g^(h~ddlZddlZddlmZmZmZddlZddlmZddl m Z ddl m Z m Z ddlmZddlmZmZmZdd lmZdd lmZdd lmZdd lmZmZmZdd lmZm Z ddl!m"Z"deeejFjHfde%e&efddfdZ'dejFjHddfdZ(deddfdZ)dejFjHddfdZ* d0dede+deee%e&efdfdee e%e&efdfdef dZ, d1dejFjHdee"e%e&effde+de-edfdeee%e&efdfdeee"e%e&effdee e%e&efdfde+defd Z. d0dejFjHdee"e%e&effde+de-edfdeee%e&efdfdee e%e&efdfdefd!Z/ d0dejFjHdeee%e&efdfdee e%e&efdfdefd"Z0 d2dejFjHdee"e%e&effde-edfdeee%e&efdfdeee"e%e&effdee e%e&efdfdefd#Z1 d0dejFjHdee"e%e&effde-edfdeee%e&efdfdee e%e&efdfdef d$Z2 d3d%ed&e+d'eee%e&efdfde+d(e+dee"e%e&efdfdee e%e&efdfd)e+d*e+defd+Z3 d4d%ed'eee%e&efdfd(e+dee"e%e&efdfdee e%e&efdfd*e+defd,Z4 d5d%ed'eee%e&efdfd(e+dee"e%e&efdfdee e%e&efdfdef d-Z5 d2d%ed'eee%e&efdfdee"e%e&efdfdee e%e&efdfdef d.Z6 d6d%ed&e+d'eee%e&efdfdefd/Z7y)7N)AnyOptionalUnion) GraphModule)_USER_PRESERVED_ATTRIBUTES_KEY) BackendConfigget_tensorrt_backend_config)convert)ConvertCustomConfigFuseCustomConfigPrepareCustomConfig)fuse)ObservedGraphModule)prepare)QuantizationTracerScopeScopeContextManager)get_custom_module_class_keys#get_skipped_module_name_and_classes)QConfigMappingmodelpreserved_attrsreturnctj||jt<|jtjD]\}}t |||y)zXStore preserved attributes to the model.meta so that it can be preserved during deepcopyN)copymetaritemssetattr)rr attr_nameattrs _/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/torch/ao/quantization/quantize_fx.pyattach_preserved_attrs_to_modelr#sP 26?1KEJJ-.!::&DEKKM( 4y$'(cpt|ts&tdtt |zdzdzy)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*#sH e[ ) $u+  .  .   *r$cb|jjD]}t|dri|_y)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_existr0.s. !!tV$DIr$cg}|jD]Z\}}t|tjjj j r|j|Pt|\|D]N}|j|=tjjj j|j|<Py)z+Swap FloatFunctional with FXFloatFunctionalN) named_childrenr&torchaonn quantizedFloatFunctionalappend_swap_ff_with_fxff_modulesFXFloatFunctional)rmodules_to_swapnamemodules r"r9r9;sO,,.' f fehhkk33CC D  " "4 ( v & '  I NN4 $xx{{44FFHtIr$is_qatfuse_custom_configbackend_configc4t|t||||S)zInternal helper function to fuse modules in preparation for quantization Args: model: GraphModule object from symbolic tracing (torch.fx.symbolic_trace) )r*r)rr?r@rAs r"_fuse_fxrCIs#5!  v)> r$qconfig_mappingexample_inputs.prepare_custom_config_equalization_configis_standalone_modulec t| t}| t}t|tr1t j dt dtj|}t|t||\}} |j} | D cic]} t|| r | t|| } } t|| } t|| j|}t!|t#j%|j}t'||||}t)|||| j*||||| }t-|| |Scc} w)aZInternal helper function for prepare_fx Args: `model`, `qconfig_mapping`, `prepare_custom_config`, `_equalization_config`: see docs for :func:`~torch.ao.quantization.prepare_fx` `is_standalone_module`: a boolean flag indicates whether we are quantizing a standalone module or not, a standalone module is a submodule of the parent module that is not inlined in the forward graph of the parent module, the way we quantize standalone module is described in: :func:`~torch.ao.quantization._prepare_standalone_module_fx` zPassing a prepare_custom_config_dict to prepare is deprecated and will not be supported in a future version. Please pass in a PrepareCustomConfig instead. stacklevel)rErFrGrArH)rrr&dictwarningswarn FutureWarning from_dictr9rpreserved_attributesr.getattrrrtracer0r set_preserved_attributesrCrnode_name_to_scoper#)rrDr?rErFrGrArHskipped_module_namesskipped_module_classespreserved_attr_namesr!rtracer graph_moduler@prepareds r" _prepare_fxr]Zs[*$ 3 5#-/'.  Q   !4 = =>S Tu3V34001EE)  5$  geT""O  46L MFufll5&9:L%l3)+DD22L&2DnUL!!%31%1 H$Ho> O7s D5c &t||||||dS)a[Internal use only] Prepare a standalone module, so that it can be used when quantizing the parent module. standalone_module means it a submodule that is not inlined in parent module, and will be quantized separately as one unit. How the standalone module is observed is specified by `input_quantized_idxs` and `output_quantized_idxs` in the prepare_custom_config for the standalone module Returns: * model(GraphModule): prepared standalone module. It has these attributes in model.meta: * `standalone_module_input_quantized_idxs(List[Int])`: a list of indexes for the graph input that is expected to be quantized, same as input_quantized_idxs configuration provided for the standalone module * `standalone_module_output_quantized_idxs(List[Int])`: a list of indexs for the graph output that is quantized same as input_quantized_idxs configuration provided for the standalone module T)rArH)r])rrDr?rErFrAs r"_prepare_standalone_module_fxr_s&>  %! r$c| t}t|tr1tjdt dtj |}tjjd|j}|Dcic]}t||r |t||}}tjj|}t|t!|d||}t#|||Scc}w)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.rKz$quantization_api.quantize_fx.fuse_fxF)r r&rMrNrOrPrQr3_C_log_api_usage_oncerRr.rSfxsymbolic_tracer0rCr#)rr@rArYr!rr[s r"fuse_fxrfs(!-/$d+  N   .778JK HH  !GH-BB)  5$  geT""O 88**51L%l3L%1C^TL#L/B s= C%c btjjdt||d||||S)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_fxFr3rbrcr])rrDrErFrGrAs r" prepare_fxris:V HH  !JK    r$cbtjjdt||d|||S)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("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)rArh)rrDrErFrAs r"prepare_qat_fxrks7~ HH  !NO   %  r$r[ is_referenceconvert_custom_config_remove_qconfig is_decomposedkeep_original_weightsc d| t}t|tr1tjdt dtj |}t||j} | D cic]} t|| r | t|| } } t||||||||| } t| | | Scc} w)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.rJrK)_remove_qconfig_flagrDrArorp) r r&rMrNrOrPrQr*rRr.rSr r#) r[rlrmrHrnrDrArorprYr!rr6s r" _convert_fxrss$ 3 5'.  Q   !4 = =>S T<(0EE)  < & glD))O ,'%#3 I$I? 's) B-c dtjjdt|d|||||S)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)rlrmrnrDrArpr3rbrcrs)r[rmrnrDrArps r" convert_fxrv-s:r HH  !JK 3''%3 r$cbtjjdt|d||||S)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)rlrmrnrDrAru)r[rmrnrDrAs r"convert_to_reference_fxrxrs7N HH  !WX 3''%  r$c dtjjdt|d|d||dS)aConvert a calibrated or trained model to a reference quantized model, with decomposed representation for quantized Tensor see https://github.com/pytorch/rfcs/blob/master/RFC-0019-Extending-PyTorch-Quantization-to-Custom-Backends.md for more details, reference quantized model is a standard representation of a quantized model provided by FX Graph Mode Quantization, it can be further lowered to run on the target hardware, like accelerators Note: this is not public API Args: * `graph_module` (GraphModule): A prepared and calibrated/trained model (GraphModule) * `convert_custom_config` (ConvertCustomConfig): custom configurations for convert function. See :func:`~torch.ao.quantization.quantize_fx.convert_fx` for more details. * `_remove_qconfig` (bool): Option to remove the qconfig attributes in the model after convert. * `qconfig_mapping` (QConfigMapping): config for specifying how to convert a model for quantization. See :func:`~torch.ao.quantization.quantize_fx.convert_fx` for more details. * `backend_config` (BackendConfig): A configuration for the backend which describes how operators should be quantized in the backend. See :func:`~torch.ao.quantization.quantize_fx.convert_fx` for more details. Return: A reference quantized model (GraphModule) with operators working with decomposed quantized Tensor Example:: # prepared_model: the model after prepare_fx/prepare_qat_fx and calibration/training # TODO: add backend_config after we split the backend_config for fbgemm and qnnpack # e.g. backend_config = get_default_backend_config("fbgemm") reference_quantized_model = _convert_to_reference_decomposed_fx(prepared_model) z@quantization_api.quantize_fx._convert_to_reference_decomposed_fxTF)rlrmrnrDrAroru)r[rmrDrAs r"#_convert_to_reference_decomposed_fxrzs>R HH  J 3'% r$c t|||dS)av[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)rH)rs)r[rlrms r"_convert_standalone_module_fxr|s !  r$)NN)NNNF)NNN)NFTNNFF)NTNNF)NTNN)FN)8rrNtypingrrrr3torch.fxrtorch.fx.graph_modulerrAr r fx.convertr fx.custom_configr r rfx.fuserfx.graph_moduler fx.preparer fx.tracerrrrfx.utilsrrrDrr5ModulerMr(r#r*r0r9boolrCtupler]r_rfrirkrsrvrxrzr|r$r"rs '' @FXX0EE, ( ehhoo- . (#s(^ (  ( %((// d  [ T  Iehhoo I$ I"IMAE   .S#XDE-c3h=>   ,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=>- -hOSLPAE T 88??T>4S>9:T#s(OT!!4d38nd!JK T #5c3h)G#HI T -c3h=> TTvOSAE g 88??g>4S>9:g#s(Og!!4d38nd!JK g -c3h=> g  gZOS!& CGAE"'---!!4d38nd!JK- -  - >4S>4?@ --c3h=>-- --dOS CGAE"' BB !4d38nd!JKBB>4S>4?@ B -c3h=> B  BBNOS CGAE // !4d38nd!JK//>4S>4?@ / -c3h=> /  /hOSCGAE 44 !4d38nd!JK4>4S>4?@4-c3h=> 4  4rNR!!4d38nd!JK r$