALTY