List of all items

Structs

• context::CachedPipeline
• context::Context
• context::ContextBuilder
• context::ContextEvent
• context::ContextId
• context::ContextInternal
• context::Macros
• model::ModelBuilder
• model::ModelInfo
• model::ModelInput
• model::StateBuilder
• model::loader::Loader
• model::loader::Lora
• model::loader::LoraBlend
• model::loader::LoraBlendPattern
• model::run::Header
• model::softmax::Softmax
• model::v4::Att
• model::v4::BackedState
• model::v4::Embed
• model::v4::Ffn
• model::v4::Head
• model::v4::Layer
• model::v4::LayerNorm
• model::v4::Model
• model::v4::ModelState
• model::v4::ModelTensor
• model::v4::Runtime
• model::v5::Att
• model::v5::BackedState
• model::v5::Embed
• model::v5::Ffn
• model::v5::Head
• model::v5::Layer
• model::v5::LayerNorm
• model::v5::Model
• model::v5::ModelState
• model::v5::ModelTensor
• model::v5::Runtime
• model::v6::Att
• model::v6::BackedState
• model::v6::Embed
• model::v6::Ffn
• model::v6::Head
• model::v6::Layer
• model::v6::LayerNorm
• model::v6::Model
• model::v6::ModelState
• model::v6::ModelTensor
• model::v6::Runtime
• runtime::JobRuntime
• runtime::infer::InferChunk
• runtime::infer::InferChunkBatch
• runtime::infer::InferInfo
• runtime::infer::InferInfoBatch
• runtime::infer::InferInput
• runtime::infer::InferInputBatch
• runtime::infer::InferIter
• runtime::infer::InferOutput
• runtime::infer::InferOutputBatch
• runtime::infer::InferRedirect
• runtime::loader::Loader
• runtime::loader::Lora
• runtime::loader::LoraBlend
• runtime::loader::LoraBlendPattern
• runtime::model::ModelBuilder
• runtime::model::ModelInfo
• runtime::v4::Att
• runtime::v4::Embed
• runtime::v4::Ffn
• runtime::v4::Frame
• runtime::v4::Head
• runtime::v4::Header
• runtime::v4::InferJob
• runtime::v4::Layer
• runtime::v4::LayerNorm
• runtime::v4::Model
• runtime::v4::ModelRuntime
• runtime::v4::ModelTensor
• runtime::v4::Runtime
• runtime::v4::State
• runtime::v5::Att
• runtime::v5::Embed
• runtime::v5::Ffn
• runtime::v5::Frame
• runtime::v5::Head
• runtime::v5::Header
• runtime::v5::InferJob
• runtime::v5::Layer
• runtime::v5::LayerNorm
• runtime::v5::Model
• runtime::v5::ModelRuntime
• runtime::v5::ModelTensor
• runtime::v5::Runtime
• runtime::v5::State
• runtime::v6::Att
• runtime::v6::Embed
• runtime::v6::Ffn
• runtime::v6::Frame
• runtime::v6::Head
• runtime::v6::Header
• runtime::v6::InferJob
• runtime::v6::Layer
• runtime::v6::LayerNorm
• runtime::v6::Model
• runtime::v6::ModelRuntime
• runtime::v6::ModelTensor
• runtime::v6::Runtime
• runtime::v6::State
• tensor::Cpu
• tensor::Cursor
• tensor::Gpu
• tensor::Tensor
• tensor::TensorGpuData
• tensor::TensorGpuView
• tensor::TensorId
• tensor::TensorStack
• tensor::View
• tensor::cache::ResourceCache
• tensor::kind::ReadWrite
• tensor::kind::Uniform
• tensor::matrix::Nf4Quant
• tensor::serialization::Seed
• tensor::shape::Shape
• tokenizer::Tokenizer

Enums

• context::CreateEnvironmentError
• model::EmbedDevice
• model::ModelError
• model::ModelOutput
• model::ModelVersion
• model::OutputType
• model::Quant
• model::v4::Hook
• model::v5::Hook
• model::v6::Hook
• runtime::infer::InferOption
• runtime::model::EmbedDevice
• runtime::model::ModelError
• runtime::model::ModelVersion
• runtime::model::Quant
• runtime::v4::Hook
• runtime::v5::Hook
• runtime::v6::Hook
• tensor::TensorError
• tensor::matrix::Matrix
• tensor::ops::Activation
• tensor::ops::TensorOp
• tensor::shape::TensorDimension
• tokenizer::TokenizerError

Traits

• context::InstanceExt
• model::BackedState
• model::Build
• model::BuildFuture
• model::ContextAutoLimits
• model::Model
• model::ModelBase
• model::ModelState
• model::loader::Reader
• model::loader::ReaderSend
• model::loader::TensorFromReader
• model::run::ModelRun
• model::softmax::ModelSoftmax
• num::CoHom
• num::Float
• num::Hom
• num::One
• num::Scalar
• num::Zero
• runtime::Job
• runtime::JobBuilder
• runtime::JobInfo
• runtime::JobInput
• runtime::loader::Reader
• runtime::loader::ReaderSend
• runtime::loader::TensorFromReader
• runtime::model::AsAny
• runtime::model::Build
• runtime::model::ContextAutoLimits
• runtime::model::ModelRuntime
• runtime::model::State
• tensor::DeepClone
• tensor::Device
• tensor::IntoPackedCursors
• tensor::TensorInit
• tensor::TensorInitContext
• tensor::TensorInto
• tensor::TensorReshape
• tensor::TensorScalar
• tensor::TensorShape
• tensor::kind::Kind
• tensor::ops::TensorCommand
• tensor::shape::IntoBytes
• tensor::shape::TensorAxis
• tensor::shape::TensorSlice

Macros

• impl_deserialize_seed

Functions

• runtime::softmax::softmax
• runtime::softmax::softmax_one
• runtime::v5::read_state
• runtime::v6::read_state

Type Aliases

• model::loader::ReaderTensor
• model::run::HookMap
• runtime::loader::ReaderTensor
• runtime::v4::HookFn
• runtime::v4::HookMap
• runtime::v5::HookFn
• runtime::v5::HookMap
• runtime::v6::HookFn
• runtime::v6::HookMap
• tensor::TensorCpu
• tensor::TensorGpu

Constants

• model::MIN_TOKEN_CHUNK_SIZE
• model::RESCALE_LAYER
• runtime::infer::MIN_TOKEN_CHUNK_SIZE
• runtime::infer::NUM_LAYER_CHUNK