ybjA',SSKrSSKrSSKrSSKJr SSKrSSKrSSKJrJ r SSK J r SSK J r SSKJrJr \R""\5rSS\\-\R*-S-S \\-S-S \S \S \S \S\S\S\S\S\S\S-S\SS4Sjjrg)N)Path)extract_raw_data_from_modelhas_external_data)ReplaceUpsampleWithResize) ONNXModel)add_pre_process_metadata&save_and_reload_model_with_shape_infer input_modeloutput_model_pathskip_optimizationskip_onnx_shapeskip_symbolic_shape auto_mergeint_maxguess_output_rankverbosesave_as_external_dataall_tensors_to_one_fileexternal_data_locationexternal_data_size_thresholdreturnc V UcU RSS5nUceUcS5e[R"SS9n[U5n[ U[ R 5(aUO[ R"U5nURVs/sH(nUR(aURS:XdM&UPM* nn[U5S:XacUSRnUS ::aN[[U5U5R5 [ RR!US 5n[#U5nU(d1SS KJn [*R-S 5 UR/UUUUU5nU(GdPU(dH[1US- 5nU (a[ R2"UUSU U SS9 O[ R4"UU5 Sn[1US- 5n[6R8"5nUUl[6R<R>Ul [ U[ R 5(a^[CU5(a [ES5e[GU5unnURI[KU5[KU55 URM5nO U(aU (aUROSS5 [6RP"UUS/S9nAUnU(dUbH[1US- 5nU (a[ R2"UUSU U SS9 O[ R4"UU5 Sn[ U[ R 5(a0[1[U5S- 5n[ R2"UUSU U SS9 [1US- 5n[ RZR]UU5 [ R"U5nSSS5 Wc7[ U[ R 5(aUO[ R"U5n[_U5 U (a[ R2"UUSU U U SS9 g[ R4"UU5 gs snf![(an[)S 5UeSnAff=f![RaA [*RUS5 [*RU[VRX"55 GNf=f!,(df  N=f)a(Shape inference and model optimization, in preparation for quantization. Args: input_model: Path to the input model file or ModelProto output_model_path: Path to the output model file skip_optimization: Skip model optimization step if true. This may result in ONNX shape inference failure for some models. skip_onnx_shape: Skip ONNX shape inference. Symbolic shape inference is most effective with transformer based models. Skipping all shape inferences may reduce the effectiveness of quantization, as a tensor with unknown shape can not be quantized. skip_symbolic_shape: Skip symbolic shape inference. Symbolic shape inference is most effective with transformer based models. Skipping all shape inferences may reduce the effectiveness of quantization, as a tensor with unknown shape can not be quantized. auto_merge: For symbolic shape inference, automatically merge symbolic dims when conflict happens. int_max: For symbolic shape inference, specify the maximum value for integer to be treated as boundless for ops like slice guess_output_rank: Guess output rank to be the same as input 0 for unknown ops verbose: Logs detailed info of inference, 0: turn off, 1: warnings, 3: detailed save_as_external_data: Saving an ONNX model to external data all_tensors_to_one_file: Saving all the external data to one file external_data_location: The file location to save the external file external_data_size_threshold: The size threshold for external data Ninput_model_pathzoutput_model_path is required.z pre.quant.)prefixzai.onnxrr )SymbolicShapeInferencezsympy is required for symbolic shape inference in quantization preprocessing. Install with: 'pip install sympy' or pass skip_symbolic_shape=True to quant_pre_process().z&Performing symbolic shape inference...zsymbolic_shape_inferred.onnxTF)rrsize_thresholdconvert_attributezoptimized.onnxzModelProto has external data not loaded into memory, ORT cannot create session. Please load external data before calling this function. See https://onnx.ai/onnx/repo-docs/ExternalData.html for more information.z7session.optimized_model_external_initializers_file_namezoptimized.onnx.dataCPUExecutionProvider) providerszYONNX Runtime Model Optimization Failed! Consider rerun with option `--skip_optimization'.zmodel_input.onnxzonnx_shape_inferred.onnx)rrlocationrr )0poptempfileTemporaryDirectoryr isinstanceonnx ModelProtoload opset_importdomainlenversionrrapplyversion_converterconvert_versionr &onnxruntime.tools.symbolic_shape_inferr ImportErrorloggerinfo infer_shapesstr save_modelsave onnxruntimeSessionOptionsoptimized_model_filepathGraphOptimizationLevelORT_ENABLE_BASICgraph_optimization_levelr ValueErrorradd_external_initializerslistSerializeToStringadd_session_config_entryInferenceSession Exceptionerror traceback format_excshape_inferenceinfer_shapes_pathr )r r r rrrrrrrrrrdeprecated_kwargs quant_tmp_dir temp_pathmodelopsetai_onnx_domain opset_versionreopt_model_path sess_optionexternal_namesexternal_valuessessinferred_model_paths ڤ/tmp/claude-0/-home-danvics-docker-quiz/c1e0577a-e42c-4a3d-b1ea-3edd61103a4e/scratchpad/stt/lib/python3.13/site-packages/onnxruntime/quantization/shape_inference.pyquant_pre_processr[s)V'++,>E  "" "  (J*JJ (  $ $L 9]' )+tGG TYYWbMc .3-?-?q-?Eu||W\WcWcgpWp%-?q ~ ! #*1-55M"))E*:MJPPR..>>ubI>uE" Y KK@ A*77! E!&!).L"LM (OO#.20G'C*/ IIe[1 -=!=>N 5)88: 7E 47B7Y7Y7j7j 4k4??;;(55(i 7RR]6^3NO99$~:NPTUdPef"-"?"?"AK)-B88QSh#33KYoXpq)K  !).L"LM (OO#.20G'C*/ IIe[1+t77!$}"58J"JK *.,C#?&+ #&i2L&L"M   2 2;@S TII12Em :p })+tGG TYYWbMcU#   "&$;+7#  %*+Cr !q v 5 o Y1134  5[ : 9sqAR %P)3P)9A;R5P.;BR C0Q ;C'R)R. Q 8 QQ  R ARRRR R() NNFFFFiFrFFNi)loggingr%rHpathlibrr(r:#onnxruntime.transformers.onnx_utilsrrfusionsr onnx_modelr quant_utilsr r getLogger__name__r4r7r)boolintr[rZrhs ^.!Y   8 $8<+/#! %#"'$))-(,y,tdoo-4y,TzD(y,y, y,  y,  y,y,y,y, y,"y, $Jy,#&y, y,rg