diff --git a/releases/1.35.0/Examples/tensorflow/quantization/keras/quantsim_cle.ipynb b/releases/1.35.0/Examples/tensorflow/quantization/keras/quantsim_cle.ipynb index b80b1ff..32473cf 100644 --- a/releases/1.35.0/Examples/tensorflow/quantization/keras/quantsim_cle.ipynb +++ b/releases/1.35.0/Examples/tensorflow/quantization/keras/quantsim_cle.ipynb @@ -277,7 +277,7 @@ { "cell_type": "code", "execution_count": null, - "id": "74bdecfa", + "id": "477ebc2b", "metadata": { "collapsed": false }, @@ -349,7 +349,7 @@ { "cell_type": "code", "execution_count": null, - "id": "f7c1c367", + "id": "4c5e87f1", "metadata": { "collapsed": false }, @@ -406,7 +406,7 @@ { "cell_type": "code", "execution_count": null, - "id": "cb823b99", + "id": "9f50bc3e", "metadata": { "collapsed": false }, diff --git a/releases/1.35.0/api_docs/onnx.html b/releases/1.35.0/api_docs/onnx.html index 76a529d..91709e4 100644 --- a/releases/1.35.0/api_docs/onnx.html +++ b/releases/1.35.0/api_docs/onnx.html @@ -243,15 +243,9 @@
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()
QuantScheme
QuantScheme.post_training_percentile
QuantScheme
QuantScheme.post_training_percentile
ClsSetInfo
QuantParams
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_fp_lora_layer()
PeftQuantUtils.get_quantized_lora_layer()
PeftQuantUtils.quantize_lora_scale_with_fixed_range()
PeftQuantUtils.set_bitwidth_for_lora_adapters()
QuantizerBase
-QuantizeDequantize
-Quantize
-QuantizationMixin
QuantizationMixin.input_quantizers
QuantizationMixin.output_quantizers
QuantizationMixin.param_quantizers
QuantizationMixin.forward()
QuantizationMixin.__quant_init__()
QuantizationMixin.set_kernel()
QuantizationMixin.set_default_kernel()
QuantizationMixin.compute_encodings()
QuantizationMixin.from_module()
QuantizationMixin.get_default_kernel()
QuantizationMixin.get_kernel()
QuantizationMixin.implements()
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()
QuantScheme
QuantScheme.post_training_percentile
QuantScheme
QuantScheme.post_training_percentile
ClsSetInfo
QuantParams
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_fp_lora_layer()
PeftQuantUtils.get_quantized_lora_layer()
PeftQuantUtils.quantize_lora_scale_with_fixed_range()
PeftQuantUtils.set_bitwidth_for_lora_adapters()
QuantizerBase
-QuantizeDequantize
-Quantize
-QuantizationMixin
QuantizationMixin.input_quantizers
QuantizationMixin.output_quantizers
QuantizationMixin.param_quantizers
QuantizationMixin.forward()
QuantizationMixin.__quant_init__()
QuantizationMixin.set_kernel()
QuantizationMixin.set_default_kernel()
QuantizationMixin.compute_encodings()
QuantizationMixin.from_module()
QuantizationMixin.get_default_kernel()
QuantizationMixin.get_kernel()
QuantizationMixin.implements()
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()
QuantScheme
QuantScheme.post_training_percentile
QuantScheme
QuantScheme.post_training_percentile
ClsSetInfo
QuantParams
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_fp_lora_layer()
PeftQuantUtils.get_quantized_lora_layer()
PeftQuantUtils.quantize_lora_scale_with_fixed_range()
PeftQuantUtils.set_bitwidth_for_lora_adapters()
QuantizerBase
-QuantizeDequantize
-Quantize
-QuantizationMixin
QuantizationMixin.input_quantizers
QuantizationMixin.output_quantizers
QuantizationMixin.param_quantizers
QuantizationMixin.forward()
QuantizationMixin.__quant_init__()
QuantizationMixin.set_kernel()
QuantizationMixin.set_default_kernel()
QuantizationMixin.compute_encodings()
QuantizationMixin.from_module()
QuantizationMixin.get_default_kernel()
QuantizationMixin.get_kernel()
QuantizationMixin.implements()
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()
QuantScheme
QuantScheme.post_training_percentile
QuantScheme
QuantScheme.post_training_percentile
ClsSetInfo
QuantParams
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_fp_lora_layer()
PeftQuantUtils.get_quantized_lora_layer()
PeftQuantUtils.quantize_lora_scale_with_fixed_range()
PeftQuantUtils.set_bitwidth_for_lora_adapters()
QuantizerBase
-QuantizeDequantize
-Quantize
-QuantizationMixin
QuantizationMixin.input_quantizers
QuantizationMixin.output_quantizers
QuantizationMixin.param_quantizers
QuantizationMixin.forward()
QuantizationMixin.__quant_init__()
QuantizationMixin.set_kernel()
QuantizationMixin.set_default_kernel()
QuantizationMixin.compute_encodings()
QuantizationMixin.from_module()
QuantizationMixin.get_default_kernel()
QuantizationMixin.get_kernel()
QuantizationMixin.implements()
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()
QuantScheme
QuantScheme.post_training_percentile
QuantScheme
QuantScheme.post_training_percentile
ClsSetInfo
QuantParams
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_fp_lora_layer()
PeftQuantUtils.get_quantized_lora_layer()
PeftQuantUtils.quantize_lora_scale_with_fixed_range()
PeftQuantUtils.set_bitwidth_for_lora_adapters()
QuantizerBase
-QuantizeDequantize
-Quantize
-QuantizationMixin
QuantizationMixin.input_quantizers
QuantizationMixin.output_quantizers
QuantizationMixin.param_quantizers
QuantizationMixin.forward()
QuantizationMixin.__quant_init__()
QuantizationMixin.set_kernel()
QuantizationMixin.set_default_kernel()
QuantizationMixin.compute_encodings()
QuantizationMixin.from_module()
QuantizationMixin.get_default_kernel()
QuantizationMixin.get_kernel()
QuantizationMixin.implements()
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()
QuantScheme
QuantScheme.post_training_percentile
QuantScheme
QuantScheme.post_training_percentile
ClsSetInfo
QuantParams
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_fp_lora_layer()
PeftQuantUtils.get_quantized_lora_layer()
PeftQuantUtils.quantize_lora_scale_with_fixed_range()
PeftQuantUtils.set_bitwidth_for_lora_adapters()
QuantizerBase
-QuantizeDequantize
-Quantize
-QuantizationMixin
QuantizationMixin.input_quantizers
QuantizationMixin.output_quantizers
QuantizationMixin.param_quantizers
QuantizationMixin.forward()
QuantizationMixin.__quant_init__()
QuantizationMixin.set_kernel()
QuantizationMixin.set_default_kernel()
QuantizationMixin.compute_encodings()
QuantizationMixin.from_module()
QuantizationMixin.get_default_kernel()
QuantizationMixin.get_kernel()
QuantizationMixin.implements()
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()
QuantScheme
QuantScheme.post_training_percentile
QuantScheme
QuantScheme.post_training_percentile
ClsSetInfo
QuantParams
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_fp_lora_layer()
PeftQuantUtils.get_quantized_lora_layer()
PeftQuantUtils.quantize_lora_scale_with_fixed_range()
PeftQuantUtils.set_bitwidth_for_lora_adapters()
QuantizerBase
-QuantizeDequantize
-Quantize
-QuantizationMixin
QuantizationMixin.input_quantizers
QuantizationMixin.output_quantizers
QuantizationMixin.param_quantizers
QuantizationMixin.forward()
QuantizationMixin.__quant_init__()
QuantizationMixin.set_kernel()
QuantizationMixin.set_default_kernel()
QuantizationMixin.compute_encodings()
QuantizationMixin.from_module()
QuantizationMixin.get_default_kernel()
QuantizationMixin.get_kernel()
QuantizationMixin.implements()
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()
QuantScheme
QuantScheme.post_training_percentile
QuantScheme
QuantScheme.post_training_percentile
ClsSetInfo
QuantParams
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_fp_lora_layer()
PeftQuantUtils.get_quantized_lora_layer()
PeftQuantUtils.quantize_lora_scale_with_fixed_range()
PeftQuantUtils.set_bitwidth_for_lora_adapters()
QuantizerBase
-QuantizeDequantize
-Quantize
-QuantizationMixin
QuantizationMixin.input_quantizers
QuantizationMixin.output_quantizers
QuantizationMixin.param_quantizers
QuantizationMixin.forward()
QuantizationMixin.__quant_init__()
QuantizationMixin.set_kernel()
QuantizationMixin.set_default_kernel()
QuantizationMixin.compute_encodings()
QuantizationMixin.from_module()
QuantizationMixin.get_default_kernel()
QuantizationMixin.get_kernel()
QuantizationMixin.implements()
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()
QuantScheme
QuantScheme.post_training_percentile
QuantScheme
QuantScheme.post_training_percentile
ClsSetInfo
QuantParams
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_fp_lora_layer()
PeftQuantUtils.get_quantized_lora_layer()
PeftQuantUtils.quantize_lora_scale_with_fixed_range()
PeftQuantUtils.set_bitwidth_for_lora_adapters()
QuantizerBase
-QuantizeDequantize
-Quantize
-QuantizationMixin
QuantizationMixin.input_quantizers
QuantizationMixin.output_quantizers
QuantizationMixin.param_quantizers
QuantizationMixin.forward()
QuantizationMixin.__quant_init__()
QuantizationMixin.set_kernel()
QuantizationMixin.set_default_kernel()
QuantizationMixin.compute_encodings()
QuantizationMixin.from_module()
QuantizationMixin.get_default_kernel()
QuantizationMixin.get_kernel()
QuantizationMixin.implements()
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()
QuantScheme
QuantScheme.post_training_percentile
QuantScheme
QuantScheme.post_training_percentile
ClsSetInfo
QuantParams
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_fp_lora_layer()
PeftQuantUtils.get_quantized_lora_layer()
PeftQuantUtils.quantize_lora_scale_with_fixed_range()
PeftQuantUtils.set_bitwidth_for_lora_adapters()
QuantizerBase
-QuantizeDequantize
-Quantize
-QuantizationMixin
QuantizationMixin.input_quantizers
QuantizationMixin.output_quantizers
QuantizationMixin.param_quantizers
QuantizationMixin.forward()
QuantizationMixin.__quant_init__()
QuantizationMixin.set_kernel()
QuantizationMixin.set_default_kernel()
QuantizationMixin.compute_encodings()
QuantizationMixin.from_module()
QuantizationMixin.get_default_kernel()
QuantizationMixin.get_kernel()
QuantizationMixin.implements()
The following api can be used to create a sparse tensor given indices and features in dense form
-Custom SparsetensorWrapper class for SparseConvTensor
-Initialize internal Module state, shared by both nn.Module and ScriptModule.
-The following api can be used to create a dense tensor given a sparse tensor
- -