i*SrSSKrSSKJr SSKJr SSKJrJrJ r J r J r J r J r Jr SSKJrJrJrJr "SS 5r"S S 5r"S S 5r"SS5r"SS5rg!\ar\"S5\eSrCff=f)a Example usage: .. code-block:: python from pathlib import Path import torch from executorch.runtime import Runtime, Program, Method et_runtime: Runtime = Runtime.get() program: Program = et_runtime.load_program(Path("/tmp/program.pte")) print("Program methods:", program.method_names) forward: Method = program.load_method("forward") inputs = (torch.ones(2, 2), torch.ones(2, 2)) outputs = forward.execute(inputs) print(f"Ran forward({inputs})") print(f" outputs: {outputs}") Example output: .. code-block:: text Program methods: {'forward'} Ran forward((tensor([[1., 1.], [1., 1.]]), tensor([[1., 1.], [1., 1.]]))) outputs: [tensor([[2., 2.], [2., 2.]])] Example usage with ETDump generation: Note: ETDump requires building ExecuTorch with event tracing enabled (CMake option ``EXECUTORCH_ENABLE_EVENT_TRACER=ON``). .. code-block:: python from pathlib import Path import os import torch from executorch.runtime import Runtime, Program, Method # Create program with etdump generation enabled et_runtime: Runtime = Runtime.get() program: Program = et_runtime.load_program( Path("/tmp/program.pte"), enable_etdump=True, debug_buffer_size=int(1e7), # 10MB buffer to capture all debug info ) # Load method and execute forward: Method = program.load_method("forward") inputs = (torch.ones(2, 2), torch.ones(2, 2)) outputs = forward.execute(inputs) # Write etdump result to file etdump_file = "/tmp/etdump_output.etdp" debug_file = "/tmp/debug_output.bin" program.write_etdump_result_to_file(etdump_file, debug_file) # Check that files were created print(f"ETDump file created: {os.path.exists(etdump_file)}") print(f"Debug file created: {os.path.exists(debug_file)}") print("Directory contents:", os.listdir("/tmp")) Example output: .. code-block:: text ETDump file created: True Debug file created: True Directory contents: ['program.pte', 'etdump_output.etdp', 'debug_output.bin'] Example usage with backend and operator introspection: .. code-block:: python from executorch.runtime import Runtime runtime = Runtime.get() # Check available backends backends = runtime.backend_registry.registered_backend_names print(f"Available backends: {backends}") # Check if a specific backend is available if runtime.backend_registry.is_available("XnnpackBackend"): print("XNNPACK backend is available") # List all registered operators operators = runtime.operator_registry.operator_names print(f"Number of registered operators: {len(operators)}") Example output: .. code-block:: text Available backends: ['XnnpackBackend', ...] # Depends on your build configuration XNNPACK backend is available Number of registered operators: 247 # Depends on linked kernels N)Path) ModuleType)AnyBinaryIODictListOptionalSequenceSetUnion)ExecuTorchMethodExecuTorchProgram MethodMeta VerificationzrPrebuilt /extension/pybindings/_portable_lib.so is not found. Please reinstall ExecuTorch from pip.c`\rSrSrSrS\SS4SjrS\\S\\4Sjr \ S\ 4S j5r S r g) MethodzaAn ExecuTorch method, loaded from a Program. This can be used to execute the method with inputs. methodreturnNcXlgN_method)selfrs Z/var/www/html/ai-image-ml/venv/lib/python3.13/site-packages/executorch/runtime/__init__.py__init__Method.__init__s inputsc$URU5$)zExecutes the method with the given inputs. Args: inputs: A sequence of input values, typically torch.Tensor objects. Returns: A list of output values, typically torch.Tensor objects. r)rrs rexecuteMethod.executes||F##rc6URR5$)zGets the metadata for the method. The metadata includes information about input and output specifications, such as tensor shapes, data types, and memory requirements. Returns: The MethodMeta object containing method specifications. )r method_metars rmetadataMethod.metadatas||''))rr)__name__ __module__ __qualname____firstlineno____doc__r rr rr!propertyrr&__static_attributes__rrrrsQ/D $hsm $ $ ** * *rrc\rSrSrSrS\S\\SS4Sjr\ S\ \ 4Sj5r S \ S\\ 4S jrS \ S\4S jrS \ S\ SS4SjrSrg)ProgramzyAn ExecuTorch program, loaded from binary PTE data. This can be used to load the methods/models defined by the program. programdatarNcX lXl0Ul[URR 55H+nSURURR U5'M- gr)_data_program_methodsrange num_methodsget_method_name)rr3r4 method_idxs rrProgram.__init__sN  57   9 9 ;DMM55d;>rrV)r(r)r*r+r,rrr-rrPr]boolrbr.r/rrrRrRsME,j,T,C$s)CC ? ? ?rrRcH\rSrSrSrS\SS4Sjr\S\\ 4Sj5r Sr g) OperatorRegistryzC>>rrfc \rSrSrSr\\R"SS9SSj55rS\ SS4S jr \ RS S S .S \ \\\\\4S\ S\S\S\4 SjjrSrg)Runtimeia5An instance of the ExecuTorch runtime environment. This can be used to concurrently load and execute any number of ExecuTorch programs and methods. Attributes: backend_registry: Registry for querying available hardware backends. operator_registry: Registry for querying available operators/kernels. )maxsizerc,SSKJs Js Jn [ US9$)zGets the Runtime singleton.rNrT),executorch.extension.pybindings.portable_lib extension pybindings portable_librorss rget Runtime.gets ML]33rrTNcP[U5Ul[U5UlXlgr)rRbackend_registryrfoperator_registryrWrXs rrRuntime.__init__s" / >!1-!@+rFr) verification enable_etdumpdebug_buffer_sizer4r~rrc[U[[45(a/URR [U5UUUS9n[ USS9$[U[ 5(aUnOe[U[5(a [ U5nOD[US5(aUR5nO"[S[U5RS35eURRUUUUS9n[ XVS9$)aWLoads an ExecuTorch program from a PTE binary. Args: data: The binary program data to load. Can be a file path (str or Path), bytes/bytearray, or a file-like object. verification: Level of program verification to perform (Minimal or InternalConsistency). Default is InternalConsistency. enable_etdump: If True, enables ETDump profiling for runtime performance analysis. Default is False. debug_buffer_size: Size of the debug buffer in bytes for ETDump data. Only used when enable_etdump=True. Default is 0. Returns: The loaded Program instance. )rrprogram_verificationN)r4readz\Expected data to be bytes, bytearray, a path to a .pte file, or a file-like object, but got .) isinstancerrPrW _load_programr1rO bytearrayhasattrr TypeErrortyper(_load_program_from_buffer)rr4r~rrp data_bytess r load_programRuntime.load_programs. dT3K ( (##11D +"3%1 2A 14( ( e $ $J i ( (tJ T6 " "JnostxoypCpCoDDEF     9 9 '/!- : q**r)rWr{r|)rro)r(r)r*r+r, staticmethod functools lru_cacherxrrrInternalConsistencyr rOrrrrPrdintr1rr.r/rrroros#4$4 ,,,&2%E%E#!" 1+E9hc9:1+# 1+  1+  1+ 1+1+rro)r,rpathlibrtypesrtypingrrrrr r r r rtr rrrModuleNotFoundErrorerr1rRrfror/rrrsfPLLL  **@9R9Rx??0 > >K+K+Q  >    s A''A;- A66A;