check_model_arch()
prepare_model()
QuantAnalyzer
QuantAnalyzer.enable_per_layer_mse_loss()
QuantAnalyzer.analyze()
CallbackFunc
QuantAnalyzer.check_model_sensitivity_to_quantization()
QuantAnalyzer.perform_per_layer_analysis_by_enabling_quant_wrappers()
QuantAnalyzer.perform_per_layer_analysis_by_disabling_quant_wrappers()
QuantAnalyzer.export_per_layer_encoding_min_max_range()
QuantAnalyzer.export_per_layer_stats_histogram()
QuantAnalyzer.export_per_layer_mse_loss()
QuantizationSimModel
QuantizationSimModel.compute_encodings()
QuantizationSimModel.export()
quantsim.save_checkpoint()
quantsim.load_checkpoint()
QuantScheme
QuantScheme.post_training_percentile
QuantScheme.post_training_tf
QuantScheme.post_training_tf_enhanced
QuantScheme.training_range_learning_with_tf_enhanced_init
QuantScheme.training_range_learning_with_tf_init
apply_adaround()
AdaroundParameters
equalize_model()
ClsSetInfo
ClsSetInfo.ClsSetLayerPairInfo
fold_all_batch_norms()
scale_model()
bias_fold()
fold_given_batch_norms()
scale_cls_sets()
correct_bias()
ConvBnInfoType
ActivationType
ActivationType.no_activation
ActivationType.relu
ActivationType.relu6
QuantParams
AutoQuant
reestimate_bn_stats()
fold_all_batch_norms_to_scale()
AdapterMetaData
peft.replace_lora_layers_with_quantizable_layers()
peft.track_lora_meta_data()
PeftQuantUtils
PeftQuantUtils.disable_lora_adapters()
PeftQuantUtils.enable_adapter_and_load_weights()
PeftQuantUtils.export_adapter_weights()
PeftQuantUtils.freeze_base_model()
PeftQuantUtils.freeze_base_model_activation_quantizers()
PeftQuantUtils.freeze_base_model_param_quantizers()
PeftQuantUtils.get_quantized_lora_layer()
PeftQuantUtils.set_bitwidth_for_lora_adapters()
update_keras_bn_ops_trainable_flag()
ModelCompressor
ModelCompressor.compress_model()
GreedySelectionParameters
TarRankSelectionParameters
SpatialSvdParameters
SpatialSvdParameters.AutoModeParams
SpatialSvdParameters.ManualModeParams
SpatialSvdParameters.Mode
SpatialSvdParameters.Mode.auto
SpatialSvdParameters.Mode.manual
WeightSvdParameters
WeightSvdParameters.AutoModeParams
WeightSvdParameters.ManualModeParams
WeightSvdParameters.Mode
WeightSvdParameters.Mode.auto
WeightSvdParameters.Mode.manual
ChannelPruningParameters
ChannelPruningParameters.AutoModeParams
ChannelPruningParameters.ManualModeParams
ChannelPruningParameters.Mode
ChannelPruningParameters.Mode.auto
ChannelPruningParameters.Mode.manual
ModuleCompRatioPair
VisualizeCompression
VisualizeCompression.display_eval_scores()
VisualizeCompression.display_comp_ratio_plot()
visualize_relative_weight_ranges_to_identify_problematic_layers()
visualize_weight_ranges()
visualize_changes_after_optimization()
LayerOutputUtil
LayerOutputUtil.generate_layer_outputs()
NamingScheme
NamingScheme.ONNX
NamingScheme.PYTORCH
NamingScheme.TORCHSCRIPT
CostMetric
CostMetric.mac
CostMetric.memory
CompressionScheme
CompressionScheme.channel_pruning
CompressionScheme.spatial_svd
CompressionScheme.weight_svd
Svd
Svd.compress_net()
visualize_weight_ranges_single_layer()
visualize_relative_weight_ranges_single_layer()
save_tf_session_single_gpu()
load_tf_sess_variables_to_keras_single_gpu()
save_as_tf_module_multi_gpu()
load_keras_model_multi_gpu()
Quantize
Applies quantization to the input.
QuantizeDequantize
Applies fake-quantization by quantizing and dequantizing the input.
quantize
quantize_dequantize
dequantize