ai.onnx.Squeeze

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

Description

Removes single-dimensional entries from the shape of a tensor. If axes is provided, only those dimensions are removed; if omitted, all size-1 dimensions are removed. Selecting an axis whose size is not 1 raises an error.

See the ONNX Squeeze spec for the reference semantics.

Inputs

Outputs

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
• datamove-elementwise-copy.wgsl.jinja
• datamove-flat-copy.wgsl.jinja

Use with @huggingface/kernels

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

Outputs with inferable metadata are allocated automatically. Explicit outputs entries request optional results or provide metadata that cannot be inferred from the supplied inputs and attributes.

This example supplies explicit metadata for:

• squeezed

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.Squeeze", { version: 1 });
// Explicit destinations request optional results or supply metadata that cannot be inferred.
const { squeezed } = await kernel({ data: { data: dataData, shape: [1, 1, 1, 1] } }, {
  outputs: { squeezed: { shape: [], dtype: "float32" } },
});