9iSSKrSSKrSSKrSSKJrJrJr SSKrSSKJ r SSK J r SSK J r Jr SSKJr SSKJrJrJr SS KJr SS KJr SS KJr SS KJrJrJr SS KJ r J!r! SSK"J#r# SSK$J%r% S\\ \RLRN4S\(\)\4SS4Sjr*S\RLRNSS4Sjr+S\ SS4Sjr,S\RLRNSS4Sjr-S1S\ S\.S\\\(\)\4S4S\\ \(\)\4S4S\ 4 Sjjr/S2S\RLRNS\\#\(\)\44S\.S\0\S4S\\\(\)\4S4S\\\#\(\)\44S\\ \(\)\4S4S \.S\ 4S!jjr1S1S\RLRNS\\#\(\)\44S\.S\0\S4S\\\(\)\4S4S\\ \(\)\4S4S\ 4S"jjr2S1S\RLRNS\\\(\)\4S4S\\ \(\)\4S4S\ 4S#jjr3\Rh"\%5S3S\RLRNS\\#\(\)\44S\0\S4S\\\(\)\4S4S\\\#\(\)\44S\\ \(\)\4S4S\ 4S$jj5r5\Rh"\%5S1S\RLRNS\\#\(\)\44S\0\S4S\\\(\)\4S4S\\ \(\)\4S4S\ 4 S%jj5r6S4S&\ S'\.S(\\\(\)\4S4S \.S)\.S\\#\(\)\4S4S\\ \(\)\4S4S*\.S+\.S\ 4S,jjr7\Rh"\%5S5S&\ S(\\\(\)\4S4S)\.S\\#\(\)\4S4S\\ \(\)\4S4S+\.S\ 4S-jj5r8S6S&\ S(\\\(\)\4S4S)\.S\\#\(\)\4S4S\\ \(\)\4S4S\ 4 S.jjr9S3S&\ S(\\\(\)\4S4S\\#\(\)\4S4S\\ \(\)\4S4S\ 4 S/jjr:S7S&\ S'\.S(\\\(\)\4S4S\ 4S0jjr;g)8N)AnyOptionalUnion) GraphModule)_USER_PRESERVED_ATTRIBUTES_KEY) BackendConfigget_tensorrt_backend_config)convert)ConvertCustomConfigFuseCustomConfigPrepareCustomConfig)fuse)ObservedGraphModule)prepare)QuantizationTracerScopeScopeContextManager)get_custom_module_class_keys#get_skipped_module_name_and_classes)QConfigMapping)DEPRECATION_WARNINGmodelpreserved_attrsreturnc[R"U5UR['UR[R5Hup#[ XU5 M g)zXStore preserved attributes to the model.meta so that it can be preserved during deepcopyN)copymetaritemssetattr)rr attr_nameattrs a/var/www/html/land-doc-ocr/venv/lib/python3.13/site-packages/torch/ao/quantization/quantize_fx.pyattach_preserved_attrs_to_modelr$sH 26?1KEJJ-.!::&DEKKM $'Ncz[U[5(d&[S[[ U55-S-S-5eg)Nz,input model must be a GraphModule, Got type:z Please make zsure to follow the tutorials.) isinstancer ValueErrorstrtype)rs r#_check_is_graph_moduler+%sK e[ ) ) $u+  .  .   *r%crURRHn[US5(aM0UlM g)aAttach meta field to all nodes of the graph if it does not exist, meta field is a field stores some meta information about the node, such as dtype and shape information for output of the node, this only exists if the program is captured by make_fx (used in quantize_pt2e flow), if the program is captured by torch.fx symbolic tracing, this field may not exist, so we add it here to avoid checking this all over the places rN)graphnodeshasattrr)rnodes r#!_attach_meta_to_node_if_not_existr10s, !!tV$$DI"r%c/nUR5H`up#[U[RRR R 5(aURU5 MU[U5 Mb UHOnURU [RRR R5URU'MQ g)z+Swap FloatFunctional with FXFloatFunctionalN) named_childrenr'torchaonn quantizedFloatFunctionalappend_swap_ff_with_fxff_modulesFXFloatFunctional)rmodules_to_swapnamemodules r#r:r:=sO,,.  fehhkk33CC D D  " "4 ( v & /   NN4 $xx{{44FFHt r%is_qatfuse_custom_configbackend_configc0[U5 [XX#5$)zInternal helper function to fuse modules in preparation for quantization Args: model: GraphModule object from symbolic tracing (torch.fx.symbolic_trace) )r+r)rr@rArBs r#_fuse_fxrDKs5! 1 BBr%qconfig_mappingexample_inputs.prepare_custom_config_equalization_configis_standalone_modulec ~Uc [5nUc [5n[U[5(a0[R "S[ SS9 [R"U5n[U5 [XG5upURn U V s0sH!n [X 5(dMU [X 5_M# n n [X5n [X RU55n[!U5 [#5R%UR5n['XX5n[)UUUU R*UUUUUS9 n[-UU 5 U$s sn f)a2Internal helper function for prepare_fx Args: `model`, `qconfig_mapping`, `prepare_custom_config`, `_equalization_config`: see docs for :func:`~torch.ao.quantization.prepare_fx` `is_standalone_module`: a boolean flag indicates whether we are quantizing a standalone module or not, a standalone module is a submodule of the parent module that is not inlined in the forward graph of the parent module, the way we quantize standalone module is described in: :func:`~torch.ao.quantization._prepare_standalone_module_fx` zPassing a prepare_custom_config_dict to prepare is deprecated and will not be supported in a future version. Please pass in a PrepareCustomConfig instead. stacklevel)rFrGrHrBrI)rrr'dictwarningswarn FutureWarning from_dictr:rpreserved_attributesr/getattrrrtracer1r set_preserved_attributesrDrnode_name_to_scoper$)rrEr@rFrGrHrBrIskipped_module_namesskipped_module_classespreserved_attr_namesr"rtracer graph_modulerAprepareds r# _prepare_fxr^ZsP*$ 3 5#-/'..  Q   !4 = =>S Tu3V401EE)(D 5  #ge""(  4 MFull5&9:L%l3)+DD22L2DUL!!%31%1 H$Ho> O7s D: D:c  [UUUUUUSS9$)a[Internal use only] Prepare a standalone module, so that it can be used when quantizing the parent module. standalone_module means it a submodule that is not inlined in parent module, and will be quantized separately as one unit. How the standalone module is observed is specified by `input_quantized_idxs` and `output_quantized_idxs` in the prepare_custom_config for the standalone module Returns: * model(GraphModule): prepared standalone module. It has these attributes in model.meta: * `standalone_module_input_quantized_idxs(List[Int])`: a list of indexes for the graph input that is expected to be quantized, same as input_quantized_idxs configuration provided for the standalone module * `standalone_module_output_quantized_idxs(List[Int])`: a list of indices for the graph output that is quantized same as input_quantized_idxs configuration provided for the standalone module T)rBrI)r^)rrEr@rFrGrBs r#_prepare_standalone_module_fxr`s&>  %! r%cUc [5n[U[5(a0[R"S[ SS9 [R "U5n[RRS5 URnUVs0sH!n[X5(dMU[X5_M# nn[RRU5n[U5 [!USX5n[#Xe5 U$s snf)aFuse modules like conv+bn, conv+bn+relu etc, model must be in eval mode. Fusion rules are defined in torch.ao.quantization.fx.fusion_pattern.py Args: * `model` (torch.nn.Module): a torch.nn.Module model * `fuse_custom_config` (FuseCustomConfig): custom configurations for fuse_fx. See :class:`~torch.ao.quantization.fx.custom_config.FuseCustomConfig` for more details Example:: from torch.ao.quantization import fuse_fx m = Model().eval() m = fuse_fx(m) zPassing a fuse_custom_config_dict to fuse is deprecated and will not be supported in a future version. Please pass in a FuseCustomConfig instead.rLz$quantization_api.quantize_fx.fuse_fxF)r r'rNrOrPrQrRr4_C_log_api_usage_oncerSr/rTfxsymbolic_tracer1rDr$)rrArBrZr"rr\s r#fuse_fxrgs*!-/$d++  N   .778JK HH  !GH-BB)(D 5  #ge""( 88**51L%l3L%1CTL#LB s C0C0c b[RRS5 [UUSUUUU5$)a'Prepare a model for post training quantization Args: * `model` (torch.nn.Module): torch.nn.Module model * `qconfig_mapping` (QConfigMapping): QConfigMapping object to configure how a model is quantized, see :class:`~torch.ao.quantization.qconfig_mapping.QConfigMapping` for more details * `example_inputs` (Tuple[Any, ...]): Example inputs for forward function of the model, Tuple of positional args (keyword args can be passed as positional args as well) * `prepare_custom_config` (PrepareCustomConfig): customization configuration for quantization tool. See :class:`~torch.ao.quantization.fx.custom_config.PrepareCustomConfig` for more details * `_equalization_config`: config for specifying how to perform equalization on the model * `backend_config` (BackendConfig): config that specifies how operators are quantized in a backend, this includes how the operators are observed, supported fusion patterns, how quantize/dequantize ops are inserted, supported dtypes etc. See :class:`~torch.ao.quantization.backend_config.BackendConfig` for more details Return: A GraphModule with observer (configured by qconfig_mapping), ready for calibration Example:: import torch from torch.ao.quantization import get_default_qconfig_mapping from torch.ao.quantization.quantize_fx import prepare_fx class Submodule(torch.nn.Module): def __init__(self) -> None: super().__init__() self.linear = torch.nn.Linear(5, 5) def forward(self, x): x = self.linear(x) return x class M(torch.nn.Module): def __init__(self) -> None: super().__init__() self.linear = torch.nn.Linear(5, 5) self.sub = Submodule() def forward(self, x): x = self.linear(x) x = self.sub(x) + x return x # initialize a floating point model float_model = M().eval() # define calibration function def calibrate(model, data_loader): model.eval() with torch.no_grad(): for image, target in data_loader: model(image) # qconfig is the configuration for how we insert observers for a particular # operator # qconfig = get_default_qconfig("fbgemm") # Example of customizing qconfig: # qconfig = torch.ao.quantization.QConfig( # activation=MinMaxObserver.with_args(dtype=torch.qint8), # weight=MinMaxObserver.with_args(dtype=torch.qint8)) # `activation` and `weight` are constructors of observer module # qconfig_mapping is a collection of quantization configurations, user can # set the qconfig for each operator (torch op calls, functional calls, module calls) # in the model through qconfig_mapping # the following call will get the qconfig_mapping that works best for models # that target "fbgemm" backend qconfig_mapping = get_default_qconfig_mapping("fbgemm") # We can customize qconfig_mapping in different ways. # e.g. set the global qconfig, which means we will use the same qconfig for # all operators in the model, this can be overwritten by other settings # qconfig_mapping = QConfigMapping().set_global(qconfig) # e.g. quantize the linear submodule with a specific qconfig # qconfig_mapping = QConfigMapping().set_module_name("linear", qconfig) # e.g. quantize all nn.Linear modules with a specific qconfig # qconfig_mapping = QConfigMapping().set_object_type(torch.nn.Linear, qconfig) # for a more complete list, please see the docstring for :class:`torch.ao.quantization.QConfigMapping` # argument # example_inputs is a tuple of inputs, that is used to infer the type of the # outputs in the model # currently it's not used, but please make sure model(*example_inputs) runs example_inputs = (torch.randn(1, 3, 224, 224),) # TODO: add backend_config after we split the backend_config for fbgemm and qnnpack # e.g. backend_config = get_default_backend_config("fbgemm") # `prepare_fx` inserts observers in the model based on qconfig_mapping and # backend_config. If the configuration for an operator in qconfig_mapping # is supported in the backend_config (meaning it's supported by the target # hardware), we'll insert observer modules according to the qconfig_mapping # otherwise the configuration in qconfig_mapping will be ignored # # Example: # in qconfig_mapping, user sets linear module to be quantized with quint8 for # activation and qint8 for weight: # qconfig = torch.ao.quantization.QConfig( # observer=MinMaxObserver.with_args(dtype=torch.quint8), # weight=MinMaxObserver.with-args(dtype=torch.qint8)) # Note: current qconfig api does not support setting output observer, but # we may extend this to support these more fine grained control in the # future # # qconfig_mapping = QConfigMapping().set_object_type(torch.nn.Linear, qconfig) # in backend config, linear module also supports in this configuration: # weighted_int8_dtype_config = DTypeConfig( # input_dtype=torch.quint8, # output_dtype=torch.quint8, # weight_dtype=torch.qint8, # bias_type=torch.float) # linear_pattern_config = BackendPatternConfig(torch.nn.Linear) \ # .set_observation_type(ObservationType.OUTPUT_USE_DIFFERENT_OBSERVER_AS_INPUT) \ # .add_dtype_config(weighted_int8_dtype_config) \ # ... # backend_config = BackendConfig().set_backend_pattern_config(linear_pattern_config) # `prepare_fx` will check that the setting requested by suer in qconfig_mapping # is supported by the backend_config and insert observers and fake quant modules # in the model prepared_model = prepare_fx(float_model, qconfig_mapping, example_inputs) # Run calibration calibrate(prepared_model, sample_inference_data) z'quantization_api.quantize_fx.prepare_fxFr4rcrdr^)rrErFrGrHrBs r# prepare_fxrjs:X HH  !JK    r%c \[RRS5 [UUSUUUS9$)aPrepare a model for quantization aware training Args: * `model` (torch.nn.Module): torch.nn.Module model * `qconfig_mapping` (QConfigMapping): see :func:`~torch.ao.quantization.prepare_fx` * `example_inputs` (Tuple[Any, ...]): see :func:`~torch.ao.quantization.prepare_fx` * `prepare_custom_config` (PrepareCustomConfig): see :func:`~torch.ao.quantization.prepare_fx` * `backend_config` (BackendConfig): see :func:`~torch.ao.quantization.prepare_fx` Return: A GraphModule with fake quant modules (configured by qconfig_mapping and backend_config), ready for quantization aware training Example:: import torch from torch.ao.quantization import get_default_qat_qconfig_mapping from torch.ao.quantization.quantize_fx import prepare_qat_fx class Submodule(torch.nn.Module): def __init__(self) -> None: super().__init__() self.linear = torch.nn.Linear(5, 5) def forward(self, x): x = self.linear(x) return x class M(torch.nn.Module): def __init__(self) -> None: super().__init__() self.linear = torch.nn.Linear(5, 5) self.sub = Submodule() def forward(self, x): x = self.linear(x) x = self.sub(x) + x return x # initialize a floating point model float_model = M().train() # (optional, but preferred) load the weights from pretrained model # float_model.load_weights(...) # define the training loop for quantization aware training def train_loop(model, train_data): model.train() for image, target in data_loader: ... # qconfig is the configuration for how we insert observers for a particular # operator # qconfig = get_default_qconfig("fbgemm") # Example of customizing qconfig: # qconfig = torch.ao.quantization.QConfig( # activation=FakeQuantize.with_args(observer=MinMaxObserver.with_args(dtype=torch.qint8)), # weight=FakeQuantize.with_args(observer=MinMaxObserver.with_args(dtype=torch.qint8))) # `activation` and `weight` are constructors of observer module # qconfig_mapping is a collection of quantization configurations, user can # set the qconfig for each operator (torch op calls, functional calls, module calls) # in the model through qconfig_mapping # the following call will get the qconfig_mapping that works best for models # that target "fbgemm" backend qconfig_mapping = get_default_qat_qconfig_mapping("fbgemm") # We can customize qconfig_mapping in different ways, please take a look at # the docstring for :func:`~torch.ao.quantization.prepare_fx` for different ways # to configure this # example_inputs is a tuple of inputs, that is used to infer the type of the # outputs in the model # currently it's not used, but please make sure model(*example_inputs) runs example_inputs = (torch.randn(1, 3, 224, 224),) # TODO: add backend_config after we split the backend_config for fbgemm and qnnpack # e.g. backend_config = get_default_backend_config("fbgemm") # `prepare_qat_fx` inserts observers in the model based on qconfig_mapping and # backend_config, if the configuration for an operator in qconfig_mapping # is supported in the backend_config (meaning it's supported by the target # hardware), we'll insert fake_quantize modules according to the qconfig_mapping # otherwise the configuration in qconfig_mapping will be ignored # see :func:`~torch.ao.quantization.prepare_fx` for a detailed explanation of # how qconfig_mapping interacts with backend_config prepared_model = prepare_qat_fx(float_model, qconfig_mapping, example_inputs) # Run training train_loop(prepared_model, train_loop) z+quantization_api.quantize_fx.prepare_qat_fxT)rBri)rrErFrGrBs r#prepare_qat_fxrls7L HH  !NO   %  r%r\ is_referenceconvert_custom_config_remove_qconfig is_decomposedkeep_original_weightsc vUc [5n[U[5(a0[R"S[ SS9 [R "U5n[U5 URn U V s0sH!n [X 5(dMU [X 5_M# n n [UUUUUUUUUS9 n [X5 U $s sn f)z_`is_standalone_module`: see docs in :func:`~torch.ao.quantization.prepare_standalone_module_fx`zPassing a convert_custom_config_dict to convert is deprecated and will not be supported in a future version. Please pass in a ConvertCustomConfig instead.rKrL)_remove_qconfig_flagrErBrprq) r r'rNrOrPrQrRr+rSr/rTr r$) r\rmrnrIrorErBrprqrZr"rr7s r# _convert_fxrts$ 3 5'..  Q   !4 = =>S T<(0EE)(D < & *gl))( ,'%#3 I$I? 's .B6B6c ^[RRS5 [USUUUUUS9$)a Convert a calibrated or trained model to a quantized model Args: * `graph_module` (torch.fx.GraphModule): A prepared and calibrated/trained model (GraphModule) * `convert_custom_config` (ConvertCustomConfig): custom configurations for convert function. See :class:`~torch.ao.quantization.fx.custom_config.ConvertCustomConfig` for more details * `_remove_qconfig` (bool): Option to remove the qconfig attributes in the model after convert. * `qconfig_mapping` (QConfigMapping): config for specifying how to convert a model for quantization. The keys must include the ones in the qconfig_mapping passed to `prepare_fx` or `prepare_qat_fx`, with the same values or `None`. Additional keys can be specified with values set to `None`. For each entry whose value is set to None, we skip quantizing that entry in the model:: qconfig_mapping = QConfigMapping .set_global(qconfig_from_prepare) .set_object_type(torch.nn.functional.add, None) # skip quantizing torch.nn.functional.add .set_object_type(torch.nn.functional.linear, qconfig_from_prepare) .set_module_name("foo.bar", None) # skip quantizing module "foo.bar" * `backend_config` (BackendConfig): A configuration for the backend which describes how operators should be quantized in the backend, this includes quantization mode support (static/dynamic/weight_only), dtype support (quint8/qint8 etc.), observer placement for each operators and fused operators. See :class:`~torch.ao.quantization.backend_config.BackendConfig` for more details Return: A quantized model (torch.nn.Module) Example:: # prepared_model: the model after prepare_fx/prepare_qat_fx and calibration/training # convert_fx converts a calibrated/trained model to a quantized model for the # target hardware, this includes converting the model first to a reference # quantized model, and then lower the reference quantized model to a backend # Currently, the supported backends are fbgemm (onednn), qnnpack (xnnpack) and # they share the same set of quantized operators, so we are using the same # lowering procedure # # backend_config defines the corresponding reference quantized module for # the weighted modules in the model, e.g. nn.Linear # TODO: add backend_config after we split the backend_config for fbgemm and qnnpack # e.g. backend_config = get_default_backend_config("fbgemm") quantized_model = convert_fx(prepared_model) z'quantization_api.quantize_fx.convert_fxF)rmrnrorErBrqr4rcrdrt)r\rnrorErBrqs r# convert_fxrw6s:t HH  !JK 3''%3 r%c \[RRS5 [USUUUUS9$)a%Convert a calibrated or trained model to a reference quantized model, see https://github.com/pytorch/rfcs/blob/master/RFC-0019-Extending-PyTorch-Quantization-to-Custom-Backends.md for more details, reference quantized model is a standard representation of a quantized model provided by FX Graph Mode Quantization, it can be further lowered to run on the target hardware, like accelerators Args: * `graph_module` (GraphModule): A prepared and calibrated/trained model (GraphModule) * `convert_custom_config` (ConvertCustomConfig): custom configurations for convert function. See :func:`~torch.ao.quantization.quantize_fx.convert_fx` for more details. * `_remove_qconfig` (bool): Option to remove the qconfig attributes in the model after convert. * `qconfig_mapping` (QConfigMapping): config for specifying how to convert a model for quantization. See :func:`~torch.ao.quantization.quantize_fx.convert_fx` for more details. * `backend_config` (BackendConfig): A configuration for the backend which describes how operators should be quantized in the backend. See :func:`~torch.ao.quantization.quantize_fx.convert_fx` for more details. Return: A reference quantized model (GraphModule) Example:: # prepared_model: the model after prepare_fx/prepare_qat_fx and calibration/training # TODO: add backend_config after we split the backend_config for fbgemm and qnnpack # e.g. backend_config = get_default_backend_config("fbgemm") reference_quantized_model = convert_to_reference_fx(prepared_model) z4quantization_api.quantize_fx.convert_to_reference_fxT)rmrnrorErBrv)r\rnrorErBs r#convert_to_reference_fxry|s7N HH  !WX 3''%  r%c ^[RRS5 [USUSUUSS9$)aConvert a calibrated or trained model to a reference quantized model, with decomposed representation for quantized Tensor see https://github.com/pytorch/rfcs/blob/master/RFC-0019-Extending-PyTorch-Quantization-to-Custom-Backends.md for more details, reference quantized model is a standard representation of a quantized model provided by FX Graph Mode Quantization, it can be further lowered to run on the target hardware, like accelerators Note: this is not public API Args: * `graph_module` (GraphModule): A prepared and calibrated/trained model (GraphModule) * `convert_custom_config` (ConvertCustomConfig): custom configurations for convert function. See :func:`~torch.ao.quantization.quantize_fx.convert_fx` for more details. * `_remove_qconfig` (bool): Option to remove the qconfig attributes in the model after convert. * `qconfig_mapping` (QConfigMapping): config for specifying how to convert a model for quantization. See :func:`~torch.ao.quantization.quantize_fx.convert_fx` for more details. * `backend_config` (BackendConfig): A configuration for the backend which describes how operators should be quantized in the backend. See :func:`~torch.ao.quantization.quantize_fx.convert_fx` for more details. Return: A reference quantized model (GraphModule) with operators working with decomposed quantized Tensor Example:: # prepared_model: the model after prepare_fx/prepare_qat_fx and calibration/training # TODO: add backend_config after we split the backend_config for fbgemm and qnnpack # e.g. backend_config = get_default_backend_config("fbgemm") reference_quantized_model = _convert_to_reference_decomposed_fx(prepared_model) z@quantization_api.quantize_fx._convert_to_reference_decomposed_fxTF)rmrnrorErBrprv)r\rnrErBs r##_convert_to_reference_decomposed_fxr{s>R HH  J 3'% r%c[UUUSS9$)a^[Internal use only] Convert a model produced by :func:`~torch.ao.quantization.prepare_standalone_module_fx` and convert it to a quantized model Returns a quantized standalone module, whether input/output is quantized is specified by prepare_custom_config, with input_quantized_idxs, output_quantized_idxs, please see docs for prepare_fx for details T)rI)rt)r\rmrns r#_convert_standalone_module_fxr}s !  r%)NN)NNNF)NNN)NFTNNFF)NTNNF)NTNN)FN)rsh '' @FXX0EE,& ( ehhoo- . (#s(^ (  ( %((// d  [ T  Iehhoo I$ I"IMAE C  C  C.S#XDE C-c3h=> C  C(OSLPAE!&E 88??E>4S>9:E E#s(O E !!4d38nd!JK E #5c3h)G#HI E-c3h=>EEEZOSAE ' 88??'>4S>9:' '#s(O ' !!4d38nd!JK ' -c3h=> ''XIMAE. 88??..S#XDE.-c3h=>. .b12 OSLPAE T 88??T>4S>9:T#s(OT!!4d38nd!JK T #5c3h)G#HI T -c3h=> TT3Tn12 OSAE m 88??m>4S>9:m#s(Om!!4d38nd!JK m -c3h=> m  m3mfOS!& CGAE"'---!!4d38nd!JK- -  - >4S>4?@ --c3h=>-- --`12OS CGAE"' BB !4d38nd!JKBB>4S>4?@ B -c3h=> B  BB3BNOS CGAE // !4d38nd!JK//>4S>4?@ / -c3h=> /  /hOSCGAE 44 !4d38nd!JK4>4S>4?@4-c3h=> 4  4rNR!!4d38nd!JK r%