| --- |
| library_name: kernels |
| license: apache-2.0 |
| tags: |
| - kernel |
| - webgpu |
| - wgsl |
| --- |
| # ai.onnx.GlobalLpPool |
|
|
| `ai.onnx` · standard ONNX operator · ONNX opset ≥ 2 |
|
|
| ## Description |
|
|
| Applies Lp pooling globally across all spatial dimensions of the input, equivalent to `LpPool` with the kernel spanning the full spatial extent. Each output value is the Lp norm (`p`-th root of sum of absolute values raised to the power `p`) over all spatial positions in a single channel. |
|
|
| See the [ONNX `GlobalLpPool` spec](https://onnx.ai/onnx/operators/onnx__GlobalLpPool.html) for the reference semantics. |
|
|
| ## Inputs |
|
|
| | Name | Upstream name | Logical dtype | Rank | Shape | Description | Presence | |
| | --- | --- | --- | --- | --- | --- | --- | |
| | `x` | `X` | `T` | — | — | Input tensor of shape `(N x C x D1 x ... x Dn)`; the spatial dimensions `D1...Dn` are reduced. | required | |
|
|
| ## Outputs |
|
|
| | Name | Upstream name | Logical dtype | Rank | Shape | Description | Presence | |
| | --- | --- | --- | --- | --- | --- | --- | |
| | `y` | `Y` | `T` | same as `x` | — | Output tensor of shape `(N x C x 1 x ... x 1)`; same rank as the input with all spatial dimensions set to 1. | required | |
|
|
| ## Attributes |
|
|
| Default values (overridable per request): |
|
|
| | Attribute | Default | Description | |
| | --- | --- | --- | |
| | `p` | `2` | The `p` value of the Lp norm for pooling over the spatial dimensions; defaults to `2` (Euclidean norm). | |
|
|
| ## Type constraints |
|
|
| | Variable | Allowed dtypes | |
| | --- | --- | |
| | `T` | `float32`, `float16` | |
|
|
| ## Device requirements |
|
|
| Some implementation variants require `shader-f16`. These are route-specific capabilities, not package-wide requirements; availability also depends on the request shape and dtype. |
|
|
| ## Files |
|
|
| - [`metadata.json`](build/webgpu/metadata.json) — kernel metadata (id, digests, per-variant templates, 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 cases |
| - [`global-lp-pool.wgsl.jinja`](build/webgpu/global-lp-pool.wgsl.jinja) |
| - [`pool-global-reduction.wgsl.jinja`](build/webgpu/pool-global-reduction.wgsl.jinja) |
|
|
| ## Use with `@huggingface/kernels` |
|
|
| ```sh |
| npm install --save-exact @huggingface/kernels@0.0.1-preview.3 |
| ``` |
|
|
| 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: |
|
|
| - `y` |
|
|
| 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. |
|
|
| ```js |
| import { getKernel } from "@huggingface/kernels"; |
| |
| const kernel = await getKernel("webgpu-kernels/ai.onnx.GlobalLpPool", { version: 1 }); |
| // Explicit destinations request optional results or supply metadata that cannot be inferred. |
| const { y } = await kernel({ x: { data: xData, shape: [1, 2, 4] } }, { |
| outputs: { y: { shape: [1, 2, 1], dtype: "float32" } }, |
| }); |
| ``` |
|
|
