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

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

Weight-only-quantized mixture-of-experts: the stacked expert
    weights bind as :class:`QTensor` and rest quantized; the activation
    stays floating point.

## `__init__`

```python
__init__(self, num_experts: 'int', hidden_size: 'int', intermediate_size: 'int', top_k: 'int', *, gate_up_bias: 'bool' = False, down_bias: 'bool' = False, dtype: '_dtype.dtype | DataType | None' = None, device: 'Device | str | None' = None, **options: 'Any') -> 'None'
```

QMoEWoQ(num_experts, hidden_size, intermediate_size, top_k, *, gate_up_bias=False, down_bias=False, dtype=None, device=None, **options)

Declare the expert stacks; the same counts, flags, and routing
kwargs as :class:`MoE` (``dtype`` declares the LOGICAL element
type; ``None`` declares the default dtype).

## `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, x: 'Tensor', router_logits: 'Tensor', shared_output: 'Tensor | None' = None) -> 'Tensor'
```

forward(*args, **kwargs) -> Any

The computation. Subclasses define it; callers invoke the module
itself (``m(x)``) so the forward hooks run around it.

## `set_weights`

```python
set_weights(self, gate_up_experts: 'QTensor', down_experts: 'QTensor', *, gate_up_bias: 'Tensor | None' = None, down_bias: 'Tensor | None' = None, gate_experts: 'QTensor | None' = None, gate_bias: 'Tensor | None' = None, e_score_correction_bias: 'Tensor | None' = None) -> 'None'
```

set_weights(gate_up_experts, down_experts, *, gate_up_bias=None, down_bias=None, gate_experts=None, gate_bias=None, e_score_correction_bias=None) -> None

Bind the quantized expert stacks (schemes travel with them) and
the declared floating-point biases.