mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-05-17 21:10:43 +00:00
c3f04251c7
### Description Added two kernels for Layer and Instance norm Also added maximum limits for `maxBufferSize` when requesting GPU device as by default it's limited to 256mb and it fails allocating 600mb buffer while running fp32 StableDiffusion weights. ### Motivation and Context These two are used in StableDiffusion and many other networks
80 lines
3.6 KiB
Markdown
80 lines
3.6 KiB
Markdown
## Operators Support Table
|
|
|
|
The following table shows ONNX
|
|
operators and the supported opset domain/versions in WebGPU EP by ONNX Runtime Web. For example,
|
|
`4-6, 8+` means ONNX Runtime Web currently support opset version 4 to 6, 8 and above.
|
|
|
|
*This file is automatically generated from the
|
|
def files via [this script](../script/generate-webgpu-operator-md.ts).
|
|
Do not modify directly.*
|
|
|
|
| Operator | Opset | Comments |
|
|
|:--------:|:-------------:|-----|
|
|
| Abs | ai.onnx(6-12,13+) | |
|
|
| Acos | ai.onnx(7+) | |
|
|
| Acosh | ai.onnx(9+) | |
|
|
| Add | ai.onnx(7-12,13,14+) | |
|
|
| ArgMax | ai.onnx(1-10,11-12,13+) | |
|
|
| ArgMin | ai.onnx(1-10,11-12,13+) | |
|
|
| Asin | ai.onnx(7+) | |
|
|
| Asinh | ai.onnx(9+) | |
|
|
| Atan | ai.onnx(7+) | |
|
|
| Atanh | ai.onnx(9+) | |
|
|
| AveragePool | ai.onnx(7-9,10,11+); com.ms.internal.nhwc(11+) | need perf optimization; need implementing activation |
|
|
| Ceil | ai.onnx(6-12,13+) | |
|
|
| Clip | ai.onnx(6-10,11,12,13+) | |
|
|
| Concat | ai.onnx(1-3,4-10,11-12,13+) | |
|
|
| Conv | ai.onnx(1-10,11+); com.ms.internal.nhwc(11+) | need perf optimization; conv3d is not supported; need implementing activation |
|
|
| ConvTranspose | ai.onnx(1-10,11+); com.ms.internal.nhwc(11+) | need perf optimization; ConvTranspose3d is not supported; need implementing activation |
|
|
| Cos | ai.onnx(7+) | |
|
|
| Cosh | ai.onnx(9+) | |
|
|
| Div | ai.onnx(7-12,13,14+) | |
|
|
| Elu | ai.onnx(6+) | |
|
|
| Erf | ai.onnx(9-12,13+) | |
|
|
| Exp | ai.onnx(6-12,13+) | |
|
|
| Expand | ai.onnx(8-12,13+) | |
|
|
| Flatten | ai.onnx(1-8,9-10,11-12,13+) | |
|
|
| Floor | ai.onnx(6-12,13+) | |
|
|
| Gather | ai.onnx(1-10,11-12,13+) | |
|
|
| Gelu | com.microsoft(1+) | |
|
|
| Gemm | ai.onnx(7-8,9-10,11+) | |
|
|
| GlobalAveragePool | ai.onnx(1+); com.ms.internal.nhwc(1+) | |
|
|
| GlobalMaxPool | ai.onnx(1+); com.ms.internal.nhwc(1+) | |
|
|
| InstanceNormalization | ai.onnx(6+); com.ms.internal.nhwc(6+) | |
|
|
| LayerNormalization | ai.onnx(17+) | |
|
|
| LeakyRelu | ai.onnx(6-15,16+) | |
|
|
| MatMul | ai.onnx(1-12,13+) | |
|
|
| MaxPool | ai.onnx(1-7,8-9,10,11,12+); com.ms.internal.nhwc(11,12+) | need perf optimization; need implementing activation |
|
|
| MemcpyFromHost | ai.onnx(1+) | |
|
|
| MemcpyToHost | ai.onnx(1+) | |
|
|
| Mul | ai.onnx(7-12,13,14+) | |
|
|
| Neg | ai.onnx(6-12,13+) | |
|
|
| Pow | ai.onnx(7-11,12,13-14,15+) | |
|
|
| Reciprocal | ai.onnx(6-12,13+) | |
|
|
| ReduceL1 | ai.onnx(1-10,11-12,13-17,18+) | |
|
|
| ReduceL2 | ai.onnx(1-10,11-12,13-17,18+) | |
|
|
| ReduceLogSum | ai.onnx(1-10,11-12,13-17,18+) | |
|
|
| ReduceLogSumExp | ai.onnx(1-10,11-12,13-17,18+) | |
|
|
| ReduceMax | ai.onnx(1-10,11,12,13-17,18+) | |
|
|
| ReduceMean | ai.onnx(1-10,11-12,13-17,18+) | |
|
|
| ReduceMin | ai.onnx(1-10,11,12,13-17,18+) | |
|
|
| ReduceProd | ai.onnx(1-10,11-12,13-17,18+) | |
|
|
| ReduceSum | ai.onnx(1-10,11-12,13+) | |
|
|
| ReduceSumSquare | ai.onnx(1-10,11-12,13-17,18+) | |
|
|
| Relu | ai.onnx(6-12,13,14+) | |
|
|
| Reshape | ai.onnx(5-12,13,14+) | no GPU kernel |
|
|
| Resize | ai.onnx(10,11-12,13-17,18,19+); com.ms.internal.nhwc(10,11-12,13-17,18,19+) | CoordinateTransformMode align_corners is not supported with downsampling |
|
|
| Shape | ai.onnx(1-12,13-14,15+) | no GPU kernel; an ORT warning is generated - need to fix |
|
|
| Sigmoid | ai.onnx(6-12,13+) | |
|
|
| Sin | ai.onnx(7+) | |
|
|
| Sinh | ai.onnx(9+) | |
|
|
| Slice | ai.onnx(1-9,10,11-12,13+) | |
|
|
| Softmax | ai.onnx(1-10,11-12,13+) | |
|
|
| Split | ai.onnx(1,2-10,11-12,13-17,18+) | |
|
|
| Sqrt | ai.onnx(6-12,13+) | |
|
|
| Squeeze | ai.onnx(1-10,11-12,13+) | |
|
|
| Sub | ai.onnx(7-12,13,14+) | |
|
|
| Tan | ai.onnx(7+) | |
|
|
| ThresholdedRelu | ai.onnx(10+) | |
|
|
| Transpose | ai.onnx(1-12,13+) | need perf optimization |
|
|
| Unsqueeze | ai.onnx(1-10,11-12,13+) | |
|