https://pytorch.org/ao/en/0.17/api_reference/api_ref_float8.htmlhttps://pytorch.org/ao/en/0.17/api_reference/api_ref_prototype_attention.htmlhttps://pytorch.org/ao/en/0.17/api_reference/api_ref_prototype_quant_logger.htmlhttps://pytorch.org/ao/en/0.17/api_reference/api_ref_qat.htmlhttps://pytorch.org/ao/en/0.17/api_reference/api_ref_quantization.htmlhttps://pytorch.org/ao/en/0.17/api_reference/api_ref_sparsity.htmlhttps://pytorch.org/ao/en/0.17/api_reference/api_ref_utils.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.core.config.AOBaseConfig.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.float8.CastConfig.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.float8.Float8GemmConfig.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.float8.Float8LinearConfig.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.float8.Float8LinearRecipeName.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.float8.ScalingGranularity.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.float8.ScalingType.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.float8.convert_to_float8_training.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.float8.precompute_float8_dynamic_scale_for_fsdp.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.prototype.attention.AttentionBackend.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.prototype.attention.apply_low_precision_attention.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.prototype.attention.fp8_fa3.attention.fp8_fa3_rope_sdpa.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.prototype.attention.fp8_fa3.attention.fp8_fa3_sdpa.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.prototype.mx_formats.MXDynamicActivationMXWeightConfig.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.prototype.mx_formats.NVFP4DynamicActivationNVFP4WeightConfig.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.prototype.mx_formats.NVFP4WeightOnlyConfig.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.prototype.quant_logger.add_activation_loggers.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.prototype.quant_logger.enable_log_stats_to_file.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.prototype.quant_logger.enable_log_tensor_save_tensors_to_disk.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.prototype.quant_logger.log_parameter_info.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.prototype.quant_logger.log_tensor.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.prototype.quant_logger.reset_counter.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.prototype.quantization.Int8DynamicActivationUIntxWeightConfig.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.prototype.quantization.UIntxWeightOnlyConfig.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.Float8DynamicActivationFloat8WeightConfig.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.Float8DynamicActivationInt4WeightConfig.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.Float8WeightOnlyConfig.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.FqnToConfig.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.Int4WeightOnlyConfig.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.Int8DynamicActivationInt8WeightConfig.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.Int8DynamicActivationIntxWeightConfig.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.Int8WeightOnlyConfig.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.IntxWeightOnlyConfig.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.qat.ComposableQATQuantizer.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.qat.FakeQuantizeConfigBase.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.qat.FakeQuantizedEmbedding.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.qat.FakeQuantizedLinear.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.qat.FakeQuantizerBase.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.qat.Float8ActInt4WeightQATQuantizer.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.qat.Float8FakeQuantizeConfig.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.qat.Float8FakeQuantizer.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.qat.FromIntXQuantizationAwareTrainingConfig.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.qat.Int4WeightOnlyEmbeddingQATQuantizer.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.qat.Int4WeightOnlyQATQuantizer.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.qat.Int8DynActInt4WeightQATQuantizer.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.qat.IntXQuantizationAwareTrainingConfig.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.qat.IntxFakeQuantizeConfig.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.qat.IntxFakeQuantizer.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.qat.QATConfig.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.qat.QATStep.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.qat.embedding.Int4WeightOnlyEmbedding.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.qat.embedding.Int4WeightOnlyQATEmbedding.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.qat.initialize_fake_quantizers.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.qat.linear.Int4WeightOnlyQATLinear.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.qat.linear.Int8DynActInt4WeightQATLinear.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.qat.linear.disable_linear_fake_quant.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.qat.linear.enable_linear_fake_quant.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.quantize_.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.quantize_.common.KernelPreference.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.quantize_.common.PackingFormat.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.quantize_.common.QuantizeTensorKwargs.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.quantization.quantize_.common._choose_quant_func_and_quantize_tensor.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.sparsity.PerChannelNormObserver.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.sparsity.WandaSparsifier.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.sparsity.apply_fake_sparsity.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.sparsity.semi_sparse_weight.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.sparsity.sparsify_.htmlhttps://pytorch.org/ao/en/0.17/api_reference/generated/torchao.utils.TorchAOBaseTensor.htmlhttps://pytorch.org/ao/en/0.17/api_reference/index.htmlhttps://pytorch.org/ao/en/0.17/contributing/benchmarking_api_guide.htmlhttps://pytorch.org/ao/en/0.17/contributing/contributor_guide.htmlhttps://pytorch.org/ao/en/0.17/contributing/index.htmlhttps://pytorch.org/ao/en/0.17/contributing/quantization_overview.htmlhttps://pytorch.org/ao/en/0.17/contributing/sparsity.htmlhttps://pytorch.org/ao/en/0.17/eager_tutorials/debugging_weights_and_activations.htmlhttps://pytorch.org/ao/en/0.17/eager_tutorials/finetuning.htmlhttps://pytorch.org/ao/en/0.17/eager_tutorials/first_quantization_example.htmlhttps://pytorch.org/ao/en/0.17/eager_tutorials/index.htmlhttps://pytorch.org/ao/en/0.17/eager_tutorials/mxfp8_expert_parallel_training.htmlhttps://pytorch.org/ao/en/0.17/eager_tutorials/pretraining.htmlhttps://pytorch.org/ao/en/0.17/eager_tutorials/serialization.htmlhttps://pytorch.org/ao/en/0.17/eager_tutorials/serving.htmlhttps://pytorch.org/ao/en/0.17/eager_tutorials/static_quantization.htmlhttps://pytorch.org/ao/en/0.17/eager_tutorials/subclass_advanced.htmlhttps://pytorch.org/ao/en/0.17/eager_tutorials/subclass_basic.htmlhttps://pytorch.org/ao/en/0.17/eager_tutorials/torchao_hf_integration.htmlhttps://pytorch.org/ao/en/0.17/eager_tutorials/torchao_vllm_integration.htmlhttps://pytorch.org/ao/en/0.17/index.htmlhttps://pytorch.org/ao/en/0.17/performant_kernels.htmlhttps://pytorch.org/ao/en/0.17/pt2e_quantization/index.htmlhttps://pytorch.org/ao/en/0.17/pt2e_quantization/pt2e_quant_openvino_inductor.htmlhttps://pytorch.org/ao/en/0.17/pt2e_quantization/pt2e_quant_ptq.htmlhttps://pytorch.org/ao/en/0.17/pt2e_quantization/pt2e_quant_qat.htmlhttps://pytorch.org/ao/en/0.17/pt2e_quantization/pt2e_quant_x86_inductor.htmlhttps://pytorch.org/ao/en/0.17/pt2e_quantization/pt2e_quant_xpu_inductor.htmlhttps://pytorch.org/ao/en/0.17/pt2e_quantization/pt2e_quantizer.htmlhttps://pytorch.org/ao/en/0.17/tutorials/index.htmlhttps://pytorch.org/ao/en/0.17/tutorials/sg_execution_times.htmlhttps://pytorch.org/ao/en/0.17/tutorials/template_tutorial.htmlhttps://pytorch.org/ao/en/0.17/workflows/index.htmlhttps://pytorch.org/ao/en/0.17/workflows/inference.htmlhttps://pytorch.org/ao/en/0.17/workflows/qat.htmlhttps://pytorch.org/ao/en/0.17/workflows/training.htmlhttps://pytorch.org/ao/en/0.17/genindex.htmlhttps://pytorch.org/ao/en/0.17/py-modindex.htmlhttps://pytorch.org/ao/en/0.17/_modules/torchao/core/config.htmlhttps://pytorch.org/ao/en/0.17/_modules/torchao/float8/config.htmlhttps://pytorch.org/ao/en/0.17/_modules/torchao/float8/float8_linear_utils.htmlhttps://pytorch.org/ao/en/0.17/_modules/torchao/float8/fsdp_utils.htmlhttps://pytorch.org/ao/en/0.17/_modules/torchao/prototype/attention/api.htmlhttps://pytorch.org/ao/en/0.17/_modules/torchao/prototype/mx_formats/inference_workflow.htmlhttps://pytorch.org/ao/en/0.17/_modules/torchao/prototype/quant_logger/quant_logger.htmlhttps://pytorch.org/ao/en/0.17/_modules/torchao/prototype/quantization/quant_api.htmlhttps://pytorch.org/ao/en/0.17/_modules/torchao/quantization/qat/api.htmlhttps://pytorch.org/ao/en/0.17/_modules/torchao/quantization/qat/embedding.htmlhttps://pytorch.org/ao/en/0.17/_modules/torchao/quantization/qat/fake_quantize_config.htmlhttps://pytorch.org/ao/en/0.17/_modules/torchao/quantization/qat/fake_quantizer.htmlhttps://pytorch.org/ao/en/0.17/_modules/torchao/quantization/qat/linear.htmlhttps://pytorch.org/ao/en/0.17/_modules/torchao/quantization/quant_api.htmlhttps://pytorch.org/ao/en/0.17/_modules/torchao/quantization/quantize_/common/kernel_preference.htmlhttps://pytorch.org/ao/en/0.17/_modules/torchao/quantization/quantize_/common/packing_format.htmlhttps://pytorch.org/ao/en/0.17/_modules/torchao/quantization/quantize_/common/quantize_tensor_kwargs.htmlhttps://pytorch.org/ao/en/0.17/_modules/torchao/sparsity/sparse_api.htmlhttps://pytorch.org/ao/en/0.17/_modules/torchao/sparsity/utils.htmlhttps://pytorch.org/ao/en/0.17/_modules/torchao/sparsity/wanda.htmlhttps://pytorch.org/ao/en/0.17/_modules/torchao/utils.htmlhttps://pytorch.org/ao/en/0.17/_modules/index.htmlhttps://pytorch.org/ao/en/0.17/search.html