---
title: "ClikaRT::ops::fused"
sidebar_label: "fused"
description: "Namespace ClikaRT::ops::fused"
---

<!-- Generated by tools/doxygen2mdx from Doxygen XML. Do not edit. -->

<span class="api-kind api-kind--namespace">namespace</span>

## Enumerations

### enum SwigluFusion {#SwigluFusion}

<div class="api-signature">

`enum class` **`SwigluFusion`** `:` `std::uint8_t`

</div>

How the gate‖up halves are laid out in a gated MoE FC1 output.

| Enumerator | Value | Description |
| --- | --- | --- |
| `Unfused` | `0` | gate comes from a SEPARATE fc3 matrix |
| `Interleaved` | `1` | one fused \[E, 2I, H\]; gate = even, up = odd columns |
| `Concat` | `2` | one fused \[E, 2I, H\]; gate = first half, up = second |

<div class="api-declared">

Declared in `ClikaRT/compute/fused_op_enums.h`, line 14

</div>

### enum QComputeMode {#QComputeMode}

<div class="api-signature">

`enum class` **`QComputeMode`** `:` `std::uint8_t`

</div>

How a weight-only-quantized contraction ([`qmatmul_woq`](../qmatmul_woq.md#qmatmul_woq) / [`qlinear_woq`](../qlinear_woq.md#qlinear_woq) / the `*_woq` conv family) contracts a floating-point activation against a quantized weight.

`ExactFP` (the default) keeps the activation in floating point wherever the weight's format has a float route: an affine, codebook, FP8 or dense-coded weight dequantizes and runs the float dot, bit-faithful to the stored scale / zero-point. A packed block weight (the GGUF Q-series, K-quant and i-quant formats, the MX formats and NVFP4) runs on an int8 block tier instead where the backend has one: the activation rounds to per-block int8 before an integer dot, so the result differs from the float dot by that rounding.

- CPU: every GGUF weight format, MXFP4, MXINT8 and NVFP4; MXFP6 and MXFP8 keep the float dot.
- CUDA and Vulkan: the block formats their integer-dot tier covers, where K is a whole number of 32-element blocks (on Vulkan, also where the device's integer dot is verified); other formats keep the float dot.
- Metal and TPU: no int8 tier; every block weight keeps the float dot. On the runtime's parity tests (uniform activations) the rounding stays below a relative L2 of 0.03 to 0.05 against the float dot, or 0.08 with a bf16 activation. An activation with outlier channels can exceed these bounds.

`DynamicInt8` dynamically quantizes the activation to int8 and runs an integer dot, faster on dot-product hardware, at a small accuracy cost (the activation loses precision). A ROUTING HINT, not a shape contract: shapes outside a backend's fused coverage fall back to `ExactFP`.

| Enumerator | Value | Description |
| --- | --- | --- |
| `ExactFP` | `0` |  |
| `DynamicInt8` | `1` |  |

<div class="api-declared">

Declared in `ClikaRT/compute/fused_op_enums.h`, line 48

</div>

## `ClikaRT/compute/fused_op_enums.h` {#fused_op_enums-h}

```cpp
#include <ClikaRT/compute/fused_op_enums.h>
```

Enum parameters of the FUSED operators: how a gated MoE lays out its gate‖up halves, and how a weight-only-quantized contraction is computed. Values are PINNED (ABI): never reorder or remove a value; append new ones at the end.