---
title: "Linear"
sidebar_label: "Linear"
description: "The clika_runtime.nn Linear class."
---

<!-- Generated by tools/api_reference/generate_api_docs.py. Do not edit. -->

Linear(in_features, out_features, bias=True, device=None, dtype=None, *, activation=None)

    ``y = x @ weight.T + bias`` over a ``[out_features, in_features]``
    weight and, with ``bias=True``, a ``[out_features]`` bias.

    Args:
        in_features: the size of each input sample.
        out_features: the size of each output sample.
        bias: declare the bias slot.
        device: where the layer's tensors live (a device or its string
            form); ``None`` declares on the cpu.
        dtype: the weight dtype the layer declares; ``None`` declares the
            default dtype (:func:`~clika_runtime.get_default_dtype`). A
            ``load_state_dict`` casts the checkpoint to the declared dtype;
            ``assign=True`` adopts the checkpoint's own dtype instead.
        activation: a fused epilogue applied to every output (``"gelu"``,
            ``"silu"``, ... or an :class:`~clika_runtime.Activation`
            value); ``None`` for none.
    

## `__init__`

```python
__init__(self, in_features: 'int', out_features: 'int', bias: 'bool' = True, device: 'Device | str | None' = None, dtype: 'DtypeLike | None' = None, *, activation: 'ActivationLike' = None) -> 'None'
```

Initialize self.  See help(type(self)) for accurate signature.

## `extra_repr`

```python
extra_repr(self) -> 'str'
```

extra_repr() -> str

One line of per-class detail for :meth:`__repr__`; a layer prints
its geometry here (``in_features=64, out_features=256``).

## `forward`

```python
forward(self, input: 'Tensor') -> 'Tensor'
```

forward(input) -> Tensor

``[*, in_features]`` to ``[*, out_features]``.

## `from_weights`

```python
from_weightsfrom_weights(weight, bias=None) -> Linear
```

from_weights(weight, bias=None) -> Linear

Construct FROM tensors: geometry, dtype, and device read off
``weight`` (``[out_features, in_features]``); an optional ``bias``
(``[out_features]``) binds beside it.

## `set_weights`

```python
set_weights(self, weight: 'Tensor', bias: 'Tensor | None' = None) -> 'None'
```

set_weights(weight, bias=None) -> None

Bind the declared slots directly; raises RuntimeError on a shape
mismatch.