ai.onnx.MaxPool

ai.onnx · standard ONNX operator · ONNX opset ≥ 12

Description

Applies max pooling over a sliding kernel window on input tensor X, computing the maximum value within each window and writing it to output Y. Output spatial dimensions are determined by kernel size, strides, padding, and dilations; ceil_mode controls whether output size is rounded up or down.

See the ONNX MaxPool spec for the reference semantics.

Inputs

Name	Bind key	Logical dtype	Rank	Shape	Description	Presence
`X`	`x`	`T`	—	—	Input tensor of shape `(N x C x D1 x ... x Dn)`; batch size `N`, channels `C`, followed by spatial dimensions.	required

Outputs

Name	Bind key	Logical dtype	WebGPU storage	Rank	Shape	Description	Presence
`Y`	`y`	`T`	runtime-selected; narrow integers and bool use 32-bit slots	same as `X`	derived; see description	Pooled output tensor with the same batch and channel dimensions as X but reduced spatial dimensions.	required
`Indices`	`indices`	`I`	`uint32`	same as `X`	derived; see description	Optional logical int64 flat indices of the maximum values selected during pooling, with the same shape as Y; indices do not account for padding and use uint32 WebGPU storage.	optional

Attributes

Attributes and default values (overridable per request):

Attribute	Default	Description
`auto_pad`	`"NOTSET"`	Deprecated auto-padding mode: `NOTSET` (use explicit pads), `SAME_UPPER`, `SAME_LOWER` (pad so output size is `ceil(input / stride)`), or `VALID` (no padding). It cannot be used together with `pads`.
`storage_order`	`0`	Storage order of the Indices output tensor: 0 for row-major, 1 for column-major.
`ceil_mode`	`0`	When non-zero, use ceiling instead of floor when computing output spatial dimensions.
`kernel_shape`	—	Required kernel shape, with one positive value per spatial axis.
`strides`	—	Stride along each spatial axis. When omitted, every stride is 1.
`pads`	—	Padding at the beginning and end of each spatial axis, ordered as `[begin_0, ..., begin_n, end_0, ..., end_n]`. When omitted, every pad is 0.
`dilations`	—	Dilation along each spatial axis. When omitted, every dilation is 1.

Type constraints

Variable	Allowed dtypes
`T`	`float32`, `float16`, `int8`, `uint8`
`I`	`int64`

Files

metadata.json — kernel metadata (id, digests, provenance)
manifest.json — the op contract (source of truth)
test.json — correctness cases
bench.json — benchmark + tuning cases
max-pool2d-nchw-k3s2p1-vec4.wgsl.jinja
max-pool2d-nchw-u32.wgsl.jinja
max-pool3d-ncdhw-k5-tiled.wgsl.jinja
pool-global-reduction.wgsl.jinja
pool-ncl1d-x4.wgsl.jinja
pool-window-nd.wgsl.jinja
pool-window-unroll.wgsl.jinja
pool2d-nchw-k2s2-vec4.wgsl.jinja
pool2d-nchw-separable.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.

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

const kernel = await getKernel("webgpu-kernels/ai.onnx.MaxPool", { version: 1 });
const { y } = await kernel({ x: { data: xData, shape: [1, 1, 3] } }, {
  attrs: { kernel_shape: [2] },
});

Downloads last month: -

kernel

webgpu

wgsl

apache-2.0

WebGPU

Requires WebGPU support. See the compatibility table.