ai.onnx.Hardmax

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

Description

Computes the hardmax of the input along a single axis: sets the position of the first maximum value along axis to 1 and all other positions to 0. The output has the same shape as the input.

See the ONNX Hardmax spec for the reference semantics.

Inputs

Outputs

Attributes

Default values (overridable per request):

Type constraints

Files

• metadata.json — kernel metadata (id, digests, per-variant templates, provenance)
• manifest.json — the op contract (source of truth)
• test.json — correctness cases
• bench.json — benchmark + tuning cases
• hardmax-axis-tree.wgsl.jinja
• hardmax-last-axis-subgroup.wgsl.jinja
• hardmax-last-axis-vec4.wgsl.jinja
• hardmax.wgsl.jinja

Use with @huggingface/kernels

npm install --save-exact @huggingface/kernels@0.0.1-preview.2

Required output shapes and logical data types are inferred from the supplied inputs and attributes; result tensors are allocated automatically.

The version: 1 option selects the published kernel contract; it is independent of any operator opset, contrib since_version, or model version. It follows the v1 branch as fixes land. To pin exact artifact bytes, pass a 40-character commit revision instead of version.

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

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

const kernel = await getKernel("webgpu-kernels/ai.onnx.Hardmax", { version: 1 });
const { y } = await kernel({ x: { data: xData, shape: [1, 3] } });