xlnstorch.nn.LNSMultiheadAttention

class xlnstorch.nn.LNSMultiheadAttention(embed_dim, num_heads, dropout=0.0, bias=True, add_bias_kv=False, add_zero_attn=False, kdim=None, vdim=None, batch_first=False)

An LNS multi-head attention layer.

See also: torch.nn.MultiheadAttention

Parameters:

• embed_dim (int) – Total dimension of the model.

• num_heads (int) – Number of parallel attention heads.

• dropout (float, optional) – Dropout probability on attention weights. Default: 0.0.

• bias (bool, optional) – If specified, add bias to the projection layers. Default: True.

• add_bias_kv (bool, optional) – If specified, add bias to the key and value sequences at dim=0. Default: False.

• add_zero_attn (bool, optional) – If specified, add a new batch of zeros to the key and value sequences at dim=1. Default: False.

• kdim (int, optional) – Total number of features in key. Default: None (uses embed_dim).

• vdim (int, optional) – Total number of features in value. Default: None (uses embed_dim).

• batch_first (bool, optional) – If True, then the input and output tensors are provided as (batch, seq, features). Default: False (seq, batch, features).

q_proj

Linear layer to project the queries.

Type:

LNSLinear

k_proj

Linear layer to project the keys.

Type:

LNSLinear

v_proj

Linear layer to project the values.

Type:

LNSLinear

out_proj

Linear layer to project the output.

Type:

LNSLinear

bias_k

Bias for the key sequence to be added at dim=0.

Type:

LNSTensor

bias_v

Bias for the value sequence to be added at dim=0.

Type:

LNSTensor

attn_dropout

Dropout layer on attention weights.

Type:

torch.nn.Dropout

__init__(embed_dim, num_heads, dropout=0.0, bias=True, add_bias_kv=False, add_zero_attn=False, kdim=None, vdim=None, batch_first=False)

Initialize internal Module state, shared by both nn.Module and ScriptModule.

Parameters:

• embed_dim (int)

• num_heads (int)

• dropout (float)

• bias (bool)

• add_bias_kv (bool)

• add_zero_attn (bool)

• kdim (int | None)

• vdim (int | None)

• batch_first (bool)

Methods

__init__(embed_dim, num_heads[, dropout, ...])	Initialize internal Module state, shared by both nn.Module and ScriptModule.
add_module(name, module)	Add a child module to the current module.
apply(fn)	Apply fn recursively to every submodule (as returned by .children()) as well as self.
bfloat16()	Casts all floating point parameters and buffers to bfloat16 datatype.
buffers([recurse])	Return an iterator over module buffers.
children()	Return an iterator over immediate children modules.
compile(*args, **kwargs)	Compile this Module's forward using torch.compile().
cpu()	Move all model parameters and buffers to the CPU.
cuda([device])	Move all model parameters and buffers to the GPU.
double()	Casts all floating point parameters and buffers to double datatype.
eval()	Set the module in evaluation mode.
extra_repr()	Return the extra representation of the module.
float()	Casts all floating point parameters and buffers to float datatype.
forward(query, key, value[, ...])	Define the computation performed at every call.
get_buffer(target)	Return the buffer given by target if it exists, otherwise throw an error.
get_extra_state()	Return any extra state to include in the module's state_dict.
get_parameter(target)	Return the parameter given by target if it exists, otherwise throw an error.
get_submodule(target)	Return the submodule given by target if it exists, otherwise throw an error.
half()	Casts all floating point parameters and buffers to half datatype.
ipu([device])	Move all model parameters and buffers to the IPU.
lns_parameters()	Returns a list of parameter groups for the module.
load_state_dict(state_dict[, strict, assign])	Copy parameters and buffers from state_dict into this module and its descendants.
modules()	Return an iterator over all modules in the network.
mtia([device])	Move all model parameters and buffers to the MTIA.
named_buffers([prefix, recurse, ...])	Return an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.
named_children()	Return an iterator over immediate children modules, yielding both the name of the module as well as the module itself.
named_modules([memo, prefix, remove_duplicate])	Return an iterator over all modules in the network, yielding both the name of the module as well as the module itself.
named_parameters([prefix, recurse, ...])	Return an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.
parameters([recurse])	Return an iterator over module parameters.
register_backward_hook(hook)	Register a backward hook on the module.
register_buffer(name, tensor[, persistent])	Add a buffer to the module.
register_forward_hook(hook, *[, prepend, ...])	Register a forward hook on the module.
register_forward_pre_hook(hook, *[, ...])	Register a forward pre-hook on the module.
register_full_backward_hook(hook[, prepend])	Register a backward hook on the module.
register_full_backward_pre_hook(hook[, prepend])	Register a backward pre-hook on the module.
register_load_state_dict_post_hook(hook)	Register a post-hook to be run after module's load_state_dict() is called.
register_load_state_dict_pre_hook(hook)	Register a pre-hook to be run before module's load_state_dict() is called.
register_module(name, module)	Alias for add_module().
register_parameter(name, param[, requires_grad])	Registers a parameter in the module.
register_state_dict_post_hook(hook)	Register a post-hook for the state_dict() method.
register_state_dict_pre_hook(hook)	Register a pre-hook for the state_dict() method.
requires_grad_([requires_grad])	Change if autograd should record operations on parameters in this module.
set_extra_state(state)	Set extra state contained in the loaded state_dict.
set_submodule(target, module[, strict])	Set the submodule given by target if it exists, otherwise throw an error.
share_memory()	See torch.Tensor.share_memory_().
state_dict(*args[, destination, prefix, ...])	Return a dictionary containing references to the whole state of the module.
to(*args, **kwargs)	Move and/or cast the parameters and buffers.
to_empty(*, device[, recurse])	Move the parameters and buffers to the specified device without copying storage.
train([mode])	Set the module in training mode.
type(dst_type)	Casts all parameters and buffers to dst_type.
xpu([device])	Move all model parameters and buffers to the XPU.
zero_grad([set_to_none])	Clears the gradients of all parameters in the module.

Attributes

T_destination
call_super_init
dump_patches
training