Inheritance diagram for Mila::Dnn::LlamaBlock< TDeviceType, TPrecision, TWeightQuant, TKvPolicy >:

Classes
struct	BlockBuildContexts
	The per-child build contexts this block implies. More...

Public Types
using	AttentionType = GroupedQueryAttention<TDeviceType, TPrecision, TKvPolicy>
using	CompositeComponentBase = CompositeComponent<TDeviceType, TPrecision>
using	LinearType = Linear<TDeviceType, TPrecision, TWeightQuant>
using	MR = typename DeviceTypeTraits<TDeviceType>::memory_resource
using	ResidualType = Residual<TDeviceType, TPrecision>
using	RmsNormType = RmsNorm<TDeviceType, TPrecision>
using	RopeType = Rope<TDeviceType, TPrecision>
using	SwiGLUType = Swiglu<TDeviceType, TPrecision>
using	TensorType = Tensor<TPrecision, MR>
Public Types inherited from Mila::Dnn::CompositeComponent< TDeviceType, TPrecision >
using	ComponentBase = Component<TDeviceType, TPrecision>
using	ComponentPtr = std::shared_ptr<Component<TDeviceType, TPrecision>>

Public Member Functions
	LlamaBlock (const std::string &name, const LlamaConfig &config, std::optional< DeviceId > device_id=std::nullopt)
TensorType &	backward (const TensorType &input, const TensorType &output_grad)
TensorType &	decode (const TensorType &input, dim_t position)
TensorType &	forward (const TensorType &input)
MemoryStats	getMemoryStats () const override
	Return the current memory allocation breakdown for this component.
MemoryStats	getRequiredMemory (const BuildContext &context) const override
	What onBuilding() would allocate for this context, without allocating.
const ComponentType	getType () const override
	Get the component type identifier.
TensorType &	prefill (const TensorType &input, dim_t position_offset)
void	resetKVCache ()
void	setState (const GqaState &state)
	Forward the shared GQA transient workspace to this block's attention layer.
bool	supportsKVCache () const noexcept
void	zeroGradients () override
	Clear all model-owned gradients for this component.
Public Member Functions inherited from Mila::Dnn::CompositeComponent< TDeviceType, TPrecision >
	CompositeComponent (CompositeComponent &&) noexcept=default
	CompositeComponent (const CompositeComponent &)=delete
	CompositeComponent (const std::string &name)
	Construct composite component with name.
CompositeComponent &	addComponent (ComponentPtr component)
	Add a pre-constructed child component (chainable).
size_t	childCount () const noexcept
	Get the number of direct children.
void	clearComponents ()
	Clear all child components.
ComponentPtr	findComponent (const std::string &path) const
	Resolve a dot-separated component path within this composite.
ComponentPtr	getComponent (const std::string &name) const
	Retrieve a direct child component by name.
const std::vector< ComponentPtr > &	getComponents () const
	Get all child components in insertion order.
DeviceId	getDeviceId () const override
	Get the compute device for this composite.
std::vector< ITensor * >	getGradients () const override
	Get all parameter gradients from all children.
std::vector< ITensor * >	getParameters () const override
	Get all parameters from all children.
bool	hasChildren () const noexcept
	Check if this composite has any children.
bool	hasComponent (const std::string &name) const
	Check if a named child component exists.
CompositeComponent &	operator= (CompositeComponent &&) noexcept=default
CompositeComponent &	operator= (const CompositeComponent &)=delete
dim_t	parameterCount () const override
	Count parameters across all children.
bool	removeComponent (const std::string &name)
void	saveFlatTensors (Serialization::SafeTensorsWriter &writer, const std::string &prefix, Serialization::TensorSavePass pass) const override
	Recurse into children, extending the flat dotted prefix.
void	synchronize () override
	Synchronize all child components.
std::string	toString () const override
	Generate a human-readable description.
ComponentPtr	tryFindComponent (const std::string &path) const
	Try to resolve a dot-separated component path within this composite.
Public Member Functions inherited from Mila::Dnn::Component< TDeviceType, TPrecision >
	Component (const std::string &name)
	Construct component with required name identifier.
virtual void	build (const BuildContext &context) final
	Build the component with the provided BuildContext (canonical overload).
const std::string	getName () const
	Get the component's name identifier.
virtual std::vector< std::string >	getParameterNames () const
	List all available parameter names for this component.
TrainingMode	getTrainingMode () const noexcept
	The current runtime behavioral mode of this Component.
virtual bool	isBuilt () const final
	Returns true if build() has completed successfully.
virtual void	loadParameter (const std::string &, const Serialization::ITensorBlob &)
	Load a parameter from serialized tensor data.
void	setTrainingMode (TrainingMode mode)
	Set the runtime behavioral mode for this Component.

Protected Member Functions
void	onBuilding (const BuildContext &context) override
	Hook invoked by build() to allocate component buffers.
void	onTrainingModeChanging (TrainingMode training_mode) override
	Hook invoked when training mode is about to change.
BlockBuildContexts	resolveBlockBuildContexts (const BuildContext &context) const
Protected Member Functions inherited from Mila::Dnn::CompositeComponent< TDeviceType, TPrecision >
template<typename TComponent>
std::shared_ptr< TComponent >	getComponentAs (const std::string &name) const
	Retrieve a typed child component by name.
void	load_ (ModelArchive &archive, SerializationMode mode) override
	Restore children from their nested scopes, mirroring save_().
void	onExecutionContextSet () override
	Hook invoked after ExecutionContext is set.
virtual void	optimize ()
	Virtual hook for graph optimization after construction.
void	requireSerializableParameters () const override
	No-op override: a composite names no parameters of its own.
void	save_ (ModelArchive &archive, SerializationMode mode) const override
Protected Member Functions inherited from Mila::Dnn::Component< TDeviceType, TPrecision >
IExecutionContext *	getExecutionContext () const
	Get the shared execution context.
bool	hasExecutionContext () const noexcept
	Check if execution context has been set.
template<TensorDataType TParameterPrecision, typename TMemoryResource>
void	loadParameterFromBlob (const std::string &param_name, const Serialization::ITensorBlob &blob, Tensor< TParameterPrecision, TMemoryResource > &target, const shape_t &expected_shape)
	Load a tensor blob into a parameter tensor with validation.
template<TensorDataType TParameterPrecision, typename TMemoryResource>
void	saveParameterToArchive (ModelArchive &archive, const std::string &parameter_name, const Tensor< TParameterPrecision, TMemoryResource > &parameter) const
	Write one parameter tensor into the archive under "tensors/<name>".
template<TensorDataType TParameterPrecision, typename TMemoryResource>
void	saveParameterToWriter (Serialization::SafeTensorsWriter &writer, const std::string &flat_name, const Tensor< TParameterPrecision, TMemoryResource > &parameter, Serialization::TensorSavePass pass) const
	Drive one parameter through one pass of a flat safetensors save.
void	setExecutionContext (IExecutionContext *context)
	Set the execution context for this component.

Additional Inherited Members
Static Public Member Functions inherited from Mila::Dnn::Component< TDeviceType, TPrecision >
static constexpr DeviceType	getDeviceType ()
	Compile-time device type for this component instance.
static constexpr TensorDataType	getPrecision () noexcept
	Compile-time tensor precision for this component instance.
Protected Types inherited from Mila::Dnn::Component< TDeviceType, TPrecision >
using	HostStagingMemoryResource
	Host memory a device-resident parameter stages through.
Protected Attributes inherited from Mila::Dnn::Component< TDeviceType, TPrecision >
BuildContext	build_context_ { shape_t{ 1 }, RuntimeMode::Training }
	The BuildContext stored at build time.

Member Function Documentation

◆ getMemoryStats()

template<DeviceType TDeviceType, TensorDataType TPrecision, WeightQuantPolicy TWeightQuant = NoWeightQuant, KvCachePolicy TKvPolicy = NoKvCompression>

MemoryStats Mila::Dnn::LlamaBlock< TDeviceType, TPrecision, TWeightQuant, TKvPolicy >::getMemoryStats ( ) const

inlineoverridevirtual

Return the current memory allocation breakdown for this component.

Reflects allocations at the moment of the call. The returned stats naturally track the component lifecycle:

After construction – nothing; construction allocates none After build( Inference ) – parameters + T=1 state buffers After build( Training ) – parameters + T=full state buffers After setTrainingMode( Train ) – parameters + state + gradients

For CompositeComponent and Network, the returned stats are the recursive aggregate of all child components.

May be called at any time – no lifecycle preconditions.

Returns: MemoryStats reflecting current allocations.

Implements Mila::Dnn::Component< TDeviceType, TPrecision >.

◆ getRequiredMemory()

template<DeviceType TDeviceType, TensorDataType TPrecision, WeightQuantPolicy TWeightQuant = NoWeightQuant, KvCachePolicy TKvPolicy = NoKvCompression>

MemoryStats Mila::Dnn::LlamaBlock< TDeviceType, TPrecision, TWeightQuant, TKvPolicy >::getRequiredMemory ( const BuildContext & context ) const

inlineoverridevirtual

What onBuilding() would allocate for this context, without allocating.

Children are named rather than walked: each is built with its own context, and a generic recursion over getComponents() would size every one of them against the block's shape. Fetched by name because the member pointers are assigned in onBuilding and are null before a build. See Specifications/MemoryFootprint.md section 4.4.

Reimplemented from Mila::Dnn::Component< TDeviceType, TPrecision >.

◆ getType()

template<DeviceType TDeviceType, TensorDataType TPrecision, WeightQuantPolicy TWeightQuant = NoWeightQuant, KvCachePolicy TKvPolicy = NoKvCompression>

const ComponentType Mila::Dnn::LlamaBlock< TDeviceType, TPrecision, TWeightQuant, TKvPolicy >::getType ( ) const

inlineoverridevirtual

Get the component type identifier.

Used for serialization and runtime type identification.

Returns: Component type enum value.

Implements Mila::Dnn::Component< TDeviceType, TPrecision >.

◆ onBuilding()

template<DeviceType TDeviceType, TensorDataType TPrecision, WeightQuantPolicy TWeightQuant = NoWeightQuant, KvCachePolicy TKvPolicy = NoKvCompression>

void Mila::Dnn::LlamaBlock< TDeviceType, TPrecision, TWeightQuant, TKvPolicy >::onBuilding ( const BuildContext & context )

inlineoverrideprotectedvirtual

Hook invoked by build() to allocate component buffers.

Receives the stored BuildContext. Implementations must use config.allocationSeqLen() when sizing output buffers – this is the single call that makes Inference and Training allocate the correct buffer sizes automatically without per-component logic.

// Example -- Linear component:
shape_t out_shape =
{
    config.batchSize(),
    config.allocationSeqLen(),   // 1 for Inference, T for Training
    config_.getOutputFeatures()
};
output_ = std::make_unique<TensorType>( device, out_shape,
    this->getName() + ".output" );

The default implementation forwards to the legacy onBuilding( const shape_t& ) overload for backwards compatibility. New components should override this overload directly.

Note: Do not call build() or onBuilding() from within this hook.; Implementations should either succeed fully or leave no partial state, as a failed build() may be retried.

Takes the build-time configuration; use its allocationSeqLen() to obtain the correct output buffer sequence dimension.

Reimplemented from Mila::Dnn::Component< TDeviceType, TPrecision >.

◆ onTrainingModeChanging()

template<DeviceType TDeviceType, TensorDataType TPrecision, WeightQuantPolicy TWeightQuant = NoWeightQuant, KvCachePolicy TKvPolicy = NoKvCompression>

void Mila::Dnn::LlamaBlock< TDeviceType, TPrecision, TWeightQuant, TKvPolicy >::onTrainingModeChanging ( TrainingMode training_mode )

inlineoverrideprotectedvirtual

Hook invoked when training mode is about to change.

Propagates the new mode to all child components. The hook runs with the Component's training mutex held; it MUST NOT call setTrainingMode().

Parameters

training_mode New training mode (Normal or Eval)

Reimplemented from Mila::Dnn::CompositeComponent< TDeviceType, TPrecision >.

◆ setState()

template<DeviceType TDeviceType, TensorDataType TPrecision, WeightQuantPolicy TWeightQuant = NoWeightQuant, KvCachePolicy TKvPolicy = NoKvCompression>

void Mila::Dnn::LlamaBlock< TDeviceType, TPrecision, TWeightQuant, TKvPolicy >::setState ( const GqaState & state )

inline

Forward the shared GQA transient workspace to this block's attention layer.

Must be called after build() and before prefill() or decode().

Parameters

state Non-owning pointers to workspace tensors owned by LlamaTransformer.

◆ zeroGradients()

template<DeviceType TDeviceType, TensorDataType TPrecision, WeightQuantPolicy TWeightQuant = NoWeightQuant, KvCachePolicy TKvPolicy = NoKvCompression>

void Mila::Dnn::LlamaBlock< TDeviceType, TPrecision, TWeightQuant, TKvPolicy >::zeroGradients ( )

inlineoverridevirtual

Clear all model-owned gradients for this component.

Default implementation is a no-op. Composite components should override to recurse to children. Leaf components should override to zero their parameter and activation gradients using device-aware helpers.

Reimplemented from Mila::Dnn::Component< TDeviceType, TPrecision >.

The documentation for this class was generated from the following file:

Mila/Src/Dnn/Components/Transformers/LlaMa/Llama.Block.ixx

Classes

Public Types

Public Member Functions

Protected Member Functions

Additional Inherited Members

Member Function Documentation

◆ getMemoryStats()

◆ getRequiredMemory()

◆ getType()

◆ onBuilding()

◆ onTrainingModeChanging()

◆ setState()

◆ zeroGradients()