---
library_name: kernels
license: apache-2.0
tags:
- kernel
- webgpu
- wgsl
---
# ai.onnx.Less

`ai.onnx`  ·  standard ONNX operator  ·  ONNX opset ≥ 13

## Description

Performs an elementwise `less-than` comparison between tensors `A` and `B` with NumPy-style multidirectional broadcasting, producing a boolean result tensor `C`. Each output element is `true` where the corresponding element of `A` is strictly less than that of `B`.

See the [ONNX `Less` spec](https://onnx.ai/onnx/operators/onnx__Less.html) for the reference semantics.

## Inputs

| Name | Bind key | Logical dtype | Rank | Shape | Description | Presence |
| --- | --- | --- | --- | --- | --- | --- |
| `A` | `a` | `T` | — | — | First input operand for the less-than comparison. | required |
| `B` | `b` | `T` | — | — | Second input operand for the less-than comparison. | required |

## Outputs

| Name | Bind key | Logical dtype | Rank | Shape | Description | Presence |
| --- | --- | --- | --- | --- | --- | --- |
| `C` | `c` | `B` | derived | broadcast result of `A` and `B` | Boolean result tensor; true where A < B. | required |

## Type constraints

| Variable | Allowed dtypes |
| --- | --- |
| `T` | `float32`, `float16`, `int32`, `int16`, `uint32`, `int8`, `uint8` |
| `B` | `bool` |

## Files

- [`metadata.json`](build/webgpu/metadata.json) — kernel metadata (id, digests, provenance)
- [`manifest.json`](build/webgpu/manifest.json) — the op contract (source of truth)
- [`test.json`](build/webgpu/test.json) — correctness cases
- [`bench.json`](build/webgpu/bench.json) — benchmark + tuning cases
- [`compare-broadcast-vec4.wgsl.jinja`](build/webgpu/compare-broadcast-vec4.wgsl.jinja)
- [`compare-broadcast.wgsl.jinja`](build/webgpu/compare-broadcast.wgsl.jinja)
- [`compare-vec4.wgsl.jinja`](build/webgpu/compare-vec4.wgsl.jinja)

## Use with `@huggingface/kernels`

The loader derives every required output's shape and logical dtype from the manifest contract and this call.
It then allocates the result tensors automatically.

The `version: 1` option selects the published kernel contract; it is independent of any operator opset, contrib `since_version`, or model version.

Replace each `*Data` placeholder with a typed array containing the corresponding input data.

```js
import { getKernel } from "@huggingface/kernels";

const kernel = await getKernel("webgpu-kernels/ai.onnx.Less", { version: 1 });
const { c } = await kernel({ a: { data: aData, shape: [] }, b: { data: bData, shape: [] } });
```