Index

A

accuracy() (in module util.misc) Add (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) add() (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.Bincount method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.CombinedStat method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.Covariance method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.CrossCovariance method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.CrossIoU method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.History method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.IoU method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.Mean method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.NormMean method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.Quantile method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.SecondMoment method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.Stat method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.TopK method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.Variance method) add_config_item() (intel_extension_for_transformers.transformers.runtime.compile.graph.graph.Graph method) add_gene() (intel_extension_for_transformers.transformers.dynamic.evolution.Evolution method) AddClsToken (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.add_cls_token) AddEmbeddings (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.add_embeddings) AddV2 (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) align_columns() (in module util.postprocess) align_headers() (in module util.postprocess) align_img() (in module intel_extension_for_transformers.neural_chat.pipeline.plugins.video.face_animation.src.face3d.util.preprocess)

align_rows() (in module util.postprocess) align_supercells() (in module util.postprocess) All (class in intel_extension_for_transformers.transformers.runtime.compile.ops.all) all_gather() (in module util.misc) ApiErrorCode (class in intel_extension_for_transformers.neural_chat.server.restful.openai_protocol) append_message() (conversation.Conversation method) apply_class_thresholds() (in module util.postprocess) apply_rotary_pos_emb() (in module intel_extension_for_transformers.transformers.kv_cache_compression.models.modeling_llama) apply_threshold() (in module util.postprocess) approx_ratio() (in module intel_extension_for_transformers.transformers.dynamic.evolution) Arange (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) ArangewithReciprocal (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.arangewithreciprocal) Assert (class in intel_extension_for_transformers.transformers.runtime.compile.ops.assert) AttentionBlock_AttentionMaskAddReshape (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.attentionBlock_AttentionMaskAddReshape) AttentionBlock_ConstantOfShapeWithMul (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.attentionBlock_ConstantOfShapeWithMul) AttentionBlock_QKVPreReshape (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.attentionBlock_QKVPreReshape) AttentionBlock_QKVReshape (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.attentionBlock_QKVReshape) AttentionBlock_WeightReshapeTo4D (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.attentionBlock_WeightReshapeTo4D) AttentionMaskLengthAdaptiveExpandIndices (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.attention_mask_length_adaptive_keep_indices) AttentionOutputLayerNormLengthAdaptiveExpandIndices (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.attention_output_layer_norm_length_adaptive_keep_indices) AttentionReshape (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.attention_reshape) AudioLanguageOptions (class in intel_extension_for_transformers.neural_chat.config) autocast_init() (in module intel_extension_for_transformers.transformers.runtime.compile.graph_utils) AutoRoundConfig (class in intel_extension_for_transformers.transformers.utils.config) AwqConfig (class in intel_extension_for_transformers.transformers.utils.config)

B

Backbone (class in models.backbone) BackendOptions (class in intel_extension_for_transformers.neural_chat.config) Baddbmm (class in intel_extension_for_transformers.transformers.runtime.compile.ops.baddbmm) BaseTrainer (class in intel_extension_for_transformers.transformers.trainer) BatchMatMul (class in intel_extension_for_transformers.transformers.runtime.compile.ops.batch_matmul) BatchMatMulV2 (class in intel_extension_for_transformers.transformers.runtime.compile.ops.batch_matmul_v2) benchmark() (in module intel_extension_for_transformers.transformers.benchmark) (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) BenchmarkConfig (class in intel_extension_for_transformers.transformers.config) BertAttention (class in intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic) BertEmbeddings (class in intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic) BertEncoder (class in intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic) BertForMaskedLM (class in intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic) BertForMultipleChoice (class in intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic) BertForNextSentencePrediction (class in intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic) BertForPreTraining (class in intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic) BertForPreTrainingOutput (class in intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic) BertForQuestionAnswering (class in intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic) BertForSequenceClassification (class in intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic) BertForTokenClassification (class in intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic) BertIntermediate (class in intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic)

BertLayer (class in intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic) BertLMHeadModel (class in intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic) BertLMPredictionHead (class in intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic) BertModel (class in intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic) BertOnlyMLMHead (class in intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic) BertOnlyNSPHead (class in intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic) BertOutput (class in intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic) BertPooler (class in intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic) BertPredictionHeadTransform (class in intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic) BertPreTrainedModel (class in intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic) BertPreTrainingHeads (class in intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic) BertSelfAttention (class in intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic) BertSelfOutput (class in intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic) bias_to_int32() (in module intel_extension_for_transformers.transformers.runtime.compile.onnx_utils) BiasAdd (class in intel_extension_for_transformers.transformers.runtime.compile.ops.bias_add) BinaryAdd (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) Bincount (class in intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats) box_numpy_null() (in module intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats) build_chatbot() (in module intel_extension_for_transformers.neural_chat.chatbot) builtin_eval_func() (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) (intel_extension_for_transformers.transformers.trainer.NLPSeq2SeqTrainer method) builtin_train_func() (intel_extension_for_transformers.transformers.trainer.BaseTrainer method)

C

cache_load_enabled (class in intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats) calculate_ins_level_acc() (in module utils.eval_utils) Cast (class in intel_extension_for_transformers.transformers.runtime.compile.ops.cast) CastTo (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.cast_to) change_node_input_tensors() (intel_extension_for_transformers.transformers.runtime.compile.graph.graph.Graph method) change_node_output_tensors() (intel_extension_for_transformers.transformers.runtime.compile.graph.graph.Graph method) change_num_name() (in module intel_extension_for_transformers.transformers.runtime.compile.onnx_utils) check_is_number() (in module utils.eval_utils) check_value() (in module intel_extension_for_transformers.transformers.config) ChildParentRetriever (class in intel_extension_for_transformers.langchain.langchain_community.retrievers.child_parent_retriever) class_subset() (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.FixedRandomSubsetSampler method) CollectQuantInfo (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.collect_quant_info) CombinedStat (class in intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats) compile() (in module intel_extension_for_transformers.transformers.runtime.compile.compile) compute_loss() (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) Concat (class in intel_extension_for_transformers.transformers.runtime.compile.ops.concat) config_file_path (intel_extension_for_transformers.transformers.pruner.pruning.Pruning attribute) configure_logging() (in module intel_extension_for_transformers.neural_chat.config_logging) Constant (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) ConstantOfShape (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) construct() (intel_extension_for_transformers.transformers.runtime.compile.ops.op.Operator method)

construct_node() (in module intel_extension_for_transformers.transformers.runtime.compile.graph_utils) Conv (class in intel_extension_for_transformers.transformers.runtime.compile.ops.conv) conversation module Conversation (class in conversation) convert_fullwidth_to_halfwidth() (in module intel_extension_for_transformers.neural_chat.pipeline.plugins.security.safety_checker) convert_image_to_base64() (conversation.Conversation method) convex_hull() (intel_extension_for_transformers.transformers.dynamic.evolution.Evolution method) Convolution (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) ConvReshape (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.conv_reshape) Cos (class in intel_extension_for_transformers.transformers.runtime.compile.ops.cos) Covariance (class in intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats) cpu_() (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.Stat method) CPU_INSTANCE (C macro) create_position_ids_from_input_ids() (in module intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic) create_position_ids_from_inputs_embeds() (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaEmbeddings method) create_tf_node() (in module intel_extension_for_transformers.transformers.runtime.compile.tf_utils) CrossCovariance (class in intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats) CrossIoU (class in intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats) crossover() (intel_extension_for_transformers.transformers.dynamic.evolution.Evolution method) cuda_() (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.Stat method) CumSum (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops)

D

DataArguments (class in intel_extension_for_transformers.neural_chat.config) debug() (in module intel_extension_for_transformers.transformers.runtime.compile.logger) DecoderAttnReshape (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.decoder_attn_reshape) del_environ_var() (in module intel_extension_for_transformers.transformers.runtime.compile.graph_utils) del_environ_vars() (in module intel_extension_for_transformers.transformers.runtime.compile.graph_utils) Dequantize (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) DequantizeLinear (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) dereference() (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.FixedSubsetSampler method) DETR (class in models.detr)

DETRMulti (class in models.detr_multi) DeviceOptions (class in intel_extension_for_transformers.neural_chat.config) dice_loss() (in module models.segmentation) distill() (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) distributed_init() (in module intel_extension_for_transformers.transformers.utils.utility) draw_landmarks() (in module intel_extension_for_transformers.neural_chat.pipeline.plugins.video.face_animation.src.face3d.util.util) dump_tensor() (intel_extension_for_transformers.transformers.runtime.compile.graph.graph.Graph method) DynamicLengthConfig (class in intel_extension_for_transformers.transformers.config) DynamicQuantConfig (class in intel_extension_for_transformers.transformers.utils.config)

E

Einsum (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) EinsumwithArange (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.einsumwitharange) EmbeddingBag (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.embeddingbag) EmbeddingsTo2DBeforeInnerProduct (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.embeddings_to_2d_before_inner_product) enable_sequential_cpu_offload() (intel_extension_for_transformers.neural_chat.pipeline.plugins.image2image.instructpix2pix_pipeline.StableDiffusionInstructPix2PixPipeline method) engine_init() (intel_extension_for_transformers.transformers.runtime.compile.graph.graph.Graph method) environ_info_init() (in module intel_extension_for_transformers.transformers.runtime.compile.graph_utils) Erf (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) error() (in module intel_extension_for_transformers.transformers.runtime.compile.logger) eval_multi_choice() (in module utils.eval_utils) eval_open() (in module utils.eval_utils) evaluate() (in module utils.eval_utils) Evolution (class in intel_extension_for_transformers.transformers.dynamic.evolution) Expand (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) expand_gather() (in module intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic) (in module intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic)

ExpandDims (class in intel_extension_for_transformers.transformers.runtime.compile.ops.expand_dims) ExpandIndices (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) ExplicitNHWCTransposeForConv (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.stableDiffusion_ExplicitNHWCTranspose) ExplicitNHWCTransposeForConvQAT (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.stableDiffusion_ExplicitNHWCTransposeQAT) export_to_bf16_onnx() (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) export_to_fp32_onnx() (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) export_to_int8_onnx() (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) export_to_jit() (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) export_to_onnx() (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) extract() (intel_extension_for_transformers.transformers.runtime.compile.ops.onnx_input.ONNXINPUT method) (intel_extension_for_transformers.transformers.runtime.compile.ops.op.Operator method) extract_numbers() (in module utils.eval_utils) extract_text_from_spans() (in module util.postprocess) extract_text_inside_bbox() (in module util.postprocess) Extractor (class in intel_extension_for_transformers.transformers.runtime.compile.extractors.extractor)

F

fatal() (in module intel_extension_for_transformers.transformers.runtime.compile.logger) feed_forward_chunk() (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertLayer method) (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaLayer method) Fill (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) finetune_model() (in module intel_extension_for_transformers.neural_chat.chatbot) FinetuningArguments (class in intel_extension_for_transformers.neural_chat.config) FixedRandomSubsetSampler (class in intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats) FixedSubsetSampler (class in intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats) FlatMapDataset (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) Flatten (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) Floor_divide (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) forward() (intel_extension_for_transformers.transformers.modeling.gpt_bigcode.modeling_gpt_bigcode.GPTBigCodeForCausalLM method) (intel_extension_for_transformers.transformers.modeling.gpt_bigcode.modeling_gpt_bigcode.GPTBigCodeForSequenceClassification method) (intel_extension_for_transformers.transformers.modeling.gpt_bigcode.modeling_gpt_bigcode.GPTBigCodeForTokenClassification method) (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertAttention method) (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertEmbeddings method) (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertEncoder method) (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertForMaskedLM method) (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertForMultipleChoice method) (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertForNextSentencePrediction method) (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertForPreTraining method) (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertForQuestionAnswering method) (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertForSequenceClassification method) (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertForTokenClassification method) (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertIntermediate method) (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertLayer method) (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertLMHeadModel method) (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertLMPredictionHead method) (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertModel method) (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertOnlyMLMHead method) (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertOnlyNSPHead method) (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertOutput method) (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertPooler method) (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertPredictionHeadTransform method) (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertPreTrainingHeads method) (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertSelfAttention method) (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertSelfOutput method) (intel_extension_for_transformers.transformers.modeling.modeling_gaudi.models.bart.modeling_bart.gaudi_BartLearnedPositionalEmbedding method) (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaAttention method) (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaClassificationHead method) (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaEmbeddings method) (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaEncoder method) (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaForCausalLM method) (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaForMaskedLM method) (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaForMultipleChoice method) (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaForQuestionAnswering method) (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaForSequenceClassification method) (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaForTokenClassification method) (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaIntermediate method) (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaLayer method) (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaLMHead method) (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaModel method) (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaOutput method) (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaPooler method) (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaSelfAttention method) (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaSelfOutput method) (models.detr.DETR method) (models.detr.PostProcess method) (models.detr.SetCriterion method) (models.detr_multi.DETRMulti method) (models.detr_multi.PostProcess method) (models.detr_multi.SetCriterion method) (models.matcher.HungarianMatcher method) (models.segmentation.PostProcessPanoptic method)

from_pretrained() (intel_extension_for_transformers.transformers.modeling.model.OptimizedModel class method) FrozenBatchNorm2d (class in models.backbone) FusedBatchNormV3 (class in intel_extension_for_transformers.transformers.runtime.compile.ops.fused_batch_norm_v3) FusedGemm (class in intel_extension_for_transformers.transformers.runtime.compile.ops.fused_gemm) FusedMatMul (class in intel_extension_for_transformers.transformers.runtime.compile.ops.fused_matmul)

G

Gather (class in intel_extension_for_transformers.transformers.runtime.compile.ops.gather) GatherElements (class in intel_extension_for_transformers.transformers.runtime.compile.ops.gather_elements) GatherV2 (class in intel_extension_for_transformers.transformers.runtime.compile.ops.gather) gaudi_BartAttention_forward() (in module intel_extension_for_transformers.transformers.modeling.modeling_gaudi.models.bart.modeling_bart) gaudi_BartLearnedPositionalEmbedding (class in intel_extension_for_transformers.transformers.modeling.modeling_gaudi.models.bart.modeling_bart) gaudi_mistral_repeat_kv() (in module intel_extension_for_transformers.transformers.modeling.modeling_gaudi.models.mistral.modeling_mistral) gaudi_mistral_rmsnorm_forward() (in module intel_extension_for_transformers.transformers.modeling.modeling_gaudi.models.mistral.modeling_mistral) gaudi_mixtral_attention_forward() (in module intel_extension_for_transformers.transformers.modeling.modeling_gaudi.models.mixtral.modeling_mixtral) gaudi_mixtral_block_sparse_moe_forward() (in module intel_extension_for_transformers.transformers.modeling.modeling_gaudi.models.mixtral.modeling_mixtral) gaudi_mixtral_decoder_layer_forward() (in module intel_extension_for_transformers.transformers.modeling.modeling_gaudi.models.mixtral.modeling_mixtral) gaudi_mixtral_model_forward() (in module intel_extension_for_transformers.transformers.modeling.modeling_gaudi.models.mixtral.modeling_mixtral) gaudi_mixtral_repeat_kv() (in module intel_extension_for_transformers.transformers.modeling.modeling_gaudi.models.mixtral.modeling_mixtral) gaudi_mixtral_rmsnorm_forward() (in module intel_extension_for_transformers.transformers.modeling.modeling_gaudi.models.mixtral.modeling_mixtral) gaudi_phi_attention_forward() (in module intel_extension_for_transformers.transformers.modeling.modeling_gaudi.models.phi.modeling_phi) gaudi_phi_decoder_layer_forward() (in module intel_extension_for_transformers.transformers.modeling.modeling_gaudi.models.phi.modeling_phi) gaudi_phi_model_forward() (in module intel_extension_for_transformers.transformers.modeling.modeling_gaudi.models.phi.modeling_phi) gaudi_spawn module gaudi_swin_get_attn_mask() (in module intel_extension_for_transformers.transformers.modeling.modeling_gaudi.models.swin.modeling_swin) GaudiMixtralForCausalLM (class in intel_extension_for_transformers.transformers.modeling.modeling_gaudi.models.mixtral.modeling_mixtral) Gelu (class in intel_extension_for_transformers.transformers.runtime.compile.ops.gelu) (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.gelu) Gemm (class in intel_extension_for_transformers.transformers.runtime.compile.ops.gemm) generalized_box_iou() (in module util.box_ops) generate() (intel_extension_for_transformers.transformers.runtime.compile.graph.graph.Graph method) GenerateSequence (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.generate_sequence) get_autocast_info() (in module intel_extension_for_transformers.transformers.runtime.compile.graph_utils) get_bbox_span_subset() (in module util.postprocess) get_children() (in module intel_extension_for_transformers.transformers.runtime.compile.onnx_utils) get_conv_template() (in module conversation) get_data_dtype() (in module intel_extension_for_transformers.transformers.runtime.compile.graph_utils) get_environ_info() (in module intel_extension_for_transformers.transformers.runtime.compile.graph_utils) get_example_inputs() (in module intel_extension_for_transformers.transformers.benchmark) get_export_args() (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) get_initializer_children_names() (in module intel_extension_for_transformers.transformers.runtime.compile.onnx_utils) get_input_embeddings() (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertModel method) (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaModel method)

get_logger() (intel_extension_for_transformers.transformers.runtime.compile.logger.Logger method) get_model_fwk_name() (in module intel_extension_for_transformers.transformers.runtime.compile.graph_utils) get_module() (in module intel_extension_for_transformers.neural_chat.tools.rome.utils.nethook) get_multi_choice_info() (in module utils.data_utils) get_next_node_names() (intel_extension_for_transformers.transformers.runtime.compile.graph.graph.Graph method) get_node_by_name() (intel_extension_for_transformers.transformers.runtime.compile.graph.graph.Graph method) get_node_children_names() (in module intel_extension_for_transformers.transformers.runtime.compile.onnx_utils) get_node_id() (intel_extension_for_transformers.transformers.runtime.compile.graph.graph.Graph method) get_output_embeddings() (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertForMaskedLM method) (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertForPreTraining method) (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertLMHeadModel method) (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaForCausalLM method) (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaForMaskedLM method) get_parameter() (in module intel_extension_for_transformers.neural_chat.tools.rome.utils.nethook) get_pre_node_names() (intel_extension_for_transformers.transformers.runtime.compile.graph.graph.Graph method) get_prompt() (conversation.Conversation method) get_quant_info() (in module intel_extension_for_transformers.transformers.runtime.compile.graph_utils) get_reprs_at_idxs() (in module intel_extension_for_transformers.neural_chat.tools.rome.repr_tools) get_reprs_at_word_tokens() (in module intel_extension_for_transformers.neural_chat.tools.rome.repr_tools) get_sparse_nodes_name() (intel_extension_for_transformers.transformers.runtime.compile.graph.graph.Graph method) get_sparsity_ratio() (intel_extension_for_transformers.transformers.pruner.pruning.Pruning method) get_store() (intel_extension_for_transformers.transformers.dynamic.evolution.Evolution method) get_tensor_dest_op() (in module intel_extension_for_transformers.transformers.runtime.compile.tf_utils) get_tensor_idx() (intel_extension_for_transformers.transformers.runtime.compile.graph.graph.Graph method) get_words_idxs_in_templates() (in module intel_extension_for_transformers.neural_chat.tools.rome.repr_tools) GPTBigCodeForCausalLM (class in intel_extension_for_transformers.transformers.modeling.gpt_bigcode.modeling_gpt_bigcode) GPTBigCodeForSequenceClassification (class in intel_extension_for_transformers.transformers.modeling.gpt_bigcode.modeling_gpt_bigcode) GPTBigCodeForTokenClassification (class in intel_extension_for_transformers.transformers.modeling.gpt_bigcode.modeling_gpt_bigcode) GPTBigCodeModel (class in intel_extension_for_transformers.transformers.modeling.gpt_bigcode.modeling_gpt_bigcode) GPTBigCodePreTrainedModel (class in intel_extension_for_transformers.transformers.modeling.gpt_bigcode.modeling_gpt_bigcode) GPTQConfig (class in intel_extension_for_transformers.transformers.utils.config) Graph (class in intel_extension_for_transformers.transformers.runtime.compile.graph.graph) graph_dispatch() (intel_extension_for_transformers.transformers.runtime.compile.graph.graph.Graph method) graph_init() (intel_extension_for_transformers.transformers.runtime.compile.graph.graph.Graph method) graph_node_names_details() (in module intel_extension_for_transformers.transformers.runtime.compile.onnx_utils) (in module intel_extension_for_transformers.transformers.runtime.compile.tf_utils)

H

header_supercell_tree() (in module util.postprocess) hierarchical_subsequence() (in module intel_extension_for_transformers.neural_chat.tools.rome.utils.nethook)

History (class in intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats) HungarianMatcher (class in models.matcher)

I

Identity (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) infer_framework_load_model() (in module intel_extension_for_transformers.transformers.pipeline) infer_task() (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) inference() (intel_extension_for_transformers.transformers.runtime.compile.graph.graph.Graph method) info() (in module intel_extension_for_transformers.transformers.runtime.compile.logger) InnerProduct (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) InnerproductReshapeFusion (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.InnerproductReshapeFusion) InnerproductWithBiasGelu (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.innerproductwithbiasgelu) InnerproductwithSlice (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.innerproductwithslice) InnerproductWithSwish (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.innerproductwithswish) Input (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) InputData (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.input_data) InputFile (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.input_file) inquire_config_item() (intel_extension_for_transformers.transformers.runtime.compile.graph.graph.Graph method) insert_environ_info() (in module intel_extension_for_transformers.transformers.runtime.compile.graph_utils) insert_nodes() (intel_extension_for_transformers.transformers.runtime.compile.graph.graph.Graph method) insert_pattern() (in module intel_extension_for_transformers.transformers.runtime.compile.graph_utils) insert_quant_info() (in module intel_extension_for_transformers.transformers.runtime.compile.graph_utils) InsertBF16Node (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.insert_bf16_node) InsertQuantNode (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.insert_quant_node) Int8BF16MixedPrecisionChecker (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.int8_bf16_mixed_precision_checker) intel_extension_for_transformers.langchain.langchain_community.retrievers.child_parent_retriever module intel_extension_for_transformers.langchain.langchain_community.vectorstores.chroma module intel_extension_for_transformers.neural_chat.chatbot module intel_extension_for_transformers.neural_chat.config module intel_extension_for_transformers.neural_chat.config_logging module intel_extension_for_transformers.neural_chat.errorcode module intel_extension_for_transformers.neural_chat.pipeline module intel_extension_for_transformers.neural_chat.pipeline.plugins.image2image.instructpix2pix_pipeline module intel_extension_for_transformers.neural_chat.pipeline.plugins.memory.memory module intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.detector.intent_detection module intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.detector.query_explainer module intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.parser.parser module intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.retriever_adapter module intel_extension_for_transformers.neural_chat.pipeline.plugins.security.safety_checker module intel_extension_for_transformers.neural_chat.pipeline.plugins.video.face_animation.src.face3d.models.bfm module intel_extension_for_transformers.neural_chat.pipeline.plugins.video.face_animation.src.face3d.models.networks module intel_extension_for_transformers.neural_chat.pipeline.plugins.video.face_animation.src.face3d.util module intel_extension_for_transformers.neural_chat.pipeline.plugins.video.face_animation.src.face3d.util.load_mats module intel_extension_for_transformers.neural_chat.pipeline.plugins.video.face_animation.src.face3d.util.preprocess module intel_extension_for_transformers.neural_chat.pipeline.plugins.video.face_animation.src.face3d.util.util module intel_extension_for_transformers.neural_chat.server.restful.openai_protocol module intel_extension_for_transformers.neural_chat.tools.rome.repr_tools module intel_extension_for_transformers.neural_chat.tools.rome.utils.nethook module intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats module intel_extension_for_transformers.tools.utils module intel_extension_for_transformers.transformers.benchmark module intel_extension_for_transformers.transformers.config module intel_extension_for_transformers.transformers.dynamic module intel_extension_for_transformers.transformers.dynamic.drop_and_restore_utils module intel_extension_for_transformers.transformers.dynamic.evolution module intel_extension_for_transformers.transformers.kv_cache_compression.models.modeling_llama module intel_extension_for_transformers.transformers.modeling module intel_extension_for_transformers.transformers.modeling.gpt_bigcode.modeling_gpt_bigcode module intel_extension_for_transformers.transformers.modeling.model module intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic module intel_extension_for_transformers.transformers.modeling.modeling_gaudi.models.bart.modeling_bart module intel_extension_for_transformers.transformers.modeling.modeling_gaudi.models.llama.pos_shift_llama module intel_extension_for_transformers.transformers.modeling.modeling_gaudi.models.mistral.modeling_mistral module intel_extension_for_transformers.transformers.modeling.modeling_gaudi.models.mixtral.modeling_mixtral module intel_extension_for_transformers.transformers.modeling.modeling_gaudi.models.phi.modeling_phi module intel_extension_for_transformers.transformers.modeling.modeling_gaudi.models.swin.modeling_swin module intel_extension_for_transformers.transformers.modeling.modeling_gaudi.streaming_llm module intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic module intel_extension_for_transformers.transformers.pipeline module intel_extension_for_transformers.transformers.pruner module intel_extension_for_transformers.transformers.pruner.pruning module intel_extension_for_transformers.transformers.quantization module intel_extension_for_transformers.transformers.runtime module intel_extension_for_transformers.transformers.runtime.compile module intel_extension_for_transformers.transformers.runtime.compile.compile module intel_extension_for_transformers.transformers.runtime.compile.extractors module intel_extension_for_transformers.transformers.runtime.compile.extractors.extractor module intel_extension_for_transformers.transformers.runtime.compile.extractors.onnx_extractor module intel_extension_for_transformers.transformers.runtime.compile.extractors.tf_extractor module intel_extension_for_transformers.transformers.runtime.compile.extractors.torch_extractor module intel_extension_for_transformers.transformers.runtime.compile.graph module intel_extension_for_transformers.transformers.runtime.compile.graph.graph module intel_extension_for_transformers.transformers.runtime.compile.graph_utils module intel_extension_for_transformers.transformers.runtime.compile.loaders module intel_extension_for_transformers.transformers.runtime.compile.loaders.loader module intel_extension_for_transformers.transformers.runtime.compile.logger module intel_extension_for_transformers.transformers.runtime.compile.onnx_utils module intel_extension_for_transformers.transformers.runtime.compile.ops module intel_extension_for_transformers.transformers.runtime.compile.ops.all module intel_extension_for_transformers.transformers.runtime.compile.ops.assert module intel_extension_for_transformers.transformers.runtime.compile.ops.baddbmm module intel_extension_for_transformers.transformers.runtime.compile.ops.batch_matmul module intel_extension_for_transformers.transformers.runtime.compile.ops.batch_matmul_v2 module intel_extension_for_transformers.transformers.runtime.compile.ops.bias_add module intel_extension_for_transformers.transformers.runtime.compile.ops.cast module intel_extension_for_transformers.transformers.runtime.compile.ops.concat module intel_extension_for_transformers.transformers.runtime.compile.ops.conv module intel_extension_for_transformers.transformers.runtime.compile.ops.cos module intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops module intel_extension_for_transformers.transformers.runtime.compile.ops.expand_dims module intel_extension_for_transformers.transformers.runtime.compile.ops.fused_batch_matmul_v2 module intel_extension_for_transformers.transformers.runtime.compile.ops.fused_batch_norm_v3 module intel_extension_for_transformers.transformers.runtime.compile.ops.fused_gemm module intel_extension_for_transformers.transformers.runtime.compile.ops.fused_matmul module intel_extension_for_transformers.transformers.runtime.compile.ops.gather module intel_extension_for_transformers.transformers.runtime.compile.ops.gather_elements module intel_extension_for_transformers.transformers.runtime.compile.ops.gelu module intel_extension_for_transformers.transformers.runtime.compile.ops.gemm module intel_extension_for_transformers.transformers.runtime.compile.ops.iterator_get_next module intel_extension_for_transformers.transformers.runtime.compile.ops.iterator_v2 module intel_extension_for_transformers.transformers.runtime.compile.ops.layer_normalization module intel_extension_for_transformers.transformers.runtime.compile.ops.log_softmax module intel_extension_for_transformers.transformers.runtime.compile.ops.map_and_batch_dataset module intel_extension_for_transformers.transformers.runtime.compile.ops.matmul module intel_extension_for_transformers.transformers.runtime.compile.ops.mean module intel_extension_for_transformers.transformers.runtime.compile.ops.mkl_layer_norm module intel_extension_for_transformers.transformers.runtime.compile.ops.model_dataset module intel_extension_for_transformers.transformers.runtime.compile.ops.one_hot module intel_extension_for_transformers.transformers.runtime.compile.ops.onnx_input module intel_extension_for_transformers.transformers.runtime.compile.ops.op module intel_extension_for_transformers.transformers.runtime.compile.ops.optimize_dataset module intel_extension_for_transformers.transformers.runtime.compile.ops.pack module intel_extension_for_transformers.transformers.runtime.compile.ops.padding_sequence module intel_extension_for_transformers.transformers.runtime.compile.ops.placeholder module intel_extension_for_transformers.transformers.runtime.compile.ops.pos_embed module intel_extension_for_transformers.transformers.runtime.compile.ops.pow module intel_extension_for_transformers.transformers.runtime.compile.ops.quantize_linear module intel_extension_for_transformers.transformers.runtime.compile.ops.quantize_v2 module intel_extension_for_transformers.transformers.runtime.compile.ops.quantized_fused_matmul_and_dequantize module intel_extension_for_transformers.transformers.runtime.compile.ops.quantized_matmul_with_bias_and_dequantize module intel_extension_for_transformers.transformers.runtime.compile.ops.reduce_mean module intel_extension_for_transformers.transformers.runtime.compile.ops.reduce_sum module intel_extension_for_transformers.transformers.runtime.compile.ops.reorder module intel_extension_for_transformers.transformers.runtime.compile.ops.reshape module intel_extension_for_transformers.transformers.runtime.compile.ops.resize module intel_extension_for_transformers.transformers.runtime.compile.ops.rsub module intel_extension_for_transformers.transformers.runtime.compile.ops.scatter_elements module intel_extension_for_transformers.transformers.runtime.compile.ops.shape module intel_extension_for_transformers.transformers.runtime.compile.ops.sin module intel_extension_for_transformers.transformers.runtime.compile.ops.size module intel_extension_for_transformers.transformers.runtime.compile.ops.slice_position_ids module intel_extension_for_transformers.transformers.runtime.compile.ops.softmax module intel_extension_for_transformers.transformers.runtime.compile.ops.split module intel_extension_for_transformers.transformers.runtime.compile.ops.squeeze module intel_extension_for_transformers.transformers.runtime.compile.ops.strided_slice module intel_extension_for_transformers.transformers.runtime.compile.ops.tensor module intel_extension_for_transformers.transformers.runtime.compile.ops.top_k module intel_extension_for_transformers.transformers.runtime.compile.ops.transpose module intel_extension_for_transformers.transformers.runtime.compile.ops.unpack module

intel_extension_for_transformers.transformers.runtime.compile.ops.unsqueeze module intel_extension_for_transformers.transformers.runtime.compile.ops.view module intel_extension_for_transformers.transformers.runtime.compile.ops.where module intel_extension_for_transformers.transformers.runtime.compile.optimizer module intel_extension_for_transformers.transformers.runtime.compile.sub_graph module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.add_cls_token module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.add_embeddings module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.arangewithreciprocal module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.attention_mask_length_adaptive_keep_indices module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.attention_output_layer_norm_length_adaptive_keep_indices module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.attention_reshape module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.attentionBlock_AttentionMaskAddReshape module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.attentionBlock_ConstantOfShapeWithMul module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.attentionBlock_QKVPreReshape module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.attentionBlock_QKVReshape module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.attentionBlock_WeightReshapeTo4D module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.cast_to module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.collect_quant_info module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.conv_reshape module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.decoder_attn_reshape module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.einsumwitharange module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.embeddingbag module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.embeddings_to_2d_before_inner_product module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.gelu module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.generate_sequence module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.InnerproductReshapeFusion module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.innerproductwithbiasgelu module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.innerproductwithslice module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.innerproductwithswish module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.input_data module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.input_file module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.insert_bf16_node module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.insert_quant_node module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.int8_bf16_mixed_precision_checker module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.interact_features module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.last_layer_shape module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.layer_norm module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.layer_norm_with_reduce_mean module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.layer_norm_with_transpose module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.llama_embeding module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.llama_matmulwithtranspose module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.llama_postprocess module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.llama_rotary_pos_emb module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.lower_all_tuples module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.matmul_with_bias module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.matmul_with_bias_add module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.matmul_with_bias_gelu module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.matmul_with_bias_relu module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.matmul_with_bias_sigmoid module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.matmul_with_bias_tanh module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.matmul_with_bias_unsqueeze module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.matmul_with_transpose module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.matmul_with_transpose_scale_add module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.merged_embeddingbag module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.neox_reorder_change module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.neox_rotary_pos_emb module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.operator_adaptor module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.output_data module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.padding_sequence module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.pattern module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.position_embeddings module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.position_embeddings_v1 module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.qkv_merge module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.qkv_reshape module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.quant_gather_to_bf16 module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.quantize_fusion module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.quantized_graph_dtype_refactor module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.remove_constant_op module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.remove_last_view module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.remove_range module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.remove_unused_operator module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.remove_zeros module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.removeslice module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.reshape_after_restore_hidden_states module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.reshape_before_and_after_attention_out_layer_norm_gather_elements module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.reshape_before_restore_hidden_states module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.reshape_fusion module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.restore_hidden_states_in_length_adaptive_update_indices module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.rms_norm module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.rotary_pos_emb module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.slicemask module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.stableDiffusion_bf16Convert module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.stableDiffusion_collectQDQInfo module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.stableDiffusion_ExplicitNHWCTranspose module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.stableDiffusion_ExplicitNHWCTransposeQAT module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.stableDiffusion_insertQuantNode module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.stableDiffusion_MHAReshape module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.stableDiffusion_QuantizeFusion module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.stableDiffusion_ReshapeFusion module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.start_end_logits module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.subgraph_matcher module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.textEncdoer_word_embedding module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.textEncoder_AttentionMaskAddReshape module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.textEncoder_AttentionReshape module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.textEncoder_causal_attention_mask module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.textEncoder_KVReshape module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.textEncoder_MulReshape module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.textEncoder_QReshape module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.textEncoder_SoftmaxReshape module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.token_type_embeddings module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.token_type_embeddings_v1 module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.torch_embedding module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.torch_ip_insert_bias module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.torch_unpack_baddbmm module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.torchinsertbf16node module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.torchpaddingsquence module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transformer2Dmodel_AttentionMaskAddReshape module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transformer2Dmodel_ConstantOfShapeWithMul module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transformer2Dmodel_encoderHiddenStatesReshape module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transformer2Dmodel_FFNSlice module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transformer2Dmodel_FFNSlice_1 module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transformer2Dmodel_getSampleBatch module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transformer2Dmodel_QKVPreReshape module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transformer2Dmodel_QKVReshape module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transformer2Dmodel_QKVReshape4D module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transformer2Dmodel_sampleSlice module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transpose_batch_matmul module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.word_embeddings module intel_extension_for_transformers.transformers.runtime.compile.tf_utils module intel_extension_for_transformers.transformers.runtime.compile.torch_utils module intel_extension_for_transformers.transformers.trainer module intel_extension_for_transformers.transformers.utils module intel_extension_for_transformers.transformers.utils.config module intel_extension_for_transformers.transformers.utils.get_throughput module intel_extension_for_transformers.transformers.utils.metrics module intel_extension_for_transformers.transformers.utils.objectives module intel_extension_for_transformers.transformers.utils.utility module InteractFeatures (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.interact_features) interpolate() (in module util.misc) inverse() (in module intel_extension_for_transformers.transformers.dynamic.evolution) invoke_with_optional_args() (in module intel_extension_for_transformers.neural_chat.tools.rome.utils.nethook) iob() (in module util.postprocess) IoU (class in intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats) iou() (in module util.postprocess) is_null_numpy_value() (in module intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats) is_supported_onnx_graph() (in module intel_extension_for_transformers.transformers.runtime.compile.onnx_utils) is_supported_onnx_node() (in module intel_extension_for_transformers.transformers.runtime.compile.onnx_utils) IteratorGetNext (class in intel_extension_for_transformers.transformers.runtime.compile.ops.iterator_get_next) IteratorV2 (class in intel_extension_for_transformers.transformers.runtime.compile.ops.iterator_v2) ITREXQuantizationConfigMixin (class in intel_extension_for_transformers.transformers.utils.config)

J

jd (C++ type), [1], [2], [3], [4], [5], [6], [7], [8], [9], [10], [11] jd::attention (C++ class) jd::attention::attention (C++ function), [1] jd::attention::~attention (C++ function) jd::attention_desc (C++ class) jd::attention_desc::attention_desc (C++ function), [1] jd::attention_desc::~attention_desc (C++ function) jd::attention_io (C++ enum) jd::attention_io::K_BIAS (C++ enumerator) jd::attention_io::K_SCALES (C++ enumerator) jd::attention_io::K_WEIGHT (C++ enumerator) jd::attention_io::MERGE_DST (C++ enumerator) jd::attention_io::MERGE_SRC (C++ enumerator) jd::attention_io::Q_BIAS (C++ enumerator) jd::attention_io::Q_K_SCALES (C++ enumerator) jd::attention_io::Q_K_SRC2 (C++ enumerator) jd::attention_io::Q_SCALES (C++ enumerator) jd::attention_io::Q_WEIGHT (C++ enumerator) jd::attention_io::QK_V_OUTPUT_SCALES (C++ enumerator) jd::attention_io::QK_V_OUTPUT_ZERO_POINT (C++ enumerator) jd::attention_io::RESHAPE_INPUT (C++ enumerator) jd::attention_io::V_BIAS (C++ enumerator) jd::attention_io::V_SCALES (C++ enumerator) jd::attention_io::V_WEIGHT (C++ enumerator) jd::cpu_engine_t (C++ class) jd::cpu_engine_t::cpu_engine_t (C++ function) jd::cpu_engine_t::create_kernel (C++ function) jd::cpu_engine_t::create_memory_storage (C++ function) jd::cpu_engine_t::create_stream (C++ function) jd::cpu_engine_t::empty_list (C++ member) jd::cpu_engine_t::get_implementation_list (C++ function) jd::cpu_engine_t::~cpu_engine_t (C++ function) jd::dynamic_quant (C++ class) jd::dynamic_quant::dynamic_quant (C++ function), [1] jd::dynamic_quant::~dynamic_quant (C++ function) jd::dynamic_quant_desc (C++ class) jd::dynamic_quant_desc::dynamic_quant_desc (C++ function), [1] jd::dynamic_quant_desc::~dynamic_quant_desc (C++ function) jd::dynamic_quant_matmul (C++ class) jd::dynamic_quant_matmul::dynamic_quant_matmul (C++ function), [1] jd::dynamic_quant_matmul::~dynamic_quant_matmul (C++ function) jd::dynamic_quant_matmul_desc (C++ class) jd::dynamic_quant_matmul_desc::dynamic_quant_matmul_desc (C++ function), [1] jd::dynamic_quant_matmul_desc::~dynamic_quant_matmul_desc (C++ function) jd::eltwiseop (C++ class) jd::eltwiseop::eltwiseop (C++ function), [1] jd::eltwiseop::~eltwiseop (C++ function) jd::eltwiseop_desc (C++ class) jd::eltwiseop_desc::eltwiseop_desc (C++ function), [1] jd::eltwiseop_desc::~eltwiseop_desc (C++ function) jd::engine_t (C++ class) jd::engine_t::create_kernel (C++ function) jd::engine_t::create_memory_storage (C++ function) jd::engine_t::create_stream (C++ function) jd::engine_t::engine_kind_ (C++ member) jd::engine_t::engine_t (C++ function) jd::engine_t::get_engine_kind (C++ function) jd::engine_t::get_implementation_list (C++ function) jd::engine_t::get_runtime_kind (C++ function) jd::engine_t::runtime_kind_ (C++ member) jd::engine_t::~engine_t (C++ function) jd::gather (C++ class) jd::gather::gather (C++ function), [1] jd::gather::~gather (C++ function) jd::gather_desc (C++ class) jd::gather_desc::gather_desc (C++ function), [1] jd::gather_desc::~gather_desc (C++ function) jd::groupnorm (C++ class) jd::groupnorm::groupnorm (C++ function), [1] jd::groupnorm::~groupnorm (C++ function) jd::groupnorm_desc (C++ class) jd::groupnorm_desc::groupnorm_desc (C++ function), [1] jd::groupnorm_desc::~groupnorm_desc (C++ function) jd::kernel_desc_proxy (C++ class) jd::kernel_desc_proxy::create_proxy_object (C++ function) jd::kernel_desc_proxy::impl_list_ (C++ member) jd::kernel_desc_proxy::kernel_desc_proxy (C++ function), [1] jd::kernel_desc_proxy::kernel_kind (C++ function) jd::kernel_desc_proxy::~kernel_desc_proxy (C++ function) jd::kernel_proxy (C++ class) jd::kernel_proxy::create_proxy_object (C++ function) jd::kernel_proxy::execute (C++ function), [1] jd::kernel_proxy::get_workspace_size (C++ function) jd::kernel_proxy::kernel_kind (C++ function) jd::kernel_proxy::kernel_proxy (C++ function), [1] jd::kernel_proxy::~kernel_proxy (C++ function) jd::layernorm_ba (C++ class) jd::layernorm_ba::layernorm_ba (C++ function), [1] jd::layernorm_ba::~layernorm_ba (C++ function) jd::layernorm_ba_desc (C++ class) jd::layernorm_ba_desc::layernorm_ba_desc (C++ function), [1] jd::layernorm_ba_desc::~layernorm_ba_desc (C++ function) jd::layernormalized_spmm (C++ class) jd::layernormalized_spmm::layernormalized_spmm (C++ function), [1] jd::layernormalized_spmm::~layernormalized_spmm (C++ function) jd::layernormalized_spmm_desc (C++ class) jd::layernormalized_spmm_desc::layernormalized_spmm_desc (C++ function), [1] jd::layernormalized_spmm_desc::~layernormalized_spmm_desc (C++ function) jd::logsoftmax (C++ class) jd::logsoftmax::logsoftmax (C++ function), [1] jd::logsoftmax::~logsoftmax (C++ function) jd::logsoftmax_desc (C++ class) jd::logsoftmax_desc::logsoftmax_desc (C++ function), [1] jd::logsoftmax_desc::~logsoftmax_desc (C++ function) jd::mha_dense (C++ class) jd::mha_dense::mha_dense (C++ function), [1] jd::mha_dense::~mha_dense (C++ function) jd::mha_dense_desc (C++ class) jd::mha_dense_desc::mha_dense_desc (C++ function), [1] jd::mha_dense_desc::~mha_dense_desc (C++ function) jd::operator_desc (C++ class) jd::operator_desc::apply_postops_list (C++ function) jd::operator_desc::apply_postops_list_ (C++ member) jd::operator_desc::attrs (C++ function) jd::operator_desc::attrs_ (C++ member) jd::operator_desc::binaryop_list_ (C++ member) jd::operator_desc::engine_kind (C++ function) jd::operator_desc::engine_kind_ (C++ member) jd::operator_desc::get_binaryop_list (C++ function) jd::operator_desc::impl_nthr (C++ function) jd::operator_desc::impl_nthr_ (C++ member) jd::operator_desc::ker_kind_ (C++ member) jd::operator_desc::ker_prop_ (C++ member) jd::operator_desc::kernel_kind (C++ function) jd::operator_desc::kernel_prop (C++ function) jd::operator_desc::operator== (C++ function) jd::operator_desc::operator_desc (C++ function), [1], [2] jd::operator_desc::runtime_kind (C++ function) jd::operator_desc::runtime_kind_ (C++ member) jd::operator_desc::set_binaryop_list (C++ function) jd::operator_desc::tensor_descs (C++ function) jd::operator_desc::tensor_dtypes (C++ function) jd::operator_desc::tensor_ftypes (C++ function) jd::operator_desc::tensor_shapes (C++ function) jd::operator_desc::ts_descs_ (C++ member) jd::operator_desc::~operator_desc (C++ function) jd::proxy_base (C++ class) jd::proxy_base::create_proxy_object (C++ function) jd::proxy_base::data_handle_ (C++ member) jd::proxy_base::get_sp (C++ function) jd::proxy_base::proxy_base (C++ function) jd::proxy_base::reset_sp (C++ function) jd::proxy_base::~proxy_base (C++ function) jd::slice (C++ class) jd::slice::slice (C++ function), [1] jd::slice::~slice (C++ function) jd::slice_desc (C++ class) jd::slice_desc::slice_desc (C++ function), [1] jd::slice_desc::~slice_desc (C++ function) jd::softmax (C++ class) jd::softmax::softmax (C++ function), [1] jd::softmax::~softmax (C++ function) jd::softmax_desc (C++ class) jd::softmax_desc::softmax_desc (C++ function), [1] jd::softmax_desc::~softmax_desc (C++ function) jd::sparse_matmul (C++ class) jd::sparse_matmul::sparse_matmul (C++ function), [1] jd::sparse_matmul::~sparse_matmul (C++ function) jd::sparse_matmul_desc (C++ class) jd::sparse_matmul_desc::sparse_matmul_desc (C++ function), [1] jd::sparse_matmul_desc::~sparse_matmul_desc (C++ function) jd::ssd (C++ type), [1], [2], [3], [4], [5], [6] jd::ssd::amx_bf16_params_t (C++ type) jd::ssd::amx_bf16bf16_inputs_t (C++ type) jd::ssd::amx_bf16f32_inputs_t (C++ type) jd::ssd::amx_inputs_t (C++ struct) jd::ssd::amx_inputs_t::bias (C++ member) jd::ssd::amx_inputs_t::dst (C++ member) jd::ssd::amx_inputs_t::src (C++ member) jd::ssd::amx_inputs_t::weight (C++ member) jd::ssd::amx_int8_params_t (C++ type) jd::ssd::amx_params_t (C++ struct) jd::ssd::amx_params_t::blocks_per_group (C++ member) jd::ssd::amx_params_t::blocksize (C++ member) jd::ssd::amx_params_t::colidxs (C++ member) jd::ssd::amx_params_t::group_rowptr (C++ member) jd::ssd::amx_params_t::has_bias (C++ member) jd::ssd::amx_params_t::nnz_group (C++ member) jd::ssd::amx_params_t::nrowptr (C++ member) jd::ssd::amx_params_t::num_tileM (C++ member) jd::ssd::amx_params_t::postop_attrs (C++ member) jd::ssd::amx_params_t::same_src_dtype (C++ member) jd::ssd::amx_params_t::shape (C++ member) jd::ssd::amx_params_t::tileM (C++ member) jd::ssd::amx_params_t::tileN (C++ member) jd::ssd::amx_params_t::weight (C++ member) jd::ssd::avx512_data_t (C++ struct) jd::ssd::avx512_data_t::bias (C++ member) jd::ssd::avx512_data_t::dense (C++ member) jd::ssd::avx512_data_t::dst (C++ member) jd::ssd::avx512_data_t::sparse (C++ member) jd::ssd::avx512_fp32_params_t (C++ struct) jd::ssd::avx512_fp32_params_t::has_bias (C++ member) jd::ssd::avx512_fp32_params_t::im_end (C++ member) jd::ssd::avx512_fp32_params_t::im_start (C++ member) jd::ssd::avx512_fp32_params_t::in_end (C++ member) jd::ssd::avx512_fp32_params_t::in_start (C++ member) jd::ssd::avx512_fp32_params_t::K (C++ member) jd::ssd::avx512_fp32_params_t::M (C++ member) jd::ssd::avx512_fp32_params_t::N (C++ member) jd::ssd::avx512_fp32_params_t::postop_attrs (C++ member) jd::ssd::avx512_fp32_params_t::sparse_ptr (C++ member) jd::ssd::BIAS (C++ member) jd::ssd::DST (C++ member) jd::ssd::DST_M1 (C++ member) jd::ssd::DST_M2 (C++ member) jd::ssd::eltwiseop_data_t (C++ struct) jd::ssd::eltwiseop_data_t::dst (C++ member) jd::ssd::eltwiseop_data_t::element_num (C++ member) jd::ssd::eltwiseop_data_t::src (C++ member) jd::ssd::eltwiseop_param_t (C++ struct) jd::ssd::eltwiseop_param_t::element_num (C++ member) jd::ssd::eltwiseop_param_t::element_num_each_th (C++ member) jd::ssd::eltwiseop_param_t::in_dt (C++ member) jd::ssd::eltwiseop_param_t::out_dt (C++ member) jd::ssd::eltwiseop_param_t::postop_attrs (C++ member) jd::ssd::eltwiseop_param_t::remain_element (C++ member) jd::ssd::layernorm_ba_data_t (C++ struct) jd::ssd::layernorm_ba_data_t::[anonymous] (C++ member) jd::ssd::layernorm_ba_data_t::alpha (C++ member) jd::ssd::layernorm_ba_data_t::beta (C++ member) jd::ssd::layernorm_ba_data_t::dst (C++ member) jd::ssd::layernorm_ba_data_t::dst2 (C++ member) jd::ssd::layernorm_ba_data_t::eps (C++ member) jd::ssd::layernorm_ba_data_t::mean (C++ member) jd::ssd::layernorm_ba_data_t::n (C++ member) jd::ssd::layernorm_ba_data_t::one (C++ member) jd::ssd::layernorm_ba_data_t::process_row (C++ member) jd::ssd::layernorm_ba_data_t::src (C++ member) jd::ssd::layernorm_ba_data_t::var (C++ member) jd::ssd::layernorm_ba_param_t (C++ struct) jd::ssd::layernorm_ba_param_t::batch_num (C++ member) jd::ssd::layernorm_ba_param_t::binaryop_attrs (C++ member)

jd::ssd::layernorm_ba_param_t::col_num (C++ member) jd::ssd::layernorm_ba_param_t::direct_process_row (C++ member) jd::ssd::layernorm_ba_param_t::input_dt (C++ member) jd::ssd::layernorm_ba_param_t::ker_per_batch (C++ member) jd::ssd::layernorm_ba_param_t::output2_dt (C++ member) jd::ssd::layernorm_ba_param_t::output_dt (C++ member) jd::ssd::layernorm_ba_param_t::postop_attrs (C++ member) jd::ssd::layernorm_ba_param_t::process_batch_per_ker (C++ member) jd::ssd::layernorm_ba_param_t::process_col (C++ member) jd::ssd::layernorm_ba_param_t::row_num (C++ member) jd::ssd::layernorm_ba_param_t::spec_type (C++ member) jd::ssd::layernorm_ba_param_t::split_output (C++ member) jd::ssd::layernorm_ba_param_t::thread_elt_offset (C++ member) jd::ssd::matmul_data_t (C++ struct) jd::ssd::matmul_data_t::dst (C++ member) jd::ssd::matmul_data_t::src0 (C++ member) jd::ssd::matmul_data_t::src1 (C++ member) jd::ssd::matmul_data_t::src2 (C++ member) jd::ssd::matmul_fp8_data_t (C++ struct) jd::ssd::matmul_fp8_data_t::alpha (C++ member) jd::ssd::matmul_fp8_data_t::astep (C++ member) jd::ssd::matmul_fp8_data_t::beta (C++ member) jd::ssd::matmul_fp8_data_t::bstep (C++ member) jd::ssd::matmul_fp8_data_t::cstep (C++ member) jd::ssd::matmul_fp8_data_t::dstep (C++ member) jd::ssd::matmul_fp8_data_t::k (C++ member) jd::ssd::matmul_fp8_data_t::kpos (C++ member) jd::ssd::matmul_fp8_data_t::matA (C++ member) jd::ssd::matmul_fp8_data_t::matB (C++ member) jd::ssd::matmul_fp8_data_t::matC (C++ member) jd::ssd::matmul_fp8_data_t::matD (C++ member) jd::ssd::matmul_fp8_data_t::matE (C++ member) jd::ssd::matmul_fp8_data_t::n (C++ member) jd::ssd::matmul_fp8_data_t::scale (C++ member) jd::ssd::matmul_fp8_param_t (C++ struct) jd::ssd::matmul_fp8_param_t::[anonymous] (C++ member) jd::ssd::matmul_fp8_param_t::alpha (C++ member) jd::ssd::matmul_fp8_param_t::beta (C++ member) jd::ssd::matmul_fp8_param_t::has_append_sum (C++ member) jd::ssd::matmul_fp8_param_t::has_scale0 (C++ member) jd::ssd::matmul_fp8_param_t::K (C++ member) jd::ssd::matmul_fp8_param_t::M (C++ member) jd::ssd::matmul_fp8_param_t::N (C++ member) jd::ssd::matmul_fp8_param_t::postop_attrs (C++ member) jd::ssd::matmul_fp8_param_t::thread_num (C++ member) jd::ssd::matmul_fp8_param_t::weight_8bit (C++ member) jd::ssd::matmul_fp8_param_t::weight_bf16 (C++ member) jd::ssd::matmul_fp8_param_t::weight_f8_e4m3 (C++ member) jd::ssd::matmul_fp8_param_t::weight_f8_e5m2 (C++ member) jd::ssd::matmul_fp8_param_t::weight_int8 (C++ member) jd::ssd::matmul_fp8_param_t::weight_type (C++ member) jd::ssd::matmul_input (C++ type) jd::ssd::matmul_input::input (C++ enum) jd::ssd::matmul_input::input::APPEND_SUM (C++ enumerator) jd::ssd::matmul_input::input::matmul_io_MAX (C++ enumerator) jd::ssd::matmul_input::input::SCALE0 (C++ enumerator) jd::ssd::matmul_input::input::SRC0 (C++ enumerator) jd::ssd::matmul_input::input::SRC1 (C++ enumerator) jd::ssd::matmul_input::input::SRC2 (C++ enumerator) jd::ssd::matmul_input::input::ZP0 (C++ enumerator) jd::ssd::matmul_io (C++ type) jd::ssd::matmul_io::io (C++ enum) jd::ssd::matmul_io::io::APPEND_SUM (C++ enumerator) jd::ssd::matmul_io::io::DST0 (C++ enumerator) jd::ssd::matmul_io::io::matmul_io_MAX (C++ enumerator) jd::ssd::matmul_io::io::SCALE0 (C++ enumerator) jd::ssd::matmul_io::io::SRC0 (C++ enumerator) jd::ssd::matmul_io::io::SRC1 (C++ enumerator) jd::ssd::matmul_io::io::SRC2 (C++ enumerator) jd::ssd::matmul_io::io::ZP0 (C++ enumerator) jd::ssd::matmul_output (C++ type) jd::ssd::matmul_output::output (C++ enum) jd::ssd::matmul_output::output::DST0 (C++ enumerator) jd::ssd::matmul_param_t (C++ struct) jd::ssd::matmul_param_t::alpha (C++ member) jd::ssd::matmul_param_t::batch (C++ member) jd::ssd::matmul_param_t::beta (C++ member) jd::ssd::matmul_param_t::K (C++ member) jd::ssd::matmul_param_t::M (C++ member) jd::ssd::matmul_param_t::m_tile (C++ member) jd::ssd::matmul_param_t::N (C++ member) jd::ssd::matmul_param_t::n_tile (C++ member) jd::ssd::matmul_u8_data_t (C++ struct) jd::ssd::matmul_u8_data_t::dst (C++ member) jd::ssd::matmul_u8_data_t::scale (C++ member) jd::ssd::matmul_u8_data_t::src0 (C++ member) jd::ssd::matmul_u8_data_t::src1 (C++ member) jd::ssd::matmul_u8_data_t::zp (C++ member) jd::ssd::mean_var_reduce_data_t (C++ struct) jd::ssd::mean_var_reduce_data_t::mean_in (C++ member) jd::ssd::mean_var_reduce_data_t::mean_out (C++ member) jd::ssd::mean_var_reduce_data_t::var_in (C++ member) jd::ssd::mean_var_reduce_data_t::var_out (C++ member) jd::ssd::mean_var_reduce_param_t (C++ struct) jd::ssd::mean_var_reduce_param_t::BM (C++ member) jd::ssd::mean_var_reduce_param_t::BN (C++ member) jd::ssd::mean_var_reduce_param_t::element_num (C++ member) jd::ssd::mean_var_reduce_param_t::M (C++ member) jd::ssd::mean_var_reduce_param_t::N (C++ member) jd::ssd::SCALES (C++ member) jd::ssd::seq_vnni_copy_params (C++ struct) jd::ssd::seq_vnni_copy_params::dstptr (C++ member) jd::ssd::seq_vnni_copy_params::dststride (C++ member) jd::ssd::seq_vnni_copy_params::k (C++ member) jd::ssd::seq_vnni_copy_params::srcptr (C++ member) jd::ssd::seq_vnni_copy_params::srcstride (C++ member) jd::ssd::softmax_data_t (C++ struct) jd::ssd::softmax_data_t::dst (C++ member) jd::ssd::softmax_data_t::one (C++ member) jd::ssd::softmax_data_t::process_vec_num (C++ member) jd::ssd::softmax_data_t::src (C++ member) jd::ssd::softmax_data_t::tmp (C++ member) jd::ssd::softmax_param_t (C++ struct) jd::ssd::softmax_param_t::get_lut_exp_attrs (C++ member) jd::ssd::softmax_param_t::input_dt (C++ member) jd::ssd::softmax_param_t::output_dt (C++ member) jd::ssd::softmax_param_t::postop_attrs (C++ member) jd::ssd::softmax_param_t::scalar_num (C++ member) jd::ssd::softmax_param_t::sepc_type (C++ member) jd::ssd::softmax_param_t::vec_align_len (C++ member) jd::ssd::softmax_param_t::vec_num_per_thr (C++ member) jd::ssd::softmax_param_t::vec_num_tail_thr (C++ member) jd::ssd::softmax_param_t::vec_tail_len (C++ member) jd::ssd::sparse_scheme (C++ enum) jd::ssd::sparse_scheme::dense_x_sparse (C++ enumerator) jd::ssd::sparse_scheme::sparse_x_dense (C++ enumerator) jd::ssd::sparse_scheme::sparse_x_sparse (C++ enumerator) jd::ssd::sparse_scheme::undef (C++ enumerator) jd::ssd::spec_softmax_type (C++ enum) jd::ssd::spec_softmax_type::lut (C++ enumerator) jd::ssd::spec_translnorm_type (C++ enum) jd::ssd::spec_translnorm_type::direct (C++ enumerator) jd::ssd::spec_translnorm_type::normal (C++ enumerator) jd::ssd::SRC (C++ member) jd::ssd::subfunc_level (C++ enum) jd::ssd::subfunc_level::kdims (C++ enumerator) jd::ssd::subfunc_level::non_kdims (C++ enumerator) jd::ssd::subfunc_level::none (C++ enumerator) jd::ssd::subfunc_level::subfunc_level_MAX (C++ enumerator) jd::ssd::transpose_copy_params (C++ struct) jd::ssd::transpose_copy_params::dstptr (C++ member) jd::ssd::transpose_copy_params::dststride (C++ member) jd::ssd::transpose_copy_params::k (C++ member) jd::ssd::transpose_copy_params::srcptr (C++ member) jd::ssd::transpose_copy_params::srcstride (C++ member) jd::ssd::transpose_mha_io (C++ type) jd::ssd::transpose_mha_io::io (C++ enum) jd::ssd::transpose_mha_io::io::BATCH (C++ enumerator) jd::ssd::transpose_mha_io::io::DST (C++ enumerator) jd::ssd::transpose_mha_io::io::HEAD_NUM (C++ enumerator) jd::ssd::transpose_mha_io::io::HEAD_SIZE (C++ enumerator) jd::ssd::transpose_mha_io::io::MASK (C++ enumerator) jd::ssd::transpose_mha_io::io::SCALE_DST (C++ enumerator) jd::ssd::transpose_mha_io::io::SCALE_K (C++ enumerator) jd::ssd::transpose_mha_io::io::SCALE_Q (C++ enumerator) jd::ssd::transpose_mha_io::io::SCALE_V (C++ enumerator) jd::ssd::transpose_mha_io::io::SEQ_LEN (C++ enumerator) jd::ssd::transpose_mha_io::io::SL_PAD (C++ enumerator) jd::ssd::transpose_mha_io::io::SRC_K (C++ enumerator) jd::ssd::transpose_mha_io::io::SRC_Q (C++ enumerator) jd::ssd::transpose_mha_io::io::SRC_V (C++ enumerator) jd::ssd::transpose_mha_io::io::TMP2M (C++ enumerator) jd::ssd::transpose_mha_io::io::transpose_mha_io_MAX (C++ enumerator) jd::ssd::transpose_mha_io::io::ZP_DST (C++ enumerator) jd::ssd::transpose_mha_step1_params (C++ struct) jd::ssd::transpose_mha_step1_params::astep (C++ member) jd::ssd::transpose_mha_step1_params::batchk (C++ member) jd::ssd::transpose_mha_step1_params::cbatchstep (C++ member) jd::ssd::transpose_mha_step1_params::cfg (C++ member) jd::ssd::transpose_mha_step1_params::cstep (C++ member) jd::ssd::transpose_mha_step1_params::expsum (C++ member) jd::ssd::transpose_mha_step1_params::k (C++ member) jd::ssd::transpose_mha_step1_params::m (C++ member) jd::ssd::transpose_mha_step1_params::matA (C++ member) jd::ssd::transpose_mha_step1_params::matB (C++ member) jd::ssd::transpose_mha_step1_params::matC (C++ member) jd::ssd::transpose_mha_step1_params::matD (C++ member) jd::ssd::transpose_mha_step1_params::scaleAB (C++ member) jd::ssd::transpose_mha_step1_params::sumstep (C++ member) jd::ssd::transpose_mha_step2_params (C++ struct) jd::ssd::transpose_mha_step2_params::dstptr (C++ member) jd::ssd::transpose_mha_step2_params::dststride (C++ member) jd::ssd::transpose_mha_step2_params::k (C++ member) jd::ssd::transpose_mha_step2_params::srcptr (C++ member) jd::ssd::transpose_mha_step2_params::srcstride (C++ member) jd::ssd::transpose_mha_step2_params::sumptr (C++ member) jd::ssd::transpose_mha_step3_params (C++ struct) jd::ssd::transpose_mha_step3_params::astep (C++ member) jd::ssd::transpose_mha_step3_params::cfg (C++ member) jd::ssd::transpose_mha_step3_params::cstep (C++ member) jd::ssd::transpose_mha_step3_params::k (C++ member) jd::ssd::transpose_mha_step3_params::matA (C++ member) jd::ssd::transpose_mha_step3_params::matB (C++ member) jd::ssd::transpose_mha_step3_params::matC (C++ member) jd::ssd::transpose_mha_step3_params::scaleAB (C++ member) jd::ssd::transpose_mha_step3_params::scaleC (C++ member) jd::ssd::transpose_mha_step3_params::zeropointC (C++ member) jd::ssd::vnni_data_t (C++ struct) jd::ssd::vnni_data_t::ptr_bias (C++ member) jd::ssd::vnni_data_t::ptr_dense (C++ member) jd::ssd::vnni_data_t::ptr_dst (C++ member) jd::ssd::vnni_data_t::ptr_dst_m1 (C++ member) jd::ssd::vnni_data_t::ptr_dst_m2 (C++ member) jd::ssd::vnni_data_t::ptr_scales (C++ member) jd::ssd::vnni_param_t (C++ struct) jd::ssd::vnni_param_t::append_sum (C++ member) jd::ssd::vnni_param_t::blocksize (C++ member) jd::ssd::vnni_param_t::BM (C++ member) jd::ssd::vnni_param_t::BN (C++ member) jd::ssd::vnni_param_t::has_bias (C++ member) jd::ssd::vnni_param_t::im_start (C++ member) jd::ssd::vnni_param_t::indices (C++ member) jd::ssd::vnni_param_t::indptr (C++ member) jd::ssd::vnni_param_t::output_type (C++ member) jd::ssd::vnni_param_t::postop_attrs (C++ member) jd::ssd::vnni_param_t::sub_func (C++ member) jd::ssd::vnni_param_t::tile_w (C++ member) jd::ssd::vnni_param_t::weight (C++ member) jd::ssd::vnni_param_t::welford (C++ member) jd::ssd::WEI (C++ member) jd::ssd::WORK_SPACE (C++ member) jd::transpose_matmul (C++ class) jd::transpose_matmul::transpose_matmul (C++ function), [1] jd::transpose_matmul::~transpose_matmul (C++ function) jd::transpose_matmul_desc (C++ class) jd::transpose_matmul_desc::transpose_matmul_desc (C++ function), [1] jd::transpose_matmul_desc::~transpose_matmul_desc (C++ function) jd::transpose_mha (C++ class) jd::transpose_mha::transpose_mha (C++ function), [1] jd::transpose_mha::~transpose_mha (C++ function) jd::transpose_mha_desc (C++ class) jd::transpose_mha_desc::transpose_mha_desc (C++ function), [1] jd::transpose_mha_desc::~transpose_mha_desc (C++ function)

L

LastLayerShape (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.last_layer_shape) LatRange (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) LayerNorm (class in intel_extension_for_transformers.transformers.runtime.compile.ops.layer_normalization) (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.layer_norm) LayerNormalization (class in intel_extension_for_transformers.transformers.runtime.compile.ops.layer_normalization) LayerNormWithReduceMean (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.layer_norm_with_reduce_mean) LayerNormWithTranspose (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.layer_norm_with_transpose) LazyImport (class in intel_extension_for_transformers.transformers.runtime.compile.graph_utils) list2str() (in module intel_extension_for_transformers.transformers.runtime.compile.graph_utils) ListConstruct (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) ListUnpack (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) LlamaAttention (class in intel_extension_for_transformers.transformers.kv_cache_compression.models.modeling_llama) LlamaEmbeddings (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.llama_embeding) LlamaFlashAttention2 (class in intel_extension_for_transformers.transformers.kv_cache_compression.models.modeling_llama) LlamaMatMulWithTranspose (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.llama_matmulwithtranspose) LlamaPostprocess (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.llama_postprocess) LlamaRoraryPosEmb (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.llama_rotary_pos_emb) LlamaSdpaAttention (class in intel_extension_for_transformers.transformers.kv_cache_compression.models.modeling_llama) load() (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.Stat method) load_cached_state() (in module intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats) load_state_dict() (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.Bincount method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.CombinedStat method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.Covariance method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.CrossCovariance method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.CrossIoU method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.History method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.IoU method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.Mean method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.Quantile method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.SecondMoment method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.Stat method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.Variance method)

load_store() (intel_extension_for_transformers.transformers.dynamic.evolution.Evolution method) load_tf_weights_in_bert() (in module intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic) Loader (class in intel_extension_for_transformers.transformers.runtime.compile.loaders.loader) log() (in module intel_extension_for_transformers.transformers.runtime.compile.logger) Logger (class in intel_extension_for_transformers.transformers.runtime.compile.logger) LogSoftmax (class in intel_extension_for_transformers.transformers.runtime.compile.ops.log_softmax) Loop (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) loss_boxes() (models.detr.SetCriterion method) (models.detr_multi.SetCriterion method) loss_cardinality() (models.detr.SetCriterion method) (models.detr_multi.SetCriterion method) loss_labels() (models.detr.SetCriterion method) (models.detr_multi.SetCriterion method) loss_masks() (models.detr.SetCriterion method) (models.detr_multi.SetCriterion method) LowerAllTuples (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.lower_all_tuples)

M

main_eval_only module main_parse_and_eval module make_loader() (in module intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats) MakeIterator (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) MapAndBatchDataset (class in intel_extension_for_transformers.transformers.runtime.compile.ops.map_and_batch_dataset) Masked_fill (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) MaskHeadSmallConv (class in models.segmentation) masks_to_boxes() (in module util.box_ops) Matmul (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) MatMul (class in intel_extension_for_transformers.transformers.runtime.compile.ops.matmul) MatMulWithBias (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.matmul_with_bias) MatMulWithBiasAdd (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.matmul_with_bias_add) MatMulWithBiasGelu (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.matmul_with_bias_gelu) MatMulWithBiasRelu (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.matmul_with_bias_relu) MatMulWithBiasSigmoid (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.matmul_with_bias_sigmoid) MatMulWithBiasTanh (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) MatmulWithBiasTanh (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.matmul_with_bias_tanh) MatMulWithBiasUnsqueeze (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.matmul_with_bias_unsqueeze) MatMulWithTranspose (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.matmul_with_transpose) (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.matmul_with_transpose_scale_add) Max (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) Mean (class in intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats) (class in intel_extension_for_transformers.transformers.runtime.compile.ops.mean) MergedEmbeddingbag (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.merged_embeddingbag) Metric (class in intel_extension_for_transformers.transformers.utils.metrics) MHAttentionMap (class in models.segmentation) mkdir() (in module intel_extension_for_transformers.neural_chat.pipeline.plugins.video.face_animation.src.face3d.util.util) mkdirs() (in module intel_extension_for_transformers.neural_chat.pipeline.plugins.video.face_animation.src.face3d.util.util) MLP (class in models.detr) (class in models.detr_multi) mmr (intel_extension_for_transformers.langchain.langchain_community.retrievers.child_parent_retriever.SearchType attribute) model (intel_extension_for_transformers.transformers.pruner.pruning.Pruning attribute) ModelArguments (class in intel_extension_for_transformers.neural_chat.config) ModelDataset (class in intel_extension_for_transformers.transformers.runtime.compile.ops.model_dataset) models.backbone module models.detr module models.detr_multi module models.matcher module models.position_encoding module models.segmentation module models.transformer module modelsize() (intel_extension_for_transformers.transformers.utils.objectives.Objective static method) modify_node_connections() (intel_extension_for_transformers.transformers.runtime.compile.graph.graph.Graph method) module conversation gaudi_spawn intel_extension_for_transformers.langchain.langchain_community.retrievers.child_parent_retriever intel_extension_for_transformers.langchain.langchain_community.vectorstores.chroma intel_extension_for_transformers.neural_chat.chatbot intel_extension_for_transformers.neural_chat.config intel_extension_for_transformers.neural_chat.config_logging intel_extension_for_transformers.neural_chat.errorcode intel_extension_for_transformers.neural_chat.pipeline intel_extension_for_transformers.neural_chat.pipeline.plugins.image2image.instructpix2pix_pipeline intel_extension_for_transformers.neural_chat.pipeline.plugins.memory.memory intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.detector.intent_detection intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.detector.query_explainer intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.parser.parser intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.retriever_adapter intel_extension_for_transformers.neural_chat.pipeline.plugins.security.safety_checker intel_extension_for_transformers.neural_chat.pipeline.plugins.video.face_animation.src.face3d.models.bfm intel_extension_for_transformers.neural_chat.pipeline.plugins.video.face_animation.src.face3d.models.networks intel_extension_for_transformers.neural_chat.pipeline.plugins.video.face_animation.src.face3d.util intel_extension_for_transformers.neural_chat.pipeline.plugins.video.face_animation.src.face3d.util.load_mats intel_extension_for_transformers.neural_chat.pipeline.plugins.video.face_animation.src.face3d.util.preprocess intel_extension_for_transformers.neural_chat.pipeline.plugins.video.face_animation.src.face3d.util.util intel_extension_for_transformers.neural_chat.server.restful.openai_protocol intel_extension_for_transformers.neural_chat.tools.rome.repr_tools intel_extension_for_transformers.neural_chat.tools.rome.utils.nethook intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats intel_extension_for_transformers.tools.utils intel_extension_for_transformers.transformers.benchmark intel_extension_for_transformers.transformers.config intel_extension_for_transformers.transformers.dynamic intel_extension_for_transformers.transformers.dynamic.drop_and_restore_utils intel_extension_for_transformers.transformers.dynamic.evolution intel_extension_for_transformers.transformers.kv_cache_compression.models.modeling_llama intel_extension_for_transformers.transformers.modeling intel_extension_for_transformers.transformers.modeling.gpt_bigcode.modeling_gpt_bigcode intel_extension_for_transformers.transformers.modeling.model intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic intel_extension_for_transformers.transformers.modeling.modeling_gaudi.models.bart.modeling_bart intel_extension_for_transformers.transformers.modeling.modeling_gaudi.models.llama.pos_shift_llama intel_extension_for_transformers.transformers.modeling.modeling_gaudi.models.mistral.modeling_mistral intel_extension_for_transformers.transformers.modeling.modeling_gaudi.models.mixtral.modeling_mixtral intel_extension_for_transformers.transformers.modeling.modeling_gaudi.models.phi.modeling_phi intel_extension_for_transformers.transformers.modeling.modeling_gaudi.models.swin.modeling_swin intel_extension_for_transformers.transformers.modeling.modeling_gaudi.streaming_llm intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic intel_extension_for_transformers.transformers.pipeline intel_extension_for_transformers.transformers.pruner intel_extension_for_transformers.transformers.pruner.pruning intel_extension_for_transformers.transformers.quantization intel_extension_for_transformers.transformers.runtime intel_extension_for_transformers.transformers.runtime.compile intel_extension_for_transformers.transformers.runtime.compile.compile intel_extension_for_transformers.transformers.runtime.compile.extractors intel_extension_for_transformers.transformers.runtime.compile.extractors.extractor intel_extension_for_transformers.transformers.runtime.compile.extractors.onnx_extractor intel_extension_for_transformers.transformers.runtime.compile.extractors.tf_extractor intel_extension_for_transformers.transformers.runtime.compile.extractors.torch_extractor intel_extension_for_transformers.transformers.runtime.compile.graph intel_extension_for_transformers.transformers.runtime.compile.graph.graph intel_extension_for_transformers.transformers.runtime.compile.graph_utils intel_extension_for_transformers.transformers.runtime.compile.loaders intel_extension_for_transformers.transformers.runtime.compile.loaders.loader intel_extension_for_transformers.transformers.runtime.compile.logger intel_extension_for_transformers.transformers.runtime.compile.onnx_utils intel_extension_for_transformers.transformers.runtime.compile.ops intel_extension_for_transformers.transformers.runtime.compile.ops.all intel_extension_for_transformers.transformers.runtime.compile.ops.assert intel_extension_for_transformers.transformers.runtime.compile.ops.baddbmm intel_extension_for_transformers.transformers.runtime.compile.ops.batch_matmul intel_extension_for_transformers.transformers.runtime.compile.ops.batch_matmul_v2 intel_extension_for_transformers.transformers.runtime.compile.ops.bias_add intel_extension_for_transformers.transformers.runtime.compile.ops.cast intel_extension_for_transformers.transformers.runtime.compile.ops.concat intel_extension_for_transformers.transformers.runtime.compile.ops.conv intel_extension_for_transformers.transformers.runtime.compile.ops.cos intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops intel_extension_for_transformers.transformers.runtime.compile.ops.expand_dims intel_extension_for_transformers.transformers.runtime.compile.ops.fused_batch_matmul_v2 intel_extension_for_transformers.transformers.runtime.compile.ops.fused_batch_norm_v3 intel_extension_for_transformers.transformers.runtime.compile.ops.fused_gemm intel_extension_for_transformers.transformers.runtime.compile.ops.fused_matmul intel_extension_for_transformers.transformers.runtime.compile.ops.gather intel_extension_for_transformers.transformers.runtime.compile.ops.gather_elements intel_extension_for_transformers.transformers.runtime.compile.ops.gelu intel_extension_for_transformers.transformers.runtime.compile.ops.gemm intel_extension_for_transformers.transformers.runtime.compile.ops.iterator_get_next intel_extension_for_transformers.transformers.runtime.compile.ops.iterator_v2 intel_extension_for_transformers.transformers.runtime.compile.ops.layer_normalization intel_extension_for_transformers.transformers.runtime.compile.ops.log_softmax intel_extension_for_transformers.transformers.runtime.compile.ops.map_and_batch_dataset intel_extension_for_transformers.transformers.runtime.compile.ops.matmul intel_extension_for_transformers.transformers.runtime.compile.ops.mean intel_extension_for_transformers.transformers.runtime.compile.ops.mkl_layer_norm intel_extension_for_transformers.transformers.runtime.compile.ops.model_dataset intel_extension_for_transformers.transformers.runtime.compile.ops.one_hot intel_extension_for_transformers.transformers.runtime.compile.ops.onnx_input intel_extension_for_transformers.transformers.runtime.compile.ops.op intel_extension_for_transformers.transformers.runtime.compile.ops.optimize_dataset intel_extension_for_transformers.transformers.runtime.compile.ops.pack intel_extension_for_transformers.transformers.runtime.compile.ops.padding_sequence intel_extension_for_transformers.transformers.runtime.compile.ops.placeholder intel_extension_for_transformers.transformers.runtime.compile.ops.pos_embed intel_extension_for_transformers.transformers.runtime.compile.ops.pow intel_extension_for_transformers.transformers.runtime.compile.ops.quantize_linear intel_extension_for_transformers.transformers.runtime.compile.ops.quantize_v2 intel_extension_for_transformers.transformers.runtime.compile.ops.quantized_fused_matmul_and_dequantize intel_extension_for_transformers.transformers.runtime.compile.ops.quantized_matmul_with_bias_and_dequantize intel_extension_for_transformers.transformers.runtime.compile.ops.reduce_mean intel_extension_for_transformers.transformers.runtime.compile.ops.reduce_sum intel_extension_for_transformers.transformers.runtime.compile.ops.reorder intel_extension_for_transformers.transformers.runtime.compile.ops.reshape intel_extension_for_transformers.transformers.runtime.compile.ops.resize intel_extension_for_transformers.transformers.runtime.compile.ops.rsub intel_extension_for_transformers.transformers.runtime.compile.ops.scatter_elements intel_extension_for_transformers.transformers.runtime.compile.ops.shape intel_extension_for_transformers.transformers.runtime.compile.ops.sin intel_extension_for_transformers.transformers.runtime.compile.ops.size intel_extension_for_transformers.transformers.runtime.compile.ops.slice_position_ids intel_extension_for_transformers.transformers.runtime.compile.ops.softmax intel_extension_for_transformers.transformers.runtime.compile.ops.split intel_extension_for_transformers.transformers.runtime.compile.ops.squeeze intel_extension_for_transformers.transformers.runtime.compile.ops.strided_slice intel_extension_for_transformers.transformers.runtime.compile.ops.tensor intel_extension_for_transformers.transformers.runtime.compile.ops.top_k intel_extension_for_transformers.transformers.runtime.compile.ops.transpose intel_extension_for_transformers.transformers.runtime.compile.ops.unpack intel_extension_for_transformers.transformers.runtime.compile.ops.unsqueeze intel_extension_for_transformers.transformers.runtime.compile.ops.view intel_extension_for_transformers.transformers.runtime.compile.ops.where intel_extension_for_transformers.transformers.runtime.compile.optimizer intel_extension_for_transformers.transformers.runtime.compile.sub_graph intel_extension_for_transformers.transformers.runtime.compile.sub_graph.add_cls_token intel_extension_for_transformers.transformers.runtime.compile.sub_graph.add_embeddings intel_extension_for_transformers.transformers.runtime.compile.sub_graph.arangewithreciprocal intel_extension_for_transformers.transformers.runtime.compile.sub_graph.attention_mask_length_adaptive_keep_indices intel_extension_for_transformers.transformers.runtime.compile.sub_graph.attention_output_layer_norm_length_adaptive_keep_indices intel_extension_for_transformers.transformers.runtime.compile.sub_graph.attention_reshape intel_extension_for_transformers.transformers.runtime.compile.sub_graph.attentionBlock_AttentionMaskAddReshape intel_extension_for_transformers.transformers.runtime.compile.sub_graph.attentionBlock_ConstantOfShapeWithMul intel_extension_for_transformers.transformers.runtime.compile.sub_graph.attentionBlock_QKVPreReshape intel_extension_for_transformers.transformers.runtime.compile.sub_graph.attentionBlock_QKVReshape intel_extension_for_transformers.transformers.runtime.compile.sub_graph.attentionBlock_WeightReshapeTo4D intel_extension_for_transformers.transformers.runtime.compile.sub_graph.cast_to intel_extension_for_transformers.transformers.runtime.compile.sub_graph.collect_quant_info intel_extension_for_transformers.transformers.runtime.compile.sub_graph.conv_reshape intel_extension_for_transformers.transformers.runtime.compile.sub_graph.decoder_attn_reshape intel_extension_for_transformers.transformers.runtime.compile.sub_graph.einsumwitharange intel_extension_for_transformers.transformers.runtime.compile.sub_graph.embeddingbag intel_extension_for_transformers.transformers.runtime.compile.sub_graph.embeddings_to_2d_before_inner_product intel_extension_for_transformers.transformers.runtime.compile.sub_graph.gelu intel_extension_for_transformers.transformers.runtime.compile.sub_graph.generate_sequence intel_extension_for_transformers.transformers.runtime.compile.sub_graph.InnerproductReshapeFusion intel_extension_for_transformers.transformers.runtime.compile.sub_graph.innerproductwithbiasgelu intel_extension_for_transformers.transformers.runtime.compile.sub_graph.innerproductwithslice intel_extension_for_transformers.transformers.runtime.compile.sub_graph.innerproductwithswish intel_extension_for_transformers.transformers.runtime.compile.sub_graph.input_data intel_extension_for_transformers.transformers.runtime.compile.sub_graph.input_file intel_extension_for_transformers.transformers.runtime.compile.sub_graph.insert_bf16_node intel_extension_for_transformers.transformers.runtime.compile.sub_graph.insert_quant_node intel_extension_for_transformers.transformers.runtime.compile.sub_graph.int8_bf16_mixed_precision_checker intel_extension_for_transformers.transformers.runtime.compile.sub_graph.interact_features intel_extension_for_transformers.transformers.runtime.compile.sub_graph.last_layer_shape intel_extension_for_transformers.transformers.runtime.compile.sub_graph.layer_norm intel_extension_for_transformers.transformers.runtime.compile.sub_graph.layer_norm_with_reduce_mean intel_extension_for_transformers.transformers.runtime.compile.sub_graph.layer_norm_with_transpose intel_extension_for_transformers.transformers.runtime.compile.sub_graph.llama_embeding intel_extension_for_transformers.transformers.runtime.compile.sub_graph.llama_matmulwithtranspose intel_extension_for_transformers.transformers.runtime.compile.sub_graph.llama_postprocess intel_extension_for_transformers.transformers.runtime.compile.sub_graph.llama_rotary_pos_emb intel_extension_for_transformers.transformers.runtime.compile.sub_graph.lower_all_tuples intel_extension_for_transformers.transformers.runtime.compile.sub_graph.matmul_with_bias intel_extension_for_transformers.transformers.runtime.compile.sub_graph.matmul_with_bias_add intel_extension_for_transformers.transformers.runtime.compile.sub_graph.matmul_with_bias_gelu intel_extension_for_transformers.transformers.runtime.compile.sub_graph.matmul_with_bias_relu intel_extension_for_transformers.transformers.runtime.compile.sub_graph.matmul_with_bias_sigmoid intel_extension_for_transformers.transformers.runtime.compile.sub_graph.matmul_with_bias_tanh intel_extension_for_transformers.transformers.runtime.compile.sub_graph.matmul_with_bias_unsqueeze intel_extension_for_transformers.transformers.runtime.compile.sub_graph.matmul_with_transpose intel_extension_for_transformers.transformers.runtime.compile.sub_graph.matmul_with_transpose_scale_add intel_extension_for_transformers.transformers.runtime.compile.sub_graph.merged_embeddingbag intel_extension_for_transformers.transformers.runtime.compile.sub_graph.neox_reorder_change intel_extension_for_transformers.transformers.runtime.compile.sub_graph.neox_rotary_pos_emb intel_extension_for_transformers.transformers.runtime.compile.sub_graph.operator_adaptor intel_extension_for_transformers.transformers.runtime.compile.sub_graph.output_data intel_extension_for_transformers.transformers.runtime.compile.sub_graph.padding_sequence intel_extension_for_transformers.transformers.runtime.compile.sub_graph.pattern intel_extension_for_transformers.transformers.runtime.compile.sub_graph.position_embeddings intel_extension_for_transformers.transformers.runtime.compile.sub_graph.position_embeddings_v1 intel_extension_for_transformers.transformers.runtime.compile.sub_graph.qkv_merge intel_extension_for_transformers.transformers.runtime.compile.sub_graph.qkv_reshape intel_extension_for_transformers.transformers.runtime.compile.sub_graph.quant_gather_to_bf16 intel_extension_for_transformers.transformers.runtime.compile.sub_graph.quantize_fusion intel_extension_for_transformers.transformers.runtime.compile.sub_graph.quantized_graph_dtype_refactor intel_extension_for_transformers.transformers.runtime.compile.sub_graph.remove_constant_op intel_extension_for_transformers.transformers.runtime.compile.sub_graph.remove_last_view intel_extension_for_transformers.transformers.runtime.compile.sub_graph.remove_range intel_extension_for_transformers.transformers.runtime.compile.sub_graph.remove_unused_operator intel_extension_for_transformers.transformers.runtime.compile.sub_graph.remove_zeros intel_extension_for_transformers.transformers.runtime.compile.sub_graph.removeslice intel_extension_for_transformers.transformers.runtime.compile.sub_graph.reshape_after_restore_hidden_states intel_extension_for_transformers.transformers.runtime.compile.sub_graph.reshape_before_and_after_attention_out_layer_norm_gather_elements intel_extension_for_transformers.transformers.runtime.compile.sub_graph.reshape_before_restore_hidden_states intel_extension_for_transformers.transformers.runtime.compile.sub_graph.reshape_fusion intel_extension_for_transformers.transformers.runtime.compile.sub_graph.restore_hidden_states_in_length_adaptive_update_indices intel_extension_for_transformers.transformers.runtime.compile.sub_graph.rms_norm intel_extension_for_transformers.transformers.runtime.compile.sub_graph.rotary_pos_emb intel_extension_for_transformers.transformers.runtime.compile.sub_graph.slicemask intel_extension_for_transformers.transformers.runtime.compile.sub_graph.stableDiffusion_bf16Convert intel_extension_for_transformers.transformers.runtime.compile.sub_graph.stableDiffusion_collectQDQInfo intel_extension_for_transformers.transformers.runtime.compile.sub_graph.stableDiffusion_ExplicitNHWCTranspose intel_extension_for_transformers.transformers.runtime.compile.sub_graph.stableDiffusion_ExplicitNHWCTransposeQAT intel_extension_for_transformers.transformers.runtime.compile.sub_graph.stableDiffusion_insertQuantNode intel_extension_for_transformers.transformers.runtime.compile.sub_graph.stableDiffusion_MHAReshape intel_extension_for_transformers.transformers.runtime.compile.sub_graph.stableDiffusion_QuantizeFusion intel_extension_for_transformers.transformers.runtime.compile.sub_graph.stableDiffusion_ReshapeFusion intel_extension_for_transformers.transformers.runtime.compile.sub_graph.start_end_logits intel_extension_for_transformers.transformers.runtime.compile.sub_graph.subgraph_matcher intel_extension_for_transformers.transformers.runtime.compile.sub_graph.textEncdoer_word_embedding intel_extension_for_transformers.transformers.runtime.compile.sub_graph.textEncoder_AttentionMaskAddReshape intel_extension_for_transformers.transformers.runtime.compile.sub_graph.textEncoder_AttentionReshape intel_extension_for_transformers.transformers.runtime.compile.sub_graph.textEncoder_causal_attention_mask intel_extension_for_transformers.transformers.runtime.compile.sub_graph.textEncoder_KVReshape intel_extension_for_transformers.transformers.runtime.compile.sub_graph.textEncoder_MulReshape intel_extension_for_transformers.transformers.runtime.compile.sub_graph.textEncoder_QReshape intel_extension_for_transformers.transformers.runtime.compile.sub_graph.textEncoder_SoftmaxReshape intel_extension_for_transformers.transformers.runtime.compile.sub_graph.token_type_embeddings intel_extension_for_transformers.transformers.runtime.compile.sub_graph.token_type_embeddings_v1 intel_extension_for_transformers.transformers.runtime.compile.sub_graph.torch_embedding intel_extension_for_transformers.transformers.runtime.compile.sub_graph.torch_ip_insert_bias intel_extension_for_transformers.transformers.runtime.compile.sub_graph.torch_unpack_baddbmm intel_extension_for_transformers.transformers.runtime.compile.sub_graph.torchinsertbf16node intel_extension_for_transformers.transformers.runtime.compile.sub_graph.torchpaddingsquence intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transformer2Dmodel_AttentionMaskAddReshape intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transformer2Dmodel_ConstantOfShapeWithMul intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transformer2Dmodel_encoderHiddenStatesReshape intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transformer2Dmodel_FFNSlice intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transformer2Dmodel_FFNSlice_1 intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transformer2Dmodel_getSampleBatch intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transformer2Dmodel_QKVPreReshape intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transformer2Dmodel_QKVReshape intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transformer2Dmodel_QKVReshape4D intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transformer2Dmodel_sampleSlice intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transpose_batch_matmul intel_extension_for_transformers.transformers.runtime.compile.sub_graph.word_embeddings intel_extension_for_transformers.transformers.runtime.compile.tf_utils intel_extension_for_transformers.transformers.runtime.compile.torch_utils intel_extension_for_transformers.transformers.trainer intel_extension_for_transformers.transformers.utils intel_extension_for_transformers.transformers.utils.config intel_extension_for_transformers.transformers.utils.get_throughput intel_extension_for_transformers.transformers.utils.metrics intel_extension_for_transformers.transformers.utils.objectives intel_extension_for_transformers.transformers.utils.utility main_eval_only main_parse_and_eval models.backbone models.detr models.detr_multi models.matcher models.position_encoding models.segmentation models.transformer text util.box_ops util.misc util.plot_utils util.postprocess utils.data_utils utils.eval_utils

MultiHeadAttenion (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) mutate() (intel_extension_for_transformers.transformers.dynamic.evolution.Evolution method)

N

names_from_input() (in module intel_extension_for_transformers.transformers.runtime.compile.graph_utils) NeoxReorderChange (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.neox_reorder_change) NeoxRoraryPosEmb (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.neox_rotary_pos_emb) neural_engine_bin() (in module intel_extension_for_transformers.transformers.runtime) NLPSeq2SeqTrainer (class in intel_extension_for_transformers.transformers.trainer) NLPTrainer (class in intel_extension_for_transformers.transformers.trainer)

nms() (in module util.postprocess) nms_by_containment() (in module util.postprocess) nms_supercells() (in module util.postprocess) normalize() (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.Quantile method) normalize_str() (in module utils.eval_utils) NormMean (class in intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats) NULL_INSTANCE (C macro)

O

Objective (class in intel_extension_for_transformers.transformers.utils.objectives) objects_to_cells() (in module util.postprocess) objects_to_table_structures() (in module util.postprocess) on_after_eval() (intel_extension_for_transformers.transformers.pruner.pruning.Pruning method) on_after_optimizer_step() (intel_extension_for_transformers.transformers.pruner.pruning.Pruning method) on_before_eval() (intel_extension_for_transformers.transformers.pruner.pruning.Pruning method) on_before_optimizer_step() (intel_extension_for_transformers.transformers.pruner.pruning.Pruning method) on_epoch_begin() (intel_extension_for_transformers.transformers.pruner.pruning.Pruning method) on_epoch_end() (intel_extension_for_transformers.transformers.pruner.pruning.Pruning method) on_step_begin() (intel_extension_for_transformers.transformers.pruner.pruning.Pruning method) on_step_end() (intel_extension_for_transformers.transformers.pruner.pruning.Pruning method) on_train_begin() (intel_extension_for_transformers.transformers.pruner.pruning.Pruning method) on_train_end() (intel_extension_for_transformers.transformers.pruner.pruning.Pruning method) Onehot (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) OneHot (class in intel_extension_for_transformers.transformers.runtime.compile.ops.one_hot)

onnx_extract_operator() (in module intel_extension_for_transformers.transformers.runtime.compile.onnx_utils) ONNXExtractor (class in intel_extension_for_transformers.transformers.runtime.compile.extractors.onnx_extractor) ONNXINPUT (class in intel_extension_for_transformers.transformers.runtime.compile.ops.onnx_input) OpAny (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) Operator (class in intel_extension_for_transformers.transformers.runtime.compile.ops.op) operator_registry() (in module intel_extension_for_transformers.transformers.runtime.compile.ops.op) OperatorAdaptor (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.operator_adaptor) optimize() (intel_extension_for_transformers.transformers.runtime.compile.optimizer.Optimizer method) optimize_model() (in module intel_extension_for_transformers.neural_chat.chatbot) OptimizeDataset (class in intel_extension_for_transformers.transformers.runtime.compile.ops.optimize_dataset) OptimizedModel (class in intel_extension_for_transformers.transformers.modeling.model) Optimizer (class in intel_extension_for_transformers.transformers.runtime.compile.optimizer) orchestrate_optimizations() (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) Output (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) OutputData (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.output_data) overlaps() (in module util.postprocess)

P

Pack (class in intel_extension_for_transformers.transformers.runtime.compile.ops.pack) PackagePositionEmbedding (class in intel_extension_for_transformers.transformers.runtime.compile.ops.pos_embed) PaddingSequence (class in intel_extension_for_transformers.transformers.runtime.compile.ops.padding_sequence) (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.padding_sequence) pareto_frontier() (intel_extension_for_transformers.transformers.dynamic.evolution.Evolution method) parse_args() (in module gaudi_spawn) parse_multi_choice_response() (in module utils.eval_utils) parse_open_response() (in module utils.eval_utils) Pattern (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.pattern) pattern_mapping() (in module intel_extension_for_transformers.transformers.runtime.compile.graph_utils) pattern_mapping_conf_validation() (in module intel_extension_for_transformers.transformers.runtime.compile.graph_utils) pattern_registry() (in module intel_extension_for_transformers.transformers.runtime.compile.sub_graph.pattern) performance() (intel_extension_for_transformers.transformers.utils.objectives.Objective static method) Placeholder (class in intel_extension_for_transformers.transformers.runtime.compile.ops.placeholder) plot_logs() (in module util.plot_utils) PositionEmbeddingLearned (class in models.position_encoding) PositionEmbeddings (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.position_embeddings) PositionEmbeddingSine (class in models.position_encoding) PositionEmbeddingsV1 (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.position_embeddings_v1) PositionIds (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) post_init_cpu() (intel_extension_for_transformers.transformers.utils.config.ITREXQuantizationConfigMixin method)

post_init_gptq() (intel_extension_for_transformers.transformers.utils.config.GPTQConfig method) post_init_runtime() (intel_extension_for_transformers.transformers.utils.config.ITREXQuantizationConfigMixin method) post_init_xpu() (intel_extension_for_transformers.transformers.utils.config.ITREXQuantizationConfigMixin method) PostProcess (class in models.detr) (class in models.detr_multi) PostProcessPanoptic (class in models.segmentation) Pow (class in intel_extension_for_transformers.transformers.runtime.compile.ops.pow) prepare_inputs_for_generation() (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertForMaskedLM method) (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertLMHeadModel method) (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaForCausalLM method) preprocess_model() (in module intel_extension_for_transformers.transformers.benchmark) Provider (class in intel_extension_for_transformers.transformers.config) prune() (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) prune_heads() (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertAttention method) (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaAttention method) pruner_info (intel_extension_for_transformers.transformers.pruner.pruning.Pruning attribute) pruners (intel_extension_for_transformers.transformers.pruner.pruning.Pruning attribute) PrunerV2 (class in intel_extension_for_transformers.transformers.config) Pruning (class in intel_extension_for_transformers.transformers.pruner.pruning) pull_key_prefix() (in module intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats) push_key_prefix() (in module intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats)

Q

QKVMerge (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.qkv_merge) QKVReshape (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.qkv_reshape) QLinearAdd (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) QLinearMatMul (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) QLinearMul (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) quant_info_init() (in module intel_extension_for_transformers.transformers.runtime.compile.graph_utils) QuantAwareTrainingConfig (class in intel_extension_for_transformers.transformers.utils.config) Quantile (class in intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats)

QuantizationMethod (class in intel_extension_for_transformers.transformers.utils.config) Quantize (class in intel_extension_for_transformers.transformers.runtime.compile.ops.quantize_linear) quantize() (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) QuantizedGraphDtypeCheck (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.quantized_graph_dtype_refactor) QuantizedMatMulWithBiasAndDequantize (class in intel_extension_for_transformers.transformers.runtime.compile.ops.quantized_matmul_with_bias_and_dequantize) QuantizeFusion (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.quantize_fusion) QuantizeLinear (class in intel_extension_for_transformers.transformers.runtime.compile.ops.quantize_linear) QuantizeV2 (class in intel_extension_for_transformers.transformers.runtime.compile.ops.quantize_v2)

R

Range (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) RealDiv (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) Reciprocal (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) recursive_copy() (in module intel_extension_for_transformers.neural_chat.tools.rome.utils.nethook) reduce_dict() (in module util.misc) ReduceMean (class in intel_extension_for_transformers.transformers.runtime.compile.ops.reduce_mean) ReduceSum (class in intel_extension_for_transformers.transformers.runtime.compile.ops.reduce_sum) refactor_batch_size() (in module intel_extension_for_transformers.transformers.benchmark) refine_columns() (in module util.postprocess) refine_rows() (in module util.postprocess) refine_table_structures() (in module util.postprocess) register_conv_template() (in module conversation) Relu (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) remove_environ_info_item() (in module intel_extension_for_transformers.transformers.runtime.compile.graph_utils) remove_environ_info_items() (in module intel_extension_for_transformers.transformers.runtime.compile.graph_utils) remove_nodes() (intel_extension_for_transformers.transformers.runtime.compile.graph.graph.Graph method) remove_objects_without_content() (in module util.postprocess) remove_supercell_overlap() (in module util.postprocess) RemoveConstantOP (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.remove_constant_op) RemoveLastView (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.remove_last_view) RemoveRange (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.remove_range) RemoveSlice (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.removeslice) RemoveUnusedOperator (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.remove_unused_operator) RemoveZeros (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.remove_zeros) rename_node() (intel_extension_for_transformers.transformers.runtime.compile.graph.graph.Graph method) Reorder (class in intel_extension_for_transformers.transformers.runtime.compile.ops.reorder) Repeat (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) replace_module() (in module intel_extension_for_transformers.neural_chat.tools.rome.utils.nethook) Reshape (class in intel_extension_for_transformers.transformers.runtime.compile.ops.reshape) ReshapeAfterRestoreHiddenStates (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.reshape_after_restore_hidden_states) ReshapeBeforeAndAfterAttentionOutLayerNormGatherElements (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.reshape_before_and_after_attention_out_layer_norm_gather_elements) ReshapeBeforeRestoreHiddenStates (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.reshape_before_restore_hidden_states) ReshapeFusion (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.reshape_fusion) Resize (class in intel_extension_for_transformers.transformers.runtime.compile.ops.resize) resnet101() (in module intel_extension_for_transformers.neural_chat.pipeline.plugins.video.face_animation.src.face3d.models.networks)

resnet152() (in module intel_extension_for_transformers.neural_chat.pipeline.plugins.video.face_animation.src.face3d.models.networks) resnet18() (in module intel_extension_for_transformers.neural_chat.pipeline.plugins.video.face_animation.src.face3d.models.networks) resnet34() (in module intel_extension_for_transformers.neural_chat.pipeline.plugins.video.face_animation.src.face3d.models.networks) resnet50() (in module intel_extension_for_transformers.neural_chat.pipeline.plugins.video.face_animation.src.face3d.models.networks) resnext101_32x8d() (in module intel_extension_for_transformers.neural_chat.pipeline.plugins.video.face_animation.src.face3d.models.networks) resnext50_32x4d() (in module intel_extension_for_transformers.neural_chat.pipeline.plugins.video.face_animation.src.face3d.models.networks) resolve_state_dict() (in module intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats) RestoreHiddenStatesInLengthAdaptive (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.restore_hidden_states_in_length_adaptive_update_indices) RetrievalTypeOptions (class in intel_extension_for_transformers.neural_chat.config) RetrieverAdapter (class in intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.retriever_adapter) RmsNorm (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.rms_norm) RobertaAttention (class in intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic) RobertaClassificationHead (class in intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic) RobertaEmbeddings (class in intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic) RobertaEncoder (class in intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic) RobertaForCausalLM (class in intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic) RobertaForMaskedLM (class in intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic) RobertaForMultipleChoice (class in intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic) RobertaForQuestionAnswering (class in intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic) RobertaForSequenceClassification (class in intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic) RobertaForTokenClassification (class in intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic) RobertaIntermediate (class in intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic) RobertaLayer (class in intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic) RobertaLMHead (class in intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic) RobertaModel (class in intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic) RobertaOutput (class in intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic) RobertaPooler (class in intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic) RobertaPreTrainedModel (class in intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic) RobertaSelfAttention (class in intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic) RobertaSelfOutput (class in intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic) RoraryPosEmb (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.rotary_pos_emb) Rsqrt (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) Rsub (class in intel_extension_for_transformers.transformers.runtime.compile.ops.rsub) RtnConfig (class in intel_extension_for_transformers.transformers.utils.config) run_evolutionary_search() (intel_extension_for_transformers.transformers.trainer.BaseTrainer method)

S

sample_layer_configuration() (in module intel_extension_for_transformers.transformers.dynamic.drop_and_restore_utils) sample_length_configuration() (in module intel_extension_for_transformers.transformers.dynamic.drop_and_restore_utils) sample_portion() (in module intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats) save() (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.Stat method) (intel_extension_for_transformers.transformers.runtime.compile.graph.graph.Graph method) save_cached_state() (in module intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats) save_jsonl() (in module utils.data_utils) save_population() (intel_extension_for_transformers.transformers.dynamic.evolution.Evolution method) save_pretrained() (intel_extension_for_transformers.transformers.utils.config.ITREXQuantizationConfigMixin method) save_store() (intel_extension_for_transformers.transformers.dynamic.evolution.Evolution method) ScatterElements (class in intel_extension_for_transformers.transformers.runtime.compile.ops.scatter_elements) search_kwargs (intel_extension_for_transformers.langchain.langchain_community.retrievers.child_parent_retriever.ChildParentRetriever attribute) search_pattern() (in module intel_extension_for_transformers.transformers.runtime.compile.graph_utils) search_straight_pattern() (in module intel_extension_for_transformers.transformers.runtime.compile.graph_utils) search_type (intel_extension_for_transformers.langchain.langchain_community.retrievers.child_parent_retriever.ChildParentRetriever attribute) SearchType (class in intel_extension_for_transformers.langchain.langchain_community.retrievers.child_parent_retriever) SecondMoment (class in intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats) SeparatorStyle (class in conversation) SequenceLength (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) set_attr() (intel_extension_for_transformers.transformers.runtime.compile.ops.all.All method) (intel_extension_for_transformers.transformers.runtime.compile.ops.assert.Assert method) (intel_extension_for_transformers.transformers.runtime.compile.ops.batch_matmul.BatchMatMul method) (intel_extension_for_transformers.transformers.runtime.compile.ops.batch_matmul_v2.BatchMatMulV2 method) (intel_extension_for_transformers.transformers.runtime.compile.ops.bias_add.BiasAdd method) (intel_extension_for_transformers.transformers.runtime.compile.ops.cast.Cast method) (intel_extension_for_transformers.transformers.runtime.compile.ops.concat.Concat method) (intel_extension_for_transformers.transformers.runtime.compile.ops.conv.Conv method) (intel_extension_for_transformers.transformers.runtime.compile.ops.cos.Cos method) (intel_extension_for_transformers.transformers.runtime.compile.ops.expand_dims.ExpandDims method) (intel_extension_for_transformers.transformers.runtime.compile.ops.fused_batch_norm_v3.FusedBatchNormV3 method) (intel_extension_for_transformers.transformers.runtime.compile.ops.fused_gemm.FusedGemm method) (intel_extension_for_transformers.transformers.runtime.compile.ops.fused_matmul.FusedMatMul method) (intel_extension_for_transformers.transformers.runtime.compile.ops.gather.Gather method) (intel_extension_for_transformers.transformers.runtime.compile.ops.gather.GatherV2 method) (intel_extension_for_transformers.transformers.runtime.compile.ops.gather_elements.GatherElements method) (intel_extension_for_transformers.transformers.runtime.compile.ops.gelu.Gelu method) (intel_extension_for_transformers.transformers.runtime.compile.ops.gemm.Gemm method) (intel_extension_for_transformers.transformers.runtime.compile.ops.iterator_get_next.IteratorGetNext method) (intel_extension_for_transformers.transformers.runtime.compile.ops.iterator_v2.IteratorV2 method) (intel_extension_for_transformers.transformers.runtime.compile.ops.layer_normalization.LayerNorm method) (intel_extension_for_transformers.transformers.runtime.compile.ops.layer_normalization.LayerNormalization method) (intel_extension_for_transformers.transformers.runtime.compile.ops.log_softmax.LogSoftmax method) (intel_extension_for_transformers.transformers.runtime.compile.ops.map_and_batch_dataset.MapAndBatchDataset method) (intel_extension_for_transformers.transformers.runtime.compile.ops.matmul.MatMul method) (intel_extension_for_transformers.transformers.runtime.compile.ops.mean.Mean method) (intel_extension_for_transformers.transformers.runtime.compile.ops.model_dataset.ModelDataset method) (intel_extension_for_transformers.transformers.runtime.compile.ops.one_hot.OneHot method) (intel_extension_for_transformers.transformers.runtime.compile.ops.op.Operator method) (intel_extension_for_transformers.transformers.runtime.compile.ops.optimize_dataset.OptimizeDataset method) (intel_extension_for_transformers.transformers.runtime.compile.ops.pack.Pack method) (intel_extension_for_transformers.transformers.runtime.compile.ops.padding_sequence.PaddingSequence method) (intel_extension_for_transformers.transformers.runtime.compile.ops.placeholder.Placeholder method) (intel_extension_for_transformers.transformers.runtime.compile.ops.pos_embed.PackagePositionEmbedding method) (intel_extension_for_transformers.transformers.runtime.compile.ops.pow.Pow method) (intel_extension_for_transformers.transformers.runtime.compile.ops.quantize_linear.Quantize method) (intel_extension_for_transformers.transformers.runtime.compile.ops.quantize_linear.QuantizeLinear method) (intel_extension_for_transformers.transformers.runtime.compile.ops.quantize_v2.QuantizeV2 method) (intel_extension_for_transformers.transformers.runtime.compile.ops.quantized_matmul_with_bias_and_dequantize.QuantizedMatMulWithBiasAndDequantize method) (intel_extension_for_transformers.transformers.runtime.compile.ops.reduce_mean.ReduceMean method) (intel_extension_for_transformers.transformers.runtime.compile.ops.reduce_sum.ReduceSum method) (intel_extension_for_transformers.transformers.runtime.compile.ops.reorder.Reorder method) (intel_extension_for_transformers.transformers.runtime.compile.ops.reshape.Reshape method) (intel_extension_for_transformers.transformers.runtime.compile.ops.resize.Resize method) (intel_extension_for_transformers.transformers.runtime.compile.ops.rsub.Rsub method) (intel_extension_for_transformers.transformers.runtime.compile.ops.scatter_elements.ScatterElements method) (intel_extension_for_transformers.transformers.runtime.compile.ops.shape.Shape method) (intel_extension_for_transformers.transformers.runtime.compile.ops.sin.Sin method) (intel_extension_for_transformers.transformers.runtime.compile.ops.size.Size method) (intel_extension_for_transformers.transformers.runtime.compile.ops.slice_position_ids.SlicePositionIds method) (intel_extension_for_transformers.transformers.runtime.compile.ops.softmax.Softmax method) (intel_extension_for_transformers.transformers.runtime.compile.ops.split.Split method) (intel_extension_for_transformers.transformers.runtime.compile.ops.squeeze.Squeeze method) (intel_extension_for_transformers.transformers.runtime.compile.ops.strided_slice.StridedSlice method) (intel_extension_for_transformers.transformers.runtime.compile.ops.top_k.TopK method) (intel_extension_for_transformers.transformers.runtime.compile.ops.transpose.Transpose method) (intel_extension_for_transformers.transformers.runtime.compile.ops.unpack.Unpack method) (intel_extension_for_transformers.transformers.runtime.compile.ops.unsqueeze.Unsqueeze method) (intel_extension_for_transformers.transformers.runtime.compile.ops.view.View method) (intel_extension_for_transformers.transformers.runtime.compile.ops.where.Where method)

set_autocast() (in module intel_extension_for_transformers.transformers.runtime.compile.graph_utils) set_dynamic_config() (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) set_environ_var() (in module intel_extension_for_transformers.transformers.runtime.compile.graph_utils) set_environ_vars() (in module intel_extension_for_transformers.transformers.runtime.compile.graph_utils) set_input_embeddings() (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertModel method) (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaModel method) set_length_config() (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertModel method) (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaModel method) set_lower_constraint() (intel_extension_for_transformers.transformers.dynamic.evolution.Evolution method) set_output_attentions() (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertModel method) (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaModel method) set_output_embeddings() (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertForMaskedLM method) (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertForPreTraining method) (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertLMHeadModel method) (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaForCausalLM method) (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaForMaskedLM method) set_requires_grad() (in module intel_extension_for_transformers.neural_chat.tools.rome.utils.nethook) set_system_message() (conversation.Conversation method) set_upper_constraint() (intel_extension_for_transformers.transformers.dynamic.evolution.Evolution method) SetCriterion (class in models.detr) (class in models.detr_multi) setup_for_distributed() (in module util.misc) Shape (class in intel_extension_for_transformers.transformers.runtime.compile.ops.shape) Sigmoid (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) sigmoid_focal_loss() (in module models.segmentation) Silu (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) similarity (intel_extension_for_transformers.langchain.langchain_community.retrievers.child_parent_retriever.SearchType attribute) Sin (class in intel_extension_for_transformers.transformers.runtime.compile.ops.sin) Size (class in intel_extension_for_transformers.transformers.runtime.compile.ops.size) SliceMask (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.slicemask) SlicePositionIds (class in intel_extension_for_transformers.transformers.runtime.compile.ops.slice_position_ids) slot_into_containers() (in module util.postprocess) SmoothedValue (class in util.misc) SmoothQuantConfig (class in intel_extension_for_transformers.transformers.utils.config) Softmax (class in intel_extension_for_transformers.transformers.runtime.compile.ops.softmax) sort_objects_by_score() (in module util.postprocess) sort_objects_left_to_right() (in module util.postprocess) sort_objects_top_to_bottom() (in module util.postprocess) Split (class in intel_extension_for_transformers.transformers.runtime.compile.ops.split) Sqrt (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) Square (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) SquaredDifference (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) Squeeze (class in intel_extension_for_transformers.transformers.runtime.compile.ops.squeeze) StableDiffusion_bf16Convert (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.stableDiffusion_bf16Convert) StableDiffusion_CollectQuantInfo (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.stableDiffusion_collectQDQInfo) StableDiffusion_InsertQuantNode (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.stableDiffusion_insertQuantNode) StableDiffusion_MHAReshape (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.stableDiffusion_MHAReshape) StableDiffusion_QuantizeFusion (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.stableDiffusion_QuantizeFusion) StableDiffusion_ReshapeFusion (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.stableDiffusion_ReshapeFusion) StableDiffusionInstructPix2PixPipeline (class in intel_extension_for_transformers.neural_chat.pipeline.plugins.image2image.instructpix2pix_pipeline) Stack (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) start_pipeline() (in module intel_extension_for_transformers.transformers.runtime.compile.compile) StartEndLogits (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.start_end_logits) Stat (class in intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats) state_dict() (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.Bincount method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.CombinedStat method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.Covariance method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.CrossCovariance method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.CrossIoU method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.History method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.IoU method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.Mean method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.Quantile method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.SecondMoment method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.Stat method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.Variance method) StaticQuantConfig (class in intel_extension_for_transformers.transformers.utils.config) StopForward StopGradient (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) store2str() (in module intel_extension_for_transformers.transformers.dynamic.evolution) str2list() (in module intel_extension_for_transformers.transformers.runtime.compile.graph_utils) StridedSlice (class in intel_extension_for_transformers.transformers.runtime.compile.ops.strided_slice) SubGraphMatcher (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.subgraph_matcher) subsequence() (in module intel_extension_for_transformers.neural_chat.tools.rome.utils.nethook) synchronize_between_processes() (util.misc.SmoothedValue method)

T

table_structure_to_cells() (in module util.postprocess) tally() (in module intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats) Tanh (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) Tensor (class in intel_extension_for_transformers.transformers.runtime.compile.ops.tensor) TensorflowExtractor (class in intel_extension_for_transformers.transformers.runtime.compile.extractors.tf_extractor) TensorSliceDataset (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) TeqConfig (class in intel_extension_for_transformers.transformers.utils.config) text module text_to_sequence() (in module text) TextEncoder_AttentionMaskAddReshape (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.textEncoder_AttentionMaskAddReshape) TextEncoder_AttentionReshape (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.textEncoder_AttentionReshape) TextEncoder_CasualAttentionMask (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.textEncoder_causal_attention_mask) TextEncoder_KVReshape (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.textEncoder_KVReshape) TextEncoder_MulReshape (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.textEncoder_MulReshape) TextEncoder_QReshape (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.textEncoder_QReshape) TextEncoder_SoftmaxReshape (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.textEncoder_SoftmaxReshape) TextEncoder_WordEmbedding (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.textEncdoer_word_embedding) TF_DTYPE_ID (in module intel_extension_for_transformers.transformers.runtime.compile.tf_utils) tf_extract_operator() (in module intel_extension_for_transformers.transformers.runtime.compile.tf_utils) Tile (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) to_() (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.Bincount method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.CombinedStat method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.Covariance method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.CrossCovariance method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.CrossIoU method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.History method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.IoU method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.Mean method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.Quantile method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.SecondMoment method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.Stat method) (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.Variance method) to_diff_dict() (intel_extension_for_transformers.transformers.utils.config.AutoRoundConfig method) (intel_extension_for_transformers.transformers.utils.config.AwqConfig method) (intel_extension_for_transformers.transformers.utils.config.GPTQConfig method) (intel_extension_for_transformers.transformers.utils.config.RtnConfig method) (intel_extension_for_transformers.transformers.utils.config.TeqConfig method)

to_gradio_chatbot() (conversation.Conversation method) to_json_file() (intel_extension_for_transformers.transformers.utils.config.ITREXQuantizationConfigMixin method) to_openai_api_messages() (conversation.Conversation method) TokenTypeEmbeddings (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.token_type_embeddings) TokenTypeEmbeddingsV1 (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.token_type_embeddings_v1) TokenTypeIds (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) TopK (class in intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats) (class in intel_extension_for_transformers.transformers.runtime.compile.ops.top_k) topk() (intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats.TopK method) torch_extract_operator() (in module intel_extension_for_transformers.transformers.runtime.compile.torch_utils) TorchEmbedding (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.torch_embedding) TorchExtractor (class in intel_extension_for_transformers.transformers.runtime.compile.extractors.torch_extractor) TorchInnerProductInsertBias (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.torch_ip_insert_bias) TorchInsertBF16Node (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.quant_gather_to_bf16) (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.torchinsertbf16node) TorchPaddingSequence (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.torchpaddingsquence) TorchUnpackBaddbmm (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.torch_unpack_baddbmm) Trace (class in intel_extension_for_transformers.neural_chat.tools.rome.utils.nethook) TraceDict (class in intel_extension_for_transformers.neural_chat.tools.rome.utils.nethook) train() (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) training_step() (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) training_step_length_adaptive() (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) Transformer2Dmodel_AttentionMaskAddReshape (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transformer2Dmodel_AttentionMaskAddReshape) Transformer2Dmodel_ConstantOfShapeWithMul (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transformer2Dmodel_ConstantOfShapeWithMul) Transformer2Dmodel_EncoderHiddenStatesReshape (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transformer2Dmodel_encoderHiddenStatesReshape) Transformer2Dmodel_FFNInputSlice (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transformer2Dmodel_FFNSlice) Transformer2Dmodel_FFNInputSlice_1 (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transformer2Dmodel_FFNSlice_1) Transformer2Dmodel_GetSampleBatch (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transformer2Dmodel_getSampleBatch) Transformer2Dmodel_QKVPreReshape (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transformer2Dmodel_QKVPreReshape) Transformer2Dmodel_QKVReshape (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transformer2Dmodel_QKVReshape) Transformer2Dmodel_QKVReshapeTo4D (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transformer2Dmodel_QKVReshape4D) Transformer2Dmodel_SampleSlice (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transformer2Dmodel_sampleSlice) Transpose (class in intel_extension_for_transformers.transformers.runtime.compile.ops.transpose) transpose_for_scores() (intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic.BertSelfAttention method) (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaSelfAttention method) transpose_mode_int8() (intel_extension_for_transformers.transformers.runtime.compile.graph.graph.Graph method) TransposeBatchMatMul (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops) (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.transpose_batch_matmul)

U

unbox_numpy_null() (in module intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats) Unpack (class in intel_extension_for_transformers.transformers.runtime.compile.ops.unpack) Unsqueeze (class in intel_extension_for_transformers.transformers.runtime.compile.ops.unsqueeze) update() (intel_extension_for_transformers.transformers.utils.config.ITREXQuantizationConfigMixin method) update_config() (intel_extension_for_transformers.transformers.pruner.pruning.Pruning method) update_keys_to_ignore() (intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic.RobertaPreTrainedModel method) update_last_message() (conversation.Conversation method) util.box_ops module

util.misc module util.plot_utils module util.postprocess module utils.data_utils module utils.eval_utils module

V

Variance (class in intel_extension_for_transformers.neural_chat.tools.rome.utils.runningstats)

View (class in intel_extension_for_transformers.transformers.runtime.compile.ops.view)

W

warn() (in module intel_extension_for_transformers.transformers.runtime.compile.logger) warning() (in module intel_extension_for_transformers.transformers.runtime.compile.logger) weight_optimization() (intel_extension_for_transformers.transformers.runtime.compile.optimizer.Optimizer method) WeightPruningConfig (class in intel_extension_for_transformers.transformers.config)

Where (class in intel_extension_for_transformers.transformers.runtime.compile.ops.where) wide_resnet101_2() (in module intel_extension_for_transformers.neural_chat.pipeline.plugins.video.face_animation.src.face3d.models.networks) wide_resnet50_2() (in module intel_extension_for_transformers.neural_chat.pipeline.plugins.video.face_animation.src.face3d.models.networks) WordEmbeddings (class in intel_extension_for_transformers.transformers.runtime.compile.sub_graph.word_embeddings)

Z

Zeros (class in intel_extension_for_transformers.transformers.runtime.compile.ops.empty_ops)