| --- |
| library_name: kernels |
| license: apache-2.0 |
| tags: |
| - kernel |
| - webgpu |
| - wgsl |
| --- |
| # com.microsoft.FusedConv |
|
|
| `com.microsoft` · ONNX Runtime contrib operator · contrib since_version 1 |
| |
| ## Description |
| |
| Applies an N-dimensional convolution with optional bias `B` and residual `Z`, followed by an optional fused activation. Omitting `activation` leaves the convolution result unchanged. Supported activations are `Relu`, `LeakyRelu`, `Sigmoid`, `Tanh`, `HardSigmoid`, `HardSwish`, and `Clip`; other schema-permitted activation strings are not implemented. The implementation supports one to three spatial dimensions and float16 or float32; higher spatial ranks and float64 are not implemented. |
| |
| See the [ONNX Runtime `FusedConv` contrib-operator spec](https://github.com/microsoft/onnxruntime/blob/main/docs/ContribOperators.md#com.microsoft.FusedConv) for the reference semantics. |
| |
| ## Inputs |
| |
| | Name | Bind key | Logical dtype | Rank | Shape | Description | Presence | |
| | --- | --- | --- | --- | --- | --- | --- | |
| | `X` | `x` | `T` | — | — | Input data tensor of shape `(N, C, D1, ..., Dn)` for one to three spatial dimensions. | required | |
| | `W` | `w` | `T` | — | — | Convolution filter tensor of shape `(M, C/group, k1, ..., kn)`, with the same spatial rank as `X`. | required | |
| | `B` | `bias` | `T` | `1` | — | Optional 1-D bias tensor of length `out_channels`, broadcast-added to each output channel. | optional | |
| | `Z` | `zResidual` | `T` | same as `X` | — | Optional residual tensor with the same shape as the output `Y`, added before the activation. | optional | |
|
|
| ## Outputs |
|
|
| | Name | Bind key | Logical dtype | Rank | Shape | Description | Presence | |
| | --- | --- | --- | --- | --- | --- | --- | |
| | `Y` | `y` | `T` | same as `X` | derived; see description | Output feature map tensor after convolution, optional bias/residual addition, and the fused activation. | required | |
|
|
| ## Attributes |
|
|
| Attributes and default values (overridable per request): |
|
|
| | Attribute | Default | Description | |
| | --- | --- | --- | |
| | `auto_pad` | `"NOTSET"` | Automatic padding mode. `NOTSET` uses `pads`; `SAME_UPPER` and `SAME_LOWER` choose padding so each output spatial size is `ceil(input / stride)`; `VALID` uses no padding. | |
| | `group` | `1` | Number of groups that input and output channels are split into; defaults to 1. | |
| | `activation` | — | Optional fused activation name: `Relu`, `LeakyRelu`, `Sigmoid`, `Tanh`, `HardSigmoid`, `HardSwish`, or `Clip`. Omission applies no activation. | |
| | `activation_params` | — | Positional parameters for the fused activation: exactly `[alpha]` is required for `LeakyRelu`, and exactly `[alpha, beta]` or `[min, max]` is required for `HardSigmoid` or `Clip`, respectively. Parameter-free activations ignore this attribute. | |
| | `dilations` | — | Optional dilation factors, one positive integer per spatial axis. Omission means all ones. | |
| | `kernel_shape` | — | Optional kernel shape, one positive integer per spatial axis. When present, it must match the spatial dimensions of the weight tensor; omission infers the shape from the weights. | |
| | `pads` | — | Optional explicit padding in ONNX order `[begin_axis_0, ..., begin_axis_n, end_axis_0, ..., end_axis_n]`. Omission means all zeros; it cannot be combined with an automatic padding mode. | |
| | `strides` | — | Optional stride factors, one positive integer per spatial axis. Omission means all ones. | |
|
|
| ## Type constraints |
|
|
| | Variable | Allowed dtypes | |
| | --- | --- | |
| | `T` | `float32`, `float16` | |
|
|
| ## Device requirements |
|
|
| Some implementation variants require `subgroup-matrix` and `subgroups`. 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, 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 |
| - [`conv-1x1-gemm-tiled-reg.wgsl.jinja`](build/webgpu/conv-1x1-gemm-tiled-reg.wgsl.jinja) |
| - [`conv-1x1-gemm-tiled.wgsl.jinja`](build/webgpu/conv-1x1-gemm-tiled.wgsl.jinja) |
| - [`conv-1x1-subgroup-matrix.wgsl.jinja`](build/webgpu/conv-1x1-subgroup-matrix.wgsl.jinja) |
| - [`conv-direct-nd.wgsl.jinja`](build/webgpu/conv-direct-nd.wgsl.jinja) |
| - [`conv-direct-unrolled.wgsl.jinja`](build/webgpu/conv-direct-unrolled.wgsl.jinja) |
| - [`conv-im2col-nchw.wgsl.jinja`](build/webgpu/conv-im2col-nchw.wgsl.jinja) |
| - [`conv1d-tiled-reg.wgsl.jinja`](build/webgpu/conv1d-tiled-reg.wgsl.jinja) |
| - [`conv2d-grouped-large-w4.wgsl.jinja`](build/webgpu/conv2d-grouped-large-w4.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/com.microsoft.FusedConv", { version: 1 }); |
| const { y } = await kernel({ |
| x: { data: xData, shape: [1, 32, 8, 8] }, |
| w: { data: wData, shape: [32, 32, 1, 1] }, |
| }); |
| ``` |
|
|
