onnx-mlir
Representation and Reference Lowering of ONNX Models in MLIR Compiler Infrastructure
파일 탐색기
최종 버전 다운로드 (.zip)- Windows-CI.yml
- jenkins-build-llvm-project.py
- jenkins-build-onnx-mlir.py
- jenkins-check-model-zoo.py
- jenkins-cleanup-build-states.py
- jenkins-publish-docker-images.py
- jenkins-stop-previous-build.py
- jenkins-verify-om-package.py
- jenkins-verify-user-image.py
- jenkins-watch-llvm-project.py
- jenkins_common.py
- Jenkinsfile
- LLVM-Watch-Docker-Build.xml
- llvm-watch.html
- ONNX-MLIR-Pipeline-Docker-Build.xml
- config.yml
- black-format-check.yml
- clang-format-check.yml
- doxygen-docs-publish.yml
- macos-amd64-build.yml
- dependabot.yml
- Dockerfile.llvm-project
- Dockerfile.om-pyrt-light
- Dockerfile.onnx-mlir
- Dockerfile.onnx-mlir-dev
- onnx-mlir.py
- navigation.yml
- default.html
- style.scss
- onnx-mlir-logo.png
- devcontainer.json
- Dockerfile.llvm-project
- krnl.md
- onnx.md
- zhigh.md
- zlow.md
- file_same_as_stdout.py
- same_as_file.py
- test.in
- test.in.dc
- test.in
- test.in.dc
- README.md
- reference.cpp
- README.md
- reference.cpp
- README.md
- reference.cpp
- README.md
- reference.cpp
- test_file-same-as-stdout.py
- test_same-as-file.py
- check.py
- CMakeLists.txt
- directive.py
- doc_parser.py
- README.md
- utils.py
- CMakeLists.txt
- gen_add_onnx.py
- main.c
- main.cpp
- c_cpp_properties.json
- launch.json
- settings.json
- Dockerfile
- onnx-mlir-1280x640.png
- onnx-mlir-250-84.png
- onnx-mlir-big-text-250x85.png
- onnx-mlir-small.png
- onnx-mlir.png
- gen_mnist_onnx.py
- mnist-compile.py
- mnist-runPyCompileAndRuntime.py
- mnist-runPyRuntime.py
- mnist-simple.png
- mnist.cpp
- Mnist.java
- mnist.onnx
- multi-threading-test.py
- README.md
- requirements.txt
- update_env.sh
- AddingAFusionPattern.md
- ConvIm2Col.md
- ConvTranspose-OutputShape.md
- ConvTranspose.md
- GridSample.md
- .gitignore
- _config.yml
- AccelNNPAHowToUseAndTest.md
- AddCustomAccelerators.md
- BuildOnLinuxOSX.md
- BuildONNX.md
- BuildOnWindows.md
- BuildPyRuntimeLight.md
- BuildStandalone.md
- CMakeLists.txt
- ConstPropagationPass.md
- DebuggingNumericalError.md
- Docker.md
- DockerInDocker.md
- Documentation.md
- DocumentList.md
- DynamicDimensionAnalysis.md
- ErrorHandling.md
- GroundedLitTests.md
- ImportONNXDefs.md
- Instrumentation.md
- JsonConfigFile-NNPA.md
- JsonConfigFile.md
- LocationInfo.md
- LoweringCode.md
- ONNXAI.md
- Options.md
- PerformanceTesting.md
- Prerequisite.md
- ProfileModel.md
- PythonPackage.md
- Quantization-NNPA.md
- RunTorchModel.md
- SequenceType.md
- SupportedONNXOps-cpu.md
- SupportedONNXOps-NNPA.md
- SupportedOps-NNPA-supplement.md
- Testing.md
- TestingHighLevel.md
- UpdatingLLVMCommit.md
- UsingPyRuntime.md
- Workflow.md
- CMakeLists.txt
- OMCompilerMacros.h
- OMCompilerRuntimeTypes.h
- OMCompilerTypes.h
- CMakeLists.txt
- OMCompilationInfo.h
- OMEntryPoint.h
- OMInstrument.h
- OMSignature.h
- OMTensor.h
- OMTensorList.h
- OnnxDataType.h
- OnnxDataTypeMetaData.inc
- CMakeLists.txt
- CMakeLists.txt
- OnnxMlirCompiler.h
- OnnxMlirRuntime.h
- CMakeLists.txt
- NNPACompilerOptions.cpp
- NNPACompilerOptions.hpp
- NNPACompilerUtils.cpp
- NNPACompilerUtils.hpp
- NNPAJsonConfigObject.cpp
- NNPAJsonConfigObject.hpp
- NNPAPlacementReporter.cpp
- NNPAPlacementReporter.hpp
- ZHighDisposableGarbageCollector.cpp
- ZHighDisposableGarbageCollector.hpp
- CMakeLists.txt
- DevicePlacement.cpp
- DevicePlacementHeuristic.cpp
- DevicePlacementHeuristic.hpp
- GenerateConfigFile.cpp
- ONNXLegalityCheck.cpp
- ONNXLegalityCheck.hpp
- ONNXToZHigh.cpp
- ONNXToZHigh.hpp
- ONNXToZHigh.td
- ONNXToZHighCommon.cpp
- ONNXToZHighCommon.hpp
- ONNXToZHighCommon.td
- PerfModel.cpp
- PerfModel.hpp
- PerfModel.inc
- PerfModelArch14.inc
- PerfModelArch15.inc
- QuantOpSelection.cpp
- RewriteONNXForZHigh.cpp
- RewriteONNXForZHigh.hpp
- RewriteONNXForZHigh.td
- ZHighToONNX.cpp
- ZHighToONNX.td
- CMakeLists.txt
- ProcessStickData.cpp
- ProcessStickData.hpp
- ProcessStickData.hpp.inc
- ProcessStickDataHelper.cpp
- ProcessStickDataHelper.hpp
- ZHighToZLow.cpp
- ZHighToZLow.hpp
- ZHighToZLow.td
- CMakeLists.txt
- ZLowToLLVM.cpp
- ZLowToLLVM.hpp
- ZLowToLLVMCommon.cpp
- ZLowToLLVMCommon.hpp
- CMakeLists.txt
- BatchNorm.cpp
- Conv2D.cpp
- CMakeLists.txt
- DLF16ToF32.cpp
- ZHighDLF16ToF32.td
- Elementwise.cpp
- ExtendedLayoutTransform.cpp
- CMakeLists.txt
- F32ToDLF16.cpp
- ZHighF32ToDLF16.td
- FixGRUY.cpp
- FixGRUYh.cpp
- GRU.cpp
- LSTM.cpp
- MatMul.cpp
- MeanReduce2D.cpp
- Pooling.cpp
- QuantizedMatMul.cpp
- QuantizedStick.cpp
- Reduction.cpp
- Reshape.cpp
- Softmax.cpp
- CMakeLists.txt
- Stick.cpp
- ZHighStick.td
- StickForGRU.cpp
- StickForLSTM.cpp
- StickifiedConstantOfShape.cpp
- CMakeLists.txt
- Unstick.cpp
- ZHighUnstick.td
- CMakeLists.txt
- OpHelper.cpp
- OpHelper.hpp
- OpHelper.td
- ShapeHelper.hpp
- ZHighFusionOpHelper.cpp
- ZHighFusionOpHelper.hpp
- CMakeLists.txt
- ZHigh.td
- ZHighOps.cpp
- ZHighOps.hpp
- CMakeLists.txt
- DialectBuilder.cpp
- DialectBuilder.hpp
- ZLow.td
- ZLowCombine.cpp
- ZLowCombine.td
- ZLowOps.cpp
- ZLowOps.hpp
- CMakeLists.txt
- NNPAPasses.hpp
- omp_ops.c
- omp_ops.h
- seq_ops.c
- seq_ops.h
- utils.c
- zdnnx.c
- zdnnx.h
- zdnnx_ops.c
- zdnnx_ops.h
- zdnnx_ops_private.c
- zdnnx_ops_private.h
- zdnnx_private.h
- CMakeLists.txt
- OMRuntimeNNPA.c
- CMakeLists.txt
- Convert.cpp
- Convert.hpp
- DLF16Conversion.hpp
- Stickify.cpp
- Stickify.hpp
- CMakeLists.txt
- LayoutHelper.cpp
- LayoutHelper.hpp
- NNPALimit.cpp
- NNPALimit.hpp
- CMakeLists.txt
- FusionOpStickUnstick.cpp
- ZHighConstPropagation.cpp
- ZHighConstPropagation.td
- ZHighDecomposeStickUnstick.cpp
- ZHighDecomposeStickUnstick.td
- ZHighLayoutPropagation.cpp
- ZHighLayoutPropagation.td
- ZHighRecomposeToStickUnstick.cpp
- ZHighRecomposeToStickUnstick.td
- ZHighScrubDisposablePass.cpp
- CMakeLists.txt
- ZLowDummyOpForMultiDerefPass.cpp
- ZLowRewrite.cpp
- ZLowStickExpansion.cpp
- CMakeLists.txt
- FoldStdAlloc.cpp
- ReplaceMallocByHugePageMalloc.cpp
- CMakeLists.txt
- NNPAAccelerator.cpp
- NNPAAccelerator.hpp
- zdnn.cmake
- Accelerator.cpp
- Accelerator.hpp
- CMakeLists.txt
- CreateAcceleratorsInc.cmake
- InitAccelerators.cpp
- CMakeLists.txt
- FrontendDialectHelper.cpp
- FrontendDialectHelper.hpp
- FrontendDialectTransformer.cpp
- FrontendDialectTransformer.hpp
- ImportONNXUtils.cpp
- ImportONNXUtils.hpp
- ModelInputShaper.cpp
- ModelInputShaper.hpp
- OpBuildTable.inc
- OpBuildTable.inc.dc.in
- SymbolTable.hpp
- CMakeLists.txt
- Command.cpp
- Command.hpp
- CommandUtils.cpp
- CommandUtils.hpp
- CompilerDialects.cpp
- CompilerDialects.hpp
- CompilerOptions.cpp
- CompilerOptions.hpp
- CompilerPasses.cpp
- CompilerPasses.hpp
- CompilerUtils.cpp
- CompilerUtils.hpp
- DisposableGarbageCollector.cpp
- DisposableGarbageCollector.hpp
- ExternalUtil.hpp.in
- HeapReporter.cpp
- HeapReporter.hpp
- JsonConfigObject.cpp
- JsonConfigObject.hpp
- OMCompile.cpp
- OMCompile.hpp
- OMPyRt.cmake
- OptionUtils.cpp
- OptionUtils.hpp
- CMakeLists.txt
- ConvertSeqToMemref.cpp
- ConvertSeqToMemref.hpp
- KrnlSeqAlloc.cpp
- KrnlSeqDealloc.cpp
- KrnlSeqExtract.cpp
- KrnlSeqStore.cpp
- CMakeLists.txt
- ConvertKrnlToAffine.cpp
- ConvertKrnlToAffine.hpp
- KrnlCopyFromBuffer.cpp
- KrnlCopyToBuffer.cpp
- KrnlGetLinearOffsetIndex.cpp
- KrnlLoad.cpp
- KrnlMatmul.cpp
- KrnlMemset.cpp
- KrnlPrefetch.cpp
- KrnlStore.cpp
- KrnlTerminator.cpp
- KrnlToAffineHelper.cpp
- KrnlToAffineHelper.hpp
- CMakeLists.txt
- ConvertKrnlToLLVM.cpp
- ConvertKrnlToLLVM.hpp
- KrnlCall.cpp
- KrnlEntryPoint.cpp
- KrnlFindIndex.cpp
- KrnlGlobal.cpp
- KrnlInstrument.cpp
- KrnlMemcpy.cpp
- KrnlNone.cpp
- KrnlPrint.cpp
- KrnlPrintTensor.cpp
- KrnlRandomNormal.cpp
- KrnlRoundEven.cpp
- KrnlStrlen.cpp
- KrnlStrncmp.cpp
- KrnlToLLVMHelper.cpp
- KrnlToLLVMHelper.hpp
- KrnlUnaryMath.cpp
- KrnlVectorTypeCast.cpp
- RuntimeAPI.cpp
- RuntimeAPI.hpp
- LSTM.cpp
- LSTM.hpp
- RNNBase.cpp
- RNNBase.hpp
- CMakeLists.txt
- Custom.cpp
- Im2Col.cpp
- LayoutTransform.cpp
- ShapeTransform.cpp
- UpsampleAndPad.cpp
- If.cpp
- Loop.cpp
- Scan.cpp
- Yield.cpp
- CumSum.cpp
- DFT.cpp
- Elementwise.cpp
- Elementwise.hpp
- Gemm.cpp
- Hardmax.cpp
- LpNormalization.cpp
- LRN.cpp
- MatMul.cpp
- MatMulInteger.cpp
- MeanVarianceNormalization.cpp
- QLinearMatMul.cpp
- RandomNormal.cpp
- RandomNormalLike.cpp
- RandomUniform.cpp
- RandomUniformLike.cpp
- Reduction.cpp
- Softmax.cpp
- TopK.cpp
- Trilu.cpp
- Window.cpp
- CategoryMapper.cpp
- Conv.cpp
- GridSample.cpp
- Normalization.cpp
- Pooling.cpp
- NonMaxSuppression.cpp
- DynamicQuantizeLinear.cpp
- QuantizeHelper.hpp
- QuantizeLinear.cpp
- GRU.cpp
- LSTM.cpp
- RNN.cpp
- RNNBase.cpp
- RNNBase.hpp
- SequenceAt.cpp
- SequenceEmpty.cpp
- SequenceErase.cpp
- SequenceInsert.cpp
- SequenceLength.cpp
- ArgMinMax.cpp
- Compress.cpp
- Concat.cpp
- ConcatShapeTranspose.cpp
- Constant.cpp
- ConstantOfShape.cpp
- DepthToSpace.cpp
- Dim.cpp
- Expand.cpp
- Flatten.cpp
- FusedSplitOpGather.cpp
- Gather.cpp
- GatherElements.cpp
- GatherND.cpp
- Identity.cpp
- NonZero.cpp
- OneHot.cpp
- Pad.cpp
- PrintSignature.cpp
- Range.cpp
- Reshape.cpp
- Resize.cpp
- ReverseSequence.cpp
- ScatterElements.cpp
- ScatterND.cpp
- Shape.cpp
- Size.cpp
- Slice.cpp
- SpaceToDepth.cpp
- Split.cpp
- Squeeze.cpp
- Tile.cpp
- Transpose.cpp
- Unique.cpp
- Unsqueeze.cpp
- CMakeLists.txt
- ConvertONNXToKrnl.cpp
- ONNXToKrnlCommon.cpp
- ONNXToKrnlCommon.hpp
- PerfectHash.cpp
- PerfectHash.hpp
- MatMul.cpp
- Conv.cpp
- CMakeLists.txt
- ConvertONNXToLinalg.cpp
- ONNXBufferizableOpInterface.cpp
- ONNXBufferizableOpInterface.hpp
- ONNXToLinalgCommon.hpp
- Passes.td
- Clip.cpp
- Elementwise.cpp
- Gemm.cpp
- MatMul.cpp
- Reduction.cpp
- Softmax.cpp
- Conv.cpp
- ConvTranspose.cpp
- Normalization.cpp
- Pooling.cpp
- LSTM.cpp
- RNNBase.cpp
- RNNBase.hpp
- ArgMax.cpp
- Concat.cpp
- Constant.cpp
- DepthToSpace.cpp
- Dim.cpp
- Expand.cpp
- Flatten.cpp
- Gather.cpp
- GatherElements.cpp
- Identity.cpp
- OneHot.cpp
- Pad.cpp
- Reshape.cpp
- ScatterND.cpp
- Shape.cpp
- Slice.cpp
- Split.cpp
- Squeeze.cpp
- Tile.cpp
- Transpose.cpp
- Unsqueeze.cpp
- CMakeLists.txt
- ConvertONNXToStablehlo.cpp
- DialectBuilder.cpp
- DialectBuilder.hpp
- ONNXToStablehloCommon.cpp
- ONNXToStablehloCommon.hpp
- Conv2D.cpp
- Elementwise.cpp
- Gemm.cpp
- ReduceMean.cpp
- Softmax.cpp
- AveragePool.cpp
- MaxPoolSingleOut.cpp
- Concat.cpp
- Constant.cpp
- Reshape.cpp
- Resize.cpp
- Split.cpp
- SqueezeUnsqueeze.cpp
- CMakeLists.txt
- ConvertONNXToTOSA.cpp
- DialectBuilder.cpp
- DialectBuilder.hpp
- ONNXToTOSACommon.hpp
- ONNXToTOSACommon.hpp.inc
- ONNXToTOSALegalizeUtils.cpp
- ONNXToTOSALegalizeUtils.hpp
- CMakeLists.txt
- CMakeLists.txt
- DialectBuilder.cpp
- DialectBuilder.hpp
- Krnl.td
- KrnlHelper.cpp
- KrnlHelper.hpp
- KrnlOps.cpp
- KrnlOps.hpp
- KrnlTypes.cpp
- KrnlTypes.hpp
- CMakeLists.txt
- DialectBuilder.cpp
- DialectBuilder.hpp
- DialectBuilder.hpp.inc
- IndexExpr.cpp
- IndexExpr.hpp
- IndexExprBuilder.cpp
- IndexExprBuilder.hpp
- IndexExprDetail.cpp
- IndexExprDetail.hpp
- IndexExprValueProvider.hpp
- VectorMachineSupport.cpp
- VectorMachineSupport.hpp
- BType.cpp
- BType.hpp
- CMakeLists.txt
- DisposableElementsAttr.cpp
- DisposableElementsAttr.hpp
- DisposableElementsAttr.hpp.inc
- DisposableElementsAttributeStorage.hpp
- DisposablePool.cpp
- DisposablePool.hpp
- ElementsAttrBuilder.cpp
- ElementsAttrBuilder.hpp
- ElementsAttrHelper.cpp
- ElementsAttrHelper.hpp
- ElementsAttrHelper.hpp.inc
- Strides.cpp
- Strides.hpp
- StridesRange.hpp
- StridesRange.hpp.inc
- WideNum.cpp
- WideNum.hpp
- WideNum.hpp.inc
- ConcatShapeTranspose.cpp
- Custom.cpp
- Dim.cpp
- EntryPoint.cpp
- FusedOp.cpp
- Im2Col.cpp
- LayoutTransform.cpp
- None.cpp
- Return.cpp
- ShapeTransform.cpp
- UpsampleAndPad.cpp
- If.cpp
- Loop.cpp
- Scan.cpp
- Attention.cpp
- Bernoulli.cpp
- DFT.cpp
- Einsum.cpp
- EinsumHelper.cpp
- EinsumHelper.hpp
- ElementwiseBroadcast.cpp
- ElementwiseUnary.cpp
- Gemm.cpp
- HardMax.cpp
- LRN.cpp
- MatMul.cpp
- RandomNormal.cpp
- RandomNormalLike.cpp
- RandomUniform.cpp
- RandomUniformLike.cpp
- Reduction.cpp
- Scatter.cpp
- TopK.cpp
- Window.cpp
- CategoryMapper.cpp
- OneHotEncoder.cpp
- Conv.cpp
- Dropout.cpp
- NNHelper.cpp.inc
- Normalization.cpp
- Pooling.cpp
- RoiAlign.cpp
- NonMaxSuppression.cpp
- DequantizeLinear.cpp
- DynamicQuantizeLinear.cpp
- QuantizeLinear.cpp
- RNN.cpp
- Sequence.cpp
- SplitToSequence.cpp
- ArgMinMax.cpp
- Compress.cpp
- Concat.cpp
- ConcatFromSequence.cpp
- Constant.cpp
- ConstantOfShape.cpp
- DepthToSpace.cpp
- Expand.cpp
- EyeLike.cpp
- Flatten.cpp
- Gather.cpp
- GatherElements.cpp
- GatherND.cpp
- GridSample.cpp
- Identity.cpp
- NonZero.cpp
- OneHot.cpp
- Optional.cpp
- Pad.cpp
- Range.cpp
- Reshape.cpp
- Resize.cpp
- ReverseSequence.cpp
- Shape.cpp
- Size.cpp
- Slice.cpp
- SpaceToDepth.cpp
- Split.cpp
- Squeeze.cpp
- Tile.cpp
- Transpose.cpp
- Unique.cpp
- Unsqueeze.cpp
- Upsample.cpp
- Canonicalize.cpp
- Canonicalize.td
- CMakeLists.txt
- OpHelper.cpp
- OpHelper.hpp
- OpHelper.hpp.inc
- ShapeHelper.cpp
- ShapeHelper.hpp
- AppendDecodingStrategy.cpp
- AppendInstrumentedOutputsPass.cpp
- CMakeLists.txt
- ConstProp.cpp
- ConstProp.hpp
- ConstProp.td
- ConvOpt.cpp
- ConvOpt.hpp
- ConvOpt.td
- Decompose.cpp
- Decompose.hpp
- Decompose.td
- DecomposeEinsum.cpp
- DecomposeEinsum.hpp
- FusionOpBasePattern.hpp
- FusionOpHelper.cpp
- FusionOpHelper.hpp
- FusionOpTransform.cpp
- FusionOpTransform.hpp
- InstrumentONNXSignaturePass.cpp
- NodeNamePattern.hpp
- ONNXFusionOpHelper.cpp
- ONNXFusionOpHelper.hpp
- ONNXHybridTransformPass.cpp
- ONNXOpTransformPass.cpp
- ONNXPreKrnlVerifyPass.cpp
- Passes.td
- Recompose.cpp
- Recompose.hpp
- RemoveSameONNXDim.cpp
- ReplaceOpWithItsOperand.cpp
- ScrubDisposablePass.cpp
- SetONNXNodeName.cpp
- ShapeInference.cpp
- ShapeInference.hpp
- ShapeInferencePass.cpp
- SimplifyShapeRelatedOps.cpp
- StandardFuncReturnPass.cpp
- TestReifyResultShapesPass.cpp
- AdditionalONNXOps.td
- CMakeLists.txt
- DialectBuilder.cpp
- DialectBuilder.hpp
- DialectBuilder.hpp.inc
- ONNX.td
- ONNXAttributes.cpp
- ONNXAttributes.hpp
- ONNXDialect.cpp
- ONNXDialect.hpp
- ONNXDimAnalysis.cpp
- ONNXDimAnalysis.hpp
- OnnxElementsAttrBuilder.cpp
- OnnxElementsAttrBuilder.hpp
- ONNXLayoutHelper.hpp
- ONNXOps.cpp
- ONNXOps.hpp
- ONNXOps.td.inc
- ONNXOps.td.inc.dc.in
- ONNXTypes.cpp
- ONNXTypes.hpp
- ONNXUnsupportedOps.hpp
- ReifyIndexExprValueProvider.cpp
- ReifyIndexExprValueProvider.hpp
- CMakeLists.txt
- CMakeLists.txt
- HasOnnxSubgraphOpInterface.cpp
- HasOnnxSubgraphOpInterface.hpp
- HasOnnxSubgraphOpInterface.td
- ResultTypeInferenceOpInterface.cpp
- ResultTypeInferenceOpInterface.hpp
- ResultTypeInferenceOpInterface.td
- ShapeHelperOpInterface.cpp
- ShapeHelperOpInterface.hpp
- ShapeHelperOpInterface.td
- ShapeInferenceOpInterface.cpp
- ShapeInferenceOpInterface.hpp
- ShapeInferenceOpInterface.td
- SpecializedKernelOpInterface.cpp
- SpecializedKernelOpInterface.hpp
- SpecializedKernelOpInterface.td
- AttrBase.td
- Passes.hpp
- OMLogger.java
- OMModel.java
- OMRunner.java
- OMTensor.java
- OMTensorList.java
- CMakeLists.txt
- jnidummy.c
- jnilog.c
- jnilog.h
- jniwrapper.c
- Jsoniter.cmake
- CMakeLists.txt
- __init__.py
- utils.py
- helloworld.py
- test_add.mlir
- use_container_compiler.py
- use_local_compiler.py
- use_standalone_compile.py
- .gitignore
- pyproject.toml
- README.md
- VERSION_NUMBER
- __init__.py
- standalone_driver.py
- helloworld.py
- matmul.mlir
- run-matmul.py
- test_add.mlir
- .gitignore
- pyproject.toml
- README.md
- VERSION_NUMBER
- __init__.py
- backend.py
- config.py
- explain.py
- fx_utils.py
- metrics.py
- register.py
- sessioncache.py
- CMakeLists.txt
- test_add.py
- test_decoder_models.py
- test_encoder_models.py
- test_explain_context.py
- test_explain_simple_model.py
- test_gemm.py
- test_relu.py
- test_sessioncache.py
- utils.py
- LICENSE
- pyproject.toml
- README.md
- VERSION_NUMBER
- CMakeLists.txt
- onnxmlirdocker.py
- PyExecutionSession.cpp
- PyExecutionSession.hpp
- PyFloat16.hpp
- PyOMCompile.cpp
- PyOMCompile.hpp
- PyOMCompile.py
- PyRuntime.py
- CMakeLists.txt
- ExecutionSession.cpp
- ExecutionSession.hpp
- OMCRuntime.cmake
- OMExternalConstant.c
- OMIndexLookup.c
- OMInstrument.c
- OMInstrumentHelper.h
- OMPyRt.cmake
- OMRandomNormal.c
- OMRandomUniform.c
- OMResize.c
- OMSort.c
- OMSort.h
- OMTensor.c
- OMTensor.cpp
- OMTensor.inc
- OMTensorHelper.cpp
- OMTensorHelper.hpp
- OMTensorList.c
- OMTensorList.cpp
- OMTensorList.inc
- OMTensorListHelper.cpp
- OMTensorListHelper.hpp
- OMTopK.c
- OMUnique.c
- OMUnique.h
- OnnxDataType.c
- OnnxDataType.cpp
- OnnxDataType.inc
- PerfData.inc
- Arrays.hpp
- CMakeLists.txt
- Common.hpp
- Diagnostic.cpp
- Diagnostic.hpp
- KrnlSupport.cpp
- KrnlSupport.hpp
- OMPyRt.cmake
- SmallFP.cpp
- SmallFP.hpp
- SmallFPConversion.c
- SmallFPConversion.h
- SmallVectorHelper.hpp
- SuppressWarnings.h
- TypeUtilities.cpp
- TypeUtilities.hpp
- BinaryDecoder.cpp
- CMakeLists.txt
- CMakeLists.txt
- s390x-lrodata.ld
- CMakeLists.txt
- onnx-lsp-server.cpp
- CMakeLists.txt
- onnx-mlir-opt.cpp
- RegisterPasses.cpp
- RegisterPasses.hpp
- CMakeLists.txt
- onnx-mlir-reduce.cpp
- CMakeLists.txt
- BufferOMPLoopHoist.cpp
- CMakeLists.txt
- EliminateWriteOnlyAlloc.cpp
- InstrumentCleanupPass.cpp
- InstrumentPass.cpp
- LowerKrnlRegion.cpp
- ONNXCSEWithNodeName.cpp
- Passes.td
- PassesKrnl.td
- ProcessKrnlParallelClause.cpp
- ProcessKrnlParallelClause.hpp
- ProcessScfParallelPrivate.cpp
- ProcessScfParallelPrivate.hpp
- WriteOpStatsToModuleAttribute.cpp
- AddLLVMVersionHeader.cmake
- CMakeLists.txt
- Version.cpp
- Version.hpp
- CMakeLists.txt
- OMCRuntime.cmake
- OMPyRt.cmake
- onnx-mlir.cpp
- CMakeLists.txt
- CMakeLists.txt
- CMakeLists.txt
- lit.local.cfg
- CMakeLists.txt
- __init__.py
- all_test_names.txt
- CMakeLists.txt
- common.py
- conftest.py
- inference_backend.py
- input_verification_backend.py
- onnxmlir_node_tests.py
- signature_backend.py
- test.py
- test_config.py.in
- test_config_compilerlib.py.in
- test_gridsample.py
- variables.py
- CMakeLists.txt
- TestCategoryMapper.cpp
- CMakeLists.txt
- CompilerLibTest.cpp
- dyn-dim-analysis.mlir
- device_placement_pass.mlir
- device_placement_pass_load_config_file.mlir
- device_placement_pass_perf_model.mlir
- device_placement_pass_save_config_file.mlir
- emit-onnxir.mlir
- emit-zhighir.mlir
- lit.local.cfg
- load-cfg-all-on-cpu.json
- load-cfg-all-relu-on-cpu.json
- load-cfg-not-match-relu.json
- load-cfg-overlapping-condition.json
- load-cfg-some-relu-on-cpu.json
- add-onnx-level.mlir
- add-onnx-zhigh-level.mlir
- add-zhigh-level.mlir
- add-zlow-level.mlir
- concat-expand-stick-dynamic.mlir
- concat-expand-stick-unfuse.mlir
- concat-expand-stick.mlir
- expand-mul-reshape.mlir
- onnx-on-ztensor-dlf16-extended-layout-transform.mlir
- onnx-on-ztensor-dlf16-layernorm.mlir
- onnx-on-ztensor-dlf16.mlir
- onnx-on-ztensor.mlir
- add-arch15.mlir
- add-exec-cpu-opt.mlir
- add-exec-cpu.mlir
- add.mlir
- common-rules.mlir
- conv-for-cpu-z16-z17.mlir
- conv.mlir
- div-bcast.mlir
- div.mlir
- exp.mlir
- gelu.mlir
- gemm.mlir
- gru.mlir
- invsqrt.mlir
- leakyrelu.mlir
- log.mlir
- lstm.mlir
- matmul-arch15.mlir
- matmul.mlir
- matmulinteger.mlir
- max.mlir
- min.mlir
- mul.mlir
- pool.mlir
- qlinearmatmul.mlir
- quantization.mlir
- reducemax.mlir
- reducemean.mlir
- reducemin.mlir
- relu.mlir
- sigmoid.mlir
- softmax.mlir
- sqrt.mlir
- sub.mlir
- sum.mlir
- tanh.mlir
- cfg.json
- lit.local.cfg
- load-config-file.mlir
- save-config-file.mlir
- add.mlir
- max.mlir
- min.mlir
- mul.mlir
- relu.mlir
- sub.mlir
- add.mlir
- compiler-stick-unstick.mlir
- conv.mlir
- div.mlir
- dlf16_to_f32.mlir
- exp.mlir
- f32_to_dlf16.mlir
- gelu.mlir
- gru.mlir
- invsqrt.mlir
- leakyrelu.mlir
- log.mlir
- lstm.mlir
- matmul.mlir
- max.mlir
- meanreduce.mlir
- min.mlir
- mul.mlir
- pool.mlir
- quantized_matmul.mlir
- quantized_stick.mlir
- quantized_stick_O3.mlir
- reducemax.mlir
- reducemin.mlir
- relu.mlir
- reshape.mlir
- sigmoid.mlir
- softmax.mlir
- sqrt.mlir
- stick-unstick.mlir
- stickified-constant-of-shape.mlir
- stickified-constant.mlir
- sub.mlir
- tanh.mlir
- test-datalayout.mlir
- lower-all-to-llvm-arch15.mlir
- lower-all-to-llvm-constant-shape.mlir
- lower-all-to-llvm-typed-pointer.mlir
- lower-all-to-llvm.mlir
- normalize-memref.mlir
- rewrite-onnx-for-zhigh-arch15.mlir
- rewrite-onnx-for-zhigh.mlir
- default-config.mlir
- empty.json
- lit.local.cfg
- load-config-file.mlir
- nodetype-nodename-config.json
- omconfig.json
- save-config-file-using-attribute.mlir
- save-config-file.mlir
- tensorinfo-config.json
- tensorinfo-config.mlir
- ccfd.mlir
- concat-expand-stick-parallel.mlir
- conv-for-z16-z17.mlir
- data-transformation-on-ztensor-num2.mlir
- data-transformation-on-ztensor.mlir
- dense-out-attention-layer.mlir
- lit.local.cfg
- matmul-div-in-attention-layer.mlir
- nnpa-placement-reporter.mlir
- saturation.mlir
- softmax-matmul-in-attention-layer.mlir
- compiler-config.mlir
- lit.local.cfg
- module_op.mlir
- module_op_arch15.mlir
- lit.local.cfg
- module_op.mlir
- constprop.mlir
- lit.local.cfg
- quantizedconstprop.mlir
- conv.mlir
- elementwise.mlir
- gru.mlir
- lstm.mlir
- matmul.mlir
- meanreduce.mlir
- pool.mlir
- quantized_matmul.mlir
- quantized_stick.mlir
- stick-unstick.mlir
- eliminate-write-only-alloc.mlir
- fold-std-alloc.mlir
- replace-malloc-hugepage.mlir
- zhigh-combine.mlir
- zhigh-decompose-stick-unstick.mlir
- zhigh-fold-op-stick-unstick-fused-op-more.mlir
- zhigh-fold-op-stick-unstick-fused-op.mlir
- zhigh-fold-op-stick-unstick.mlir
- zhigh-fused-concat-expand-stick.mlir
- zhigh-fused-expand-mul-stick.mlir
- zhigh-layout-propagation.mlir
- zhigh-recompose-to-stick-unstick.mlir
- zlow-canonicalize.mlir
- zlow-normalize-by-using-dummyop.mlir
- zlow-rewrite.mlir
- zlow-stick-alloc-normalization.mlir
- zlow-stick-unstick-expansion.mlir
- lit.local.cfg
- add.mlir
- onnx_add.mlir
- onnx_all.mlir
- buffer_copy.mlir
- krnl_to_affine.mlir
- krnl_to_affine_matmul-parallel.mlir
- krnl_to_affine_matmul.mlir
- krnl_to_affine_parallel_clause.mlir
- krnl_to_affine_with_canonicalize.mlir
- matmul.mlir
- yield_to_affine.mlir
- constants.mlir
- lit.local.cfg
- symbol-postfix.mlir
- constants.mlir
- lit.local.cfg
- symbol-postfix.mlir
- constants_mix_types.mlir
- call_with_return.mlir
- compilation_info.mlir
- compilation_info_omit.mlir
- entry_point.mlir
- input_verification.mlir
- instrument_dwarf_marker.mlir
- krnl_C_library_function_lowering.mlir
- krnl_category_mapper.mlir
- krnl_global_with_alignment_lowering.mlir
- krnl_math_function_lowering.mlir
- krnl_random_normal_lowering.mlir
- krnl_to_llvm_omtensor_ownership.mlir
- lrodata-section.mlir
- none.mlir
- reshape.mlir
- Custom_with_canonicalize.mlir
- EntryPoint.mlir
- Im2Col.mlir
- Im2Col_O3.mlir
- LayoutTransform_with_canonicalize.mlir
- ShapeTransform_with_canonicalize.mlir
- UpsampleAndPad.mlir
- If.mlir
- If_with_canonicalize.mlir
- Loop.mlir
- Loop_with_canonicalize.mlir
- CumSum_with_canonicalize.mlir
- Elementwise.mlir
- Elementwise_with_canonicalize.mlir
- Elementwise_with_canonicalize_O3.mlir
- Elementwise_with_parallel_canonicalize_O3.mlir
- Gemm_with_canonicalize.mlir
- Gemm_with_parallel_canonicalize_O3.mlir
- HannWindow_with_canonicalize.mlir
- HannWindow_with_canonicalize_O3.mlir
- HardMax_with_canonicalize.mlir
- LpNormalization_with_canonicalize.mlir
- LpNormalization_with_canonicalize_O3.mlir
- MatMul.mlir
- MatMul_with_canonicalize.mlir
- MatMul_with_canonicalize_O3.mlir
- MatMul_with_parallel_canonicalize_O3.mlir
- MatMulInteger_with_canonicalize.mlir
- MatMulInteger_with_canonicalize_O3.mlir
- QLinearMatMul_with_canonicalize.mlir
- QLinearMatMul_with_canonicalize_O3.mlir
- RamdomNormal.mlir
- RamdomNormalLike.mlir
- RandomUniform.mlir
- RandomUniformLike.mlir
- Reduction.mlir
- Reduction_with_canonicalize.mlir
- Reduction_with_canonicalize_O3.mlir
- Reduction_with_parallel_canonicalize_O3.mlir
- Softmax_with_canonicalize.mlir
- Softmax_with_parallel_canonicalize_O3.mlir
- TopK_with_canonicalize.mlir
- Trilu_with_canonicalize.mlir
- Windows_with_canonicalize.mlir
- Windows_with_canonicalize_O3.mlir
- onnx_lowering_category_mapper.mlir
- Conv_with_canonicalize.mlir
- Normalization.mlir
- Normalization_O3_SIMD_canonicalize.mlir
- Normalization_O3_SIMD_parallel_canonicalize.mlir
- Normalization_with_canonicalize.mlir
- Pooling.mlir
- Pooling_with_canonicalize.mlir
- onnx_lowering_nonmaxsuppression_op.mlir
- DequantizeLinear_with_canonicalize.mlir
- DynamicQuantizeLinear_with_canonicalize.mlir
- DynamicQuantizeLinear_with_simd_canonicalize.mlir
- DynamicQuantizeLinear_with_simd_parallel_canonicalize.mlir
- QuantizationWithoutZeroPoint.mlir
- QuantizeLinear_with_canonicalize.mlir
- QuantizeLinear_with_fast_math_canonicalize.mlir
- onnx_lowering_gru_op.mlir
- onnx_lowering_lstm_op.mlir
- onnx_lowering_rnn_op.mlir
- Sequence_with_dealloc.mlir.broken
- SequenceErase.mlir
- SequenceInsert_with_canonicalize.mlir
- Compress_with_canonicalize.mlir
- Concat_with_canonicalize.mlir
- Concat_with_parallel_canonicalize_O3.mlir
- Constant.mlir
- ConstantOfShape.mlir
- Expand_with_canonicalize.mlir
- Expand_with_parallel_canonicalize_O3.mlir
- Flatten.mlir
- FusedSplitOpGather.mlir
- FusedSplitOpGather_with_parallel.mlir
- FusedSplitOpGatherFallback.mlir
- FusedSplitOpGatherScalar.mlir
- Gather.mlir
- Gather_safe.mlir
- Gather_with_canonicalize.mlir
- GatherElements.mlir
- GatherElements_with_canonicalize.mlir
- GatherND.mlir
- GatherND_with_canonicalize.mlir
- GridSample.mlir
- GridSampleParallel.mlir
- Identity.mlir
- onnx_lowering_depth_to_space_op.mlir
- onnx_lowering_range_op.mlir
- onnx_lowering_space_to_depth.mlir
- Pad_with_canonicalize.mlir
- Reshape.mlir
- Reshape_with_canonicalize.mlir
- Resize.mlir
- ReverseSquence.mlir
- ScatterElements.mlir
- ScatterND.mlir
- Size.mlir
- Slice_with_canonicalize.mlir
- Slice_with_parallel_canonicalize_O3.mlir
- Split.mlir
- Split_with_canonicalize.mlir
- Squeeze.mlir
- Squeeze_with_canonicalize.mlir
- Tile_with_canonicalize.mlir
- Transpose.mlir
- Transpose_neg_pattern_with_canonicalize.mlir
- Transpose_with_canonicalize.mlir
- Transpose_with_parallel_canonicalize_O3.mlir
- Unique_with_canonicalize.mlir
- Unsqueeze.mlir
- onnx_lowering_fuse.mlir
- onnx_lowering_reuse.mlir
- mixed_ops.mlir
- MatMul.mlir
- Conv.mlir
- driver.cpp
- Clip.mlir
- Elementwise.mlir
- Gemm.mlir
- GlobalPooling.mlir
- MatMul.mlir
- Reduction.mlir
- Softmax-Decompose.mlir
- Softmax.mlir
- Conv.mlir
- ConvTranspose.mlir
- Normalization.mlir
- Pooling.mlir
- LSTM-loop.mlir
- LSTM.mlir
- ArgMax.mlir
- Concat.mlir
- Constant.mlir
- DepthToSpace.mlir
- Dim.mlir
- Expand.mlir
- Flatten.mlir
- Gather.mlir
- GatherElements.mlir
- Identity.mlir
- OneHot.mlir
- Pad.mlir
- Reshape.mlir
- ScatterND.mlir
- Shape.mlir
- Slice.mlir
- Split.mlir
- Squeeze.mlir
- Tile.mlir
- Transpose.mlir
- Unsqueeze.mlir
- lit.local.cfg
- Conv.mlir
- Elementwise.mlir
- Gemm_to_matmul.mlir
- ReduceMean.mlir
- Softmax.mlir
- AveragePool.mlir
- MaxPoolSingleOut.mlir
- Concat.mlir
- Constant.mlir
- Reshape.mlir
- Resize.mlir
- Split.mlir
- SqueezeUnsqueeze.mlir
- config_file.mlir
- custom-omconfig.json
- lit.local.cfg
- omconfig.json
- check_verbosity.mlir
- check_verbosity.mlir
- dllexport.mlir
- append_decoding_strategies.mlir
- append_instrumented_outputs.mlir
- append_instrumented_outputs_noop.mlir
- buffer_loop_hoisting.mlir
- bufferization.mlir
- check_passthrough_options.mlir
- compilation_info.mlir
- compilation_info_in_module_op.mlir
- compile_phases.mlir
- do_not_emit_full_mlir.mlir
- instrument_onnx_node.mlir
- invalid_output_path.mlir
- llvm.ident.mlir
- message-constant-file.mlir
- model_tag.mlir
- omit-compile-info.mlir
- outputfile.mlir
- product.version.mlir
- remove_onnx_arg_attrs.mlir
- run_onnx_lib_static.mlir
- shape_information.mlir
- shape_information_mix.mlir
- shape_information_range.mlir
- shape_information_set_batch_size.mlir
- static_quantization.mlir
- version.mlir
- block.mlir
- define_loops_not_cse.mlir
- get_induction_var_value.mlir
- get_linear_offset_index.mlir
- hoisting.mlir
- imperfectly_nested_stmts.mlir
- krnl_memset.mlir
- krnl_normalization.mlir
- krnl_region_lowering.mlir
- krnl_sequence_lowering.mlir
- krnl_substitution.mlir
- ops.mlir
- permute.mlir
- unroll.mlir
- lit.local.cfg
- module_op.mlir
- lit.local.cfg
- module_op.mlir
- test_castlike_decomp.json
- cast_to_int_4_and_back.onnxtext
- dim_param.json
- dim_param_and_option.json
- dim_param_static_arg_dynamic_arg.json
- external_data.external
- external_data.json
- external_data_traversal.json
- external_data_traversal_v2.json
- external_data_traversal_v3.json
- fp16_nonraw_data.json
- fp16_raw_data.json
- fp8_nonraw_data.json
- fp8_raw_data.json
- fun_model_test.onnxtext
- functiontest_attrname.onnxtext
- functiontest_attrwithdefault.onnxtext
- functiontest_nestedcall.onnxtext
- fusedmatmul.onnxtext
- layer_normalization_function_decomposition.onnxtext
- nonraw_data.json
- prims_convert_element_type.onnxtext
- random_normal_like_dtype_bf16.onnxtext
- random_normal_like_dtype_f32.onnxtext
- random_normal_like_no_dtype.onnxtext
- random_uniform_like.onnxtext
- raw_data.json
- sequence_map_resize.onnxtext
- string_data.json
- test_abs.onnxtext
- test_acos_22.onnxtext
- test_acos_7.onnxtext
- test_add_dimparams.onnxtext
- test_cast.onnxtext
- test_range_float_type_positive_delta_expanded.json
- test_strnormalizer_export_monday_casesensintive_nochangecase.json
- upsample_10.onnxtext
- upsample_7.onnxtext
- upsample_9.onnxtext
- zipmap.onnxtext
- invalid.mlir
- onnx_canonicalization.mlir
- onnx_canonicalization_locations.mlir
- onnx_canonicalization_upsample_and_pad.mlir
- onnx_constprop.mlir
- onnx_constprop_flags.mlir
- onnx_constprop_locations.mlir
- onnx_constprop_no_shape_inference.mlir
- onnx_constprop_parallel.mlir
- onnx_conv_opt.mlir
- onnx_cse.mlir
- onnx_cse_with_node_name.mlir
- onnx_decompose.mlir
- onnx_decompose_canonicalize.mlir
- onnx_decompose_conv.mlir
- onnx_decompose_convtranspose.mlir
- onnx_decompose_convtranspose_output_shape.mlir
- onnx_decompose_customop.mlir
- onnx_decompose_einsum.mlir
- onnx_decompose_hardswish.mlir
- onnx_dim_analysis.mlir
- onnx_fold.mlir
- onnx_fusion_op_transform.mlir
- onnx_hybrid_transform.mlir
- onnx_location.mlir
- onnx_lowering_call_canonicalize_O3.mlir
- onnx_pre_krnl_verify_error.mlir
- onnx_recompose.mlir
- onnx_recompose_combine_parallel_conv.mlir
- onnx_recompose_locations.mlir
- onnx_reify_result_shapes_add.mlir
- onnx_remove_same_onnx_dim.mlir
- onnx_replace_op_with_its_operand.mlir
- onnx_set_node_name.mlir
- onnx_shape_inference.mlir
- onnx_shape_inference_attention.mlir
- onnx_shape_inference_einsum.mlir
- onnx_shape_inference_error.mlir
- onnx_shape_inference_maxpool.mlir
- onnx_shape_inference_optional.mlir
- onnx_shape_inference_upsample_and_pad.mlir
- onnx_simplify_shape_related_ops.mlir
- onnx_structure.mlir
- test_conv1x1_decompose.mlir
- buffer_omploop_hoisting.mlir
- krnl_parallel_clause_to_omp.mlir
- scf_parallel_private.mlir
- CMakeLists.txt
- lit.cfg.py
- lit.site.cfg.py.in
- CategoryMapperModel.cpp
- CMakeLists.txt
- ConvModel.cpp
- ElementwiseModel.cpp
- GemmModel.cpp
- GRUModel.cpp
- LeakyReluModel.cpp
- LSTMModel.cpp
- MatMulModel.cpp
- ModelLib.cpp
- ModelLib.hpp
- RNNModel.cpp
- ScanModel.cpp
- SoftplusModel.cpp
- add_sub_onnx.py
- CMakeLists.txt
- CMakeLists.txt
- Common.hpp
- TestConv.cpp
- TestElementwise.cpp
- TestGemm.cpp
- TestGRU.cpp
- TestLeakyRelu.cpp
- TestLoop.cpp
- TestLSTM.cpp
- TestMatMul2D.cpp
- TestMatMulBroadcast.cpp
- TestRNN.cpp
- TestScan.cpp
- TestSoftplus.cpp
- CMakeLists.txt
- ParseBenchmarks.py
- PerfConv.cpp
- PerfElementwise.cpp
- PerfGemm.cpp
- PerfHelper.cpp
- PerfHelper.hpp
- PerfRNN.cpp
- CMakeLists.txt
- TestBType.cpp
- CMakeLists.txt
- TestCustomFn.cpp
- CMakeLists.txt
- TestDisposableElementsAttr.cpp
- CMakeLists.txt
- TestONNXEinsumOp.cpp
- CMakeLists.txt
- TestGemmVersionConv.cpp
- CMakeLists.txt
- OMTensorTest.c
- CMakeLists.txt
- TestSmallFP.cpp
- CMakeLists.txt
- TestStrides.cpp
- CMakeLists.txt
- TestInstrumentation.cpp
- CMakeLists.txt
- benchmark
- onnx
- pybind11
- rapidcheck
- stablehlo
- cppcheck-scan.py
- cppcheck_exclude_dirs.txt
- cppcheck_suppressions.txt
- add.mlir
- commands.sh
- div.mlir
- driver-nnpa.sh
- driver-quant.sh
- driver-zdnn-csu-more.sh
- driver-zdnn-csu.sh
- exp.mlir
- gelu.mlir
- generatePerfModel.ipynb
- log.mlir
- matmul_3d.mlir
- matmul_bcast23.mlir
- max.mlir
- min.mlir
- mul.mlir
- pow-2.mlir
- pow-3.mlir
- pow-4.mlir
- pow-8.mlir
- README.md
- reducemean.mlir
- relu.mlir
- sigmoid.mlir
- softmax.mlir
- sub.mlir
- tanh.mlir
- __init__.py
- test_1.py
- test_2.py
- test_3.py
- test_add.onnx
- LICENSE
- pyproject.toml
- README.md
- VERSION_NUMBER
- gpt2-decode.py
- omdecoder.py
- omgenerate.py
- README.md
- run_gpt2_from_huggingface.py
- dim_param.py
- fp16_data.py
- fp8_data.py
- string_data.py
- x_data.py
- analyze-simd.py
- AnalyzeShape.py
- build-mlir-standalone.sh
- build-mlir.cmd
- build-mlir.sh
- build-onnx-mlir.cmd
- build-run-onnx-lib.sh
- check-doc-example.sh
- check-docs.cmd
- check-onnx-backend-numerical.sh
- check-onnx-mlir.cmd
- check-onnx-numerical.cmd
- check-unittest.cmd
- check-unittest.sh
- CheckONNXModel.py
- clone-mlir.sh
- CMakeLists.txt
- collect_perf_stats.sh
- documentOps.py
- example-cfg.yaml
- fixLitTest.py
- gen_onnx_mlir.py
- GroundLitTest.py
- install-mlir.cmd
- install-mlir.sh
- install-onnx-mlir-standalone.sh
- install-onnx-mlir.sh
- install-onnx.sh
- install-protobuf.cmd
- IsolatePass.py
- make-report.py
- make-timechart.py
- mlir2FileCheck.py
- mlir_log_utils.py
- mlirAffine2cpp.py
- onnx-mlir-print.sh
- onnx-mlir-report-heap.sh
- onnx-mlir-truncate.py
- onnx2json.py
- onnx2text.py
- onnxExternalizeData.py
- onnxmlirrun.py
- parse-cntr-report.py
- perf_counters.txt
- pre-onnx-mlir.py
- profile-model.py
- repairLitTestSeparators.py
- RunONNXLib.cpp
- RunONNXModel.py
- RunONNXModelZoo.py
- .clang-format
- .dockerignore
- .gitignore
- .gitmodules
- CHANGELOG.md
- CMakeLists.txt
- CODE_OF_CONDUCT.md
- CODING_PRACTICE.md
- CONTRIBUTING.md
- Doxyfile
- GOVERNANCE.md
- LICENSE
- MLIR.cmake
- OMCRuntime.cmake
- OMPyRt.cmake
- pyproject.toml
- README.md
- requirements.txt
- SECURITY.md
- VERSION_NUMBER
# 설치 가이드
1. 코드 내려받기
git clone https://github.com/onnx/onnx-mlir
깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.
cd onnx-mlir
방금 내려받은 프로젝트 폴더 안으로 이동합니다.
2. Docker
쉬움 추천사전 준비물
- Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
- Docker Desktop 컨테이너를 빌드하고 실행하려면 필요합니다. 설치 후 실행해서 백그라운드에 켜두세요.
docker build -f docker/Dockerfile.llvm-project -t onnx-mlir .
Dockerfile을 기반으로 실행 가능한 이미지를 빌드합니다.
docker run -p 8080:80 onnx-mlir
빌드된 이미지를 실제 컨테이너로 실행합니다.
터미널에 docker compose ps 를 입력해 컨테이너들이 Up 상태인지 확인하세요. README에 포트 번호가 적혀있다면 브라우저에서 http://localhost:포트번호 로 접속해보세요.
3. CMake
보통사전 준비물
cmake >= 3.26.0
이 명령어를 터미널에 그대로 입력해 실행하세요.
build 폴더 안에 실행 파일이 생성됐는지 확인하고, 직접 실행해보세요 (예: ./build/앱이름).
이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.
// repository documentation
Was this content helpful?
(0 ratings)