Struct Mamba2Layer 

pub struct Mamba2Layer<B: Backend> {
    pub norm: RmsNorm<B>,
    pub mamba_block: Mamba2<B>,
}

A single Mamba-2 residual block:

  output = x·scale + Mamba2( RMSNorm(x) )

where scale is 1.0 normally and 0.0 when the residual connection is intentionally suppressed by the layer stack configuration.

Fields

norm: RmsNorm<B>

Pre-norm applied to the input before the SSM block.

Using RMSNorm before the block (Pre-LN) is standard practice in modern LLMs and improves training stability.

mamba_block: Mamba2<B>

The Mamba-2 SSM block (see Mamba2).

Implementations

impl<B: Backend + Mamba2BackendExt> Mamba2Layer<B>

pub fn forward( &self, x: Tensor<B, 3>, cache: Option<Mamba2Cache<B>>, ssd_path: Mamba2SsdPath, residual_scale: f32, ) -> (Tensor<B, 3>, Mamba2Cache<B>)

Run the Pre-LN residual block over a full sequence.

Computes:

  output = x · residual_scale + Mamba2( RMSNorm(x) )

Shapes

• x : [batch, sequence, d_model]
• output : [batch, sequence, d_model]

pub fn step( &self, x: Tensor<B, 2>, cache: Option<Mamba2Cache<B>>, residual_scale: f32, ) -> (Tensor<B, 2>, Mamba2Cache<B>)

Run the Pre-LN residual block for a single decoding step.

Computes:

  output = x · residual_scale + Mamba2.step( RMSNorm(x) )

Shapes

• x : [batch, d_model]
• output: [batch, d_model]

Trait Implementations

impl<B> AutodiffModule<B> for Mamba2Layer<B>

where B: AutodiffBackend + Backend, <B as AutodiffBackend>::InnerBackend: Backend,

type InnerModule = Mamba2Layer<<B as AutodiffBackend>::InnerBackend>

Inner module without auto-differentiation.

fn valid(&self) -> Self::InnerModule

Returns the same module, but on the inner backend without auto-differentiation.

fn from_inner(module: Self::InnerModule) -> Self

Wraps an inner module back into an auto-diff module.

impl<B: Backend> Clone for Mamba2Layer<B>

fn clone(&self) -> Self

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl<B: Debug + Backend> Debug for Mamba2Layer<B>

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<B: Backend> Display for Mamba2Layer<B>

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<B> HasAutodiffModule<B> for Mamba2Layer<B::InnerBackend>

where B: AutodiffBackend + Backend, <B as AutodiffBackend>::InnerBackend: Backend,

type TrainModule = Mamba2Layer<B>

The module with auto-differentiation.

impl<B: Backend> Module<B> for Mamba2Layer<B>

type Record = Mamba2LayerRecord<B>

Type to save and load the module.

fn load_record(self, record: Self::Record) -> Self

Load the module state from a record.

fn into_record(self) -> Self::Record

Convert the module into a record containing the state.

fn num_params(&self) -> usize

Get the number of parameters the module has, including all of its sub-modules.

fn visit<Visitor: ModuleVisitor<B>>(&self, visitor: &mut Visitor)

Visit each tensor parameter in the module with a visitor.

fn map<Mapper: ModuleMapper<B>>(self, mapper: &mut Mapper) -> Self

Map each tensor parameter in the module with a mapper.

fn collect_devices(&self, devices: Devices<B>) -> Devices<B>

Return all the devices found in the underneath module tree added to the given vector without duplicates.

fn to_device(self, device: &B::Device) -> Self

Move the module and all of its sub-modules to the given device.

fn fork(self, device: &B::Device) -> Self

Fork the module and all of its sub-modules to the given device.

fn devices(&self) -> Vec<<B as BackendTypes>::Device>

Return all the devices found in the underneath module tree without duplicates.

fn no_grad(self) -> Self

Each tensor in the module tree will not require grad.

fn train<AB>(self) -> Self::TrainModule

where AB: AutodiffBackend<InnerBackend = B>, Self: HasAutodiffModule<AB>,

Move the module and all of its sub-modules to the autodiff backend.

fn quantize_weights(self, quantizer: &mut Quantizer) -> Self

Quantize the weights of the module.

impl<B: Backend> ModuleDisplay for Mamba2Layer<B>

fn format(&self, passed_settings: DisplaySettings) -> String

Formats the module with provided display settings.

fn custom_settings(&self) -> Option<DisplaySettings>

Custom display settings for the module.

fn custom_content(&self, _content: Content) -> Option<Content>

Custom attributes for the module.

impl<B: Backend> ModuleDisplayDefault for Mamba2Layer<B>

fn content(&self, content: Content) -> Option<Content>

Attributes of the module used for display purposes.

fn num_params(&self) -> usize

Gets the number of the parameters of the module.