mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-05-17 21:10:43 +00:00
7a8fa12850
### Description This PR adds the actual implementation of the WebGPU EP based on https://github.com/microsoft/onnxruntime/pull/22318. This change includes the following: <details> <summary><b>core framework of WebGPU EP</b></summary> - WebGPU EP factory classes for: - handling WebGPU options - creating WebGPU EP instance - creating WebGPU context - WebGPU Execution Provider classes - GPU Buffer allocator - data transfer - Buffer management classes - Buffer Manager - BufferCacheManager - DisabledCacheManager - SimpleCacheManager - LazyReleaseCacheManager - BucketCacheManager - Program classes - Program (base) - Program Cache Key - Program Manager - Shader helper classes - Shader Helper - ShaderIndicesHelper - ShaderVariableHelper - Utils - GPU Query based profiler - compute context - string utils - Miscs - Python binding webgpu support (basic) </details> <details> <summary><b>Kernel implementation</b></summary> - onnx.ai (default opset): - Elementwise (math): Abs, Neg, Floor, Ceil, Reciprocal, Sqrt, Exp, Erf, Log, Sin, Cos, Tan, Asin, Acos, Atan, Sinh, Cosh, Asinh, Acosh, Atanh, Tanh, Not, Cast - Elementwise (activation): Sigmoid, HardSigmoid, Clip, Elu, Relu, LeakyRelu, ThresholdedRelu, Gelu - Binary (math): Add, Sub, Mul, Div, Pow, Equal, Greater, GreaterOrEqual, Less, LessOrEqual - (Tensors): Shape, Reshape, Squeeze, Unsqueeze - Where - Transpose - Concat - Expand - Gather - Tile - Range - LayerNormalization - com.microsoft - FastGelu - MatMulNBits - MultiHeadAttention - RotaryEmbedding - SkipLayerNormalization - LayerNormalization - SimplifiedLayerNormalization - SkipSimplifiedLayerNormalization </details> <details> <summary><b>Build, test and CI pipeline integration</b></summary> - build works for Windows, macOS and iOS - support onnxruntime_test_all and python node test - added a new unit test for `--use_external_dawn` build flag. - updated MacOS pipeline to build with WebGPU support - added a new pipeline for WebGPU Windows </details> This change does not include: - Node.js binding support for WebGPU (will be a separate PR)
108 lines
3.3 KiB
YAML
108 lines
3.3 KiB
YAML
##### start trigger Don't edit it manually, Please do edit set-trigger-rules.py ####
|
|
### please do rerun set-trigger-rules.py ###
|
|
trigger:
|
|
branches:
|
|
include:
|
|
- main
|
|
- rel-*
|
|
paths:
|
|
exclude:
|
|
- docs/**
|
|
- README.md
|
|
- CONTRIBUTING.md
|
|
- BUILD.md
|
|
- 'js/web'
|
|
- 'onnxruntime/core/providers/js'
|
|
pr:
|
|
branches:
|
|
include:
|
|
- main
|
|
- rel-*
|
|
paths:
|
|
exclude:
|
|
- docs/**
|
|
- README.md
|
|
- CONTRIBUTING.md
|
|
- BUILD.md
|
|
- 'js/web'
|
|
- 'onnxruntime/core/providers/js'
|
|
#### end trigger ####
|
|
|
|
parameters:
|
|
- name: RunOnnxRuntimeTests
|
|
displayName: Run Tests?
|
|
type: boolean
|
|
default: true
|
|
|
|
stages:
|
|
- stage: webgpu
|
|
dependsOn: []
|
|
jobs:
|
|
- template: templates/jobs/win-ci-vs-2022-job.yml
|
|
parameters:
|
|
BuildConfig: 'RelWithDebInfo'
|
|
EnvSetupScript: setup_env.bat
|
|
buildArch: x64
|
|
# add --build_java if necessary
|
|
additionalBuildFlags: >-
|
|
--enable_pybind
|
|
--build_nodejs
|
|
--use_webgpu
|
|
--cmake_extra_defines onnxruntime_BUILD_UNIT_TESTS=ON
|
|
msbuildPlatform: x64
|
|
isX86: false
|
|
job_name_suffix: x64_RelWithDebInfo
|
|
RunOnnxRuntimeTests: ${{ parameters.RunOnnxRuntimeTests }}
|
|
ORT_EP_NAME: WebGPU
|
|
EnablePython: false
|
|
WITH_CACHE: true
|
|
MachinePool: onnxruntime-Win2022-VS2022-webgpu-A10
|
|
|
|
- stage: webgpu_external_dawn
|
|
dependsOn: []
|
|
jobs:
|
|
- job: build_x64_RelWithDebInfo
|
|
variables:
|
|
DEPS_CACHE_DIR: $(Agent.TempDirectory)/deps_ccache
|
|
ORT_CACHE_DIR: $(Agent.TempDirectory)/ort_ccache
|
|
TODAY: $[format('{0:dd}{0:MM}{0:yyyy}', pipeline.startTime)]
|
|
workspace:
|
|
clean: all
|
|
pool: onnxruntime-Win2022-VS2022-webgpu-A10
|
|
timeoutInMinutes: 300
|
|
steps:
|
|
- checkout: self
|
|
clean: true
|
|
submodules: none
|
|
|
|
- template: templates/jobs/win-ci-prebuild-steps.yml
|
|
parameters:
|
|
EnvSetupScript: setup_env.bat
|
|
DownloadCUDA: false
|
|
DownloadTRT: false
|
|
BuildArch: x64
|
|
BuildConfig: RelWithDebInfo
|
|
MachinePool: onnxruntime-Win2022-VS2022-webgpu-A10
|
|
WithCache: true
|
|
Today: $(Today)
|
|
|
|
- template: templates/jobs/win-ci-build-steps.yml
|
|
parameters:
|
|
WithCache: true
|
|
Today: $(TODAY)
|
|
CacheDir: $(ORT_CACHE_DIR)
|
|
AdditionalKey: " $(System.StageName) | RelWithDebInfo "
|
|
BuildPyArguments: '--config RelWithDebInfo --build_dir $(Build.BinariesDirectory) --skip_submodule_sync --update --parallel --cmake_generator "Visual Studio 17 2022" --use_webgpu --use_external_dawn --skip_tests --target onnxruntime_webgpu_external_dawn_test'
|
|
MsbuildArguments: '-maxcpucount'
|
|
BuildArch: x64
|
|
Platform: x64
|
|
BuildConfig: RelWithDebInfo
|
|
|
|
- script: |
|
|
onnxruntime_webgpu_external_dawn_test.exe
|
|
displayName: Run tests (onnxruntime_webgpu_external_dawn_test)
|
|
workingDirectory: '$(Build.BinariesDirectory)\RelWithDebInfo\RelWithDebInfo'
|
|
- script: |
|
|
onnxruntime_webgpu_external_dawn_test.exe --no_proc_table
|
|
displayName: Run tests (onnxruntime_webgpu_external_dawn_test)
|
|
workingDirectory: '$(Build.BinariesDirectory)\RelWithDebInfo\RelWithDebInfo'
|