Index

_

__call__() (intel_extension_for_transformers.neural_chat.cli.cli_commands.TextVoiceChatExecutor method)

A

Add (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) add_config_item() (intel_extension_for_transformers.llm.runtime.deprecated.compile.graph.graph.Graph method) add_gene() (intel_extension_for_transformers.transformers.dynamic.evolution.Evolution method) AddClsToken (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.add_cls_token) AddEmbeddings (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.add_embeddings) AddV2 (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) All (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.all) app module append_message() (fastchat.conversation.Conversation method) approx_ratio() (in module intel_extension_for_transformers.transformers.dynamic.evolution) Arange (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) ArangewithReciprocal (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.arangewithreciprocal) asr module Assert (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.assert) AttentionBlock_AttentionMaskAddReshape (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.attentionBlock_AttentionMaskAddReshape) AttentionBlock_ConstantOfShapeWithMul (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.attentionBlock_ConstantOfShapeWithMul)

AttentionBlock_QKVPreReshape (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.attentionBlock_QKVPreReshape) AttentionBlock_QKVReshape (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.attentionBlock_QKVReshape) AttentionBlock_WeightReshapeTo4D (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.attentionBlock_WeightReshapeTo4D) AttentionMaskLengthAdaptiveExpandIndices (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.attention_mask_length_adaptive_keep_indices) AttentionOutputLayerNormLengthAdaptiveExpandIndices (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.attention_output_layer_norm_length_adaptive_keep_indices) AttentionReshape (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.attention_reshape) audio2text() (intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.asr.AudioSpeechRecognition method) (intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.asr_chinese.ChineseAudioSpeechRecognition method) AudioLanguageOptions (class in intel_extension_for_transformers.neural_chat.config) AudioSpeechRecognition (class in intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.asr) AugmenterType (class in intel_extension_for_transformers.utils.utils) auto_distil_evaluation_loop() (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) autocast_init() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.graph_utils) AutoCausalLM (class in intel_extension_for_transformers.llm.evaluation.lm_eval.models.huggingface) autodistill() (intel_extension_for_transformers.transformers.optimizer_tf.TFOptimization method) AutoDistillation (class in intel_extension_for_transformers.transformers.mixture.auto_distillation) autodistillation() (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) AutoDistillationConfig (class in intel_extension_for_transformers.transformers.config) AutoSeq2SeqLM (class in intel_extension_for_transformers.llm.evaluation.lm_eval.models.huggingface)

B

BackendOptions (class in intel_extension_for_transformers.neural_chat.config) Baddbmm (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.baddbmm) BaseCommand (class in intel_extension_for_transformers.neural_chat.cli.cli_commands) BaseCommandExecutor (class in intel_extension_for_transformers.neural_chat.cli.base_executor) (class in intel_extension_for_transformers.neural_chat.server.base_executor) BaseModel (class in intel_extension_for_transformers.neural_chat.models.base_model) BaseTrainer (class in intel_extension_for_transformers.transformers.trainer) BasicNAS (class in intel_extension_for_transformers.transformers.nas.basic_nas) BatchMatMul (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.batch_matmul) BatchMatMulV2 (class in intel_extension_for_transformers.llm.runtime.deprecated.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.llm.runtime.deprecated.compile.onnx_utils) BiasAdd (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.bias_add) BinaryAdd (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) bloom_gelu_back() (in module intel_extension_for_transformers.transformers.modeling.bloom.modeling_bloom) bloom_gelu_forward() (in module intel_extension_for_transformers.transformers.modeling.bloom.modeling_bloom) BloomGelu (class in intel_extension_for_transformers.transformers.modeling.bloom.modeling_bloom) bounded_parallel_map() (in module intel_extension_for_transformers.llm.runtime.graph.scripts.convert_llama) build_alibi_tensor() (in module intel_extension_for_transformers.transformers.modeling.bloom.modeling_bloom) build_chatbot() (in module intel_extension_for_transformers.neural_chat.chatbot) build_train_func() (intel_extension_for_transformers.transformers.optimizer_tf.TFOptimization method) builtin_eval_func() (intel_extension_for_transformers.transformers.optimizer_tf.TFOptimization method) (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) bytes_to_unicode() (in module intel_extension_for_transformers.llm.runtime.graph.scripts.convert_bloom) (in module intel_extension_for_transformers.llm.runtime.graph.scripts.convert_chatglm) (in module intel_extension_for_transformers.llm.runtime.graph.scripts.convert_dolly) (in module intel_extension_for_transformers.llm.runtime.graph.scripts.convert_falcon) (in module intel_extension_for_transformers.llm.runtime.graph.scripts.convert_gptj) (in module intel_extension_for_transformers.llm.runtime.graph.scripts.convert_gptneox) (in module intel_extension_for_transformers.llm.runtime.graph.scripts.convert_mpt) (in module intel_extension_for_transformers.llm.runtime.graph.scripts.convert_opt) (in module intel_extension_for_transformers.llm.runtime.graph.scripts.convert_starcoder)

C

Cast (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.cast) CastTo (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.cast_to) change_node_input_tensors() (intel_extension_for_transformers.llm.runtime.deprecated.compile.graph.graph.Graph method) change_node_output_tensors() (intel_extension_for_transformers.llm.runtime.deprecated.compile.graph.graph.Graph method) change_num_name() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.onnx_utils) chat() (intel_extension_for_transformers.neural_chat.models.base_model.BaseModel method) chat_completion module chat_stream() (intel_extension_for_transformers.neural_chat.models.base_model.BaseModel method) Chatbot (class in fastchat.serve.gradio_patch) chatglm_generate_stream() (in module fastchat.serve.serve_chatglm) ChatIO (class in fastchat.serve.inference) check_value() (in module intel_extension_for_transformers.transformers.config) ChineseAudioSpeechRecognition (class in intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.asr_chinese) ChromaRetriever (class in intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.retrieval_chroma) clean_html_all() (in module fastchat.data.clean_sharegpt) CLinear (class in fastchat.serve.compression) cnn_dailymail module CollectQuantInfo (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.collect_quant_info) compile() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.compile) compress() (in module fastchat.serve.compression) CompressionConfig (class in fastchat.serve.compression) compute_loss() (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) Concat (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.concat)

config (intel_extension_for_transformers.neural_chat.cli.cli_commands.TextVoiceChatExecutor attribute) config_file_path (intel_extension_for_transformers.transformers.pruner.pruning.Pruning attribute) Constant (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) ConstantOfShape (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) construct() (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.op.Operator method) construct_node() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.graph_utils) Conv (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.conv) Conversation (class in fastchat.conversation) convert_fullwidth_to_halfwidth() (in module intel_extension_for_transformers.neural_chat.pipeline.plugins.security.safety_checker) convex_hull() (intel_extension_for_transformers.transformers.dynamic.evolution.Evolution method) Convolution (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) ConvReshape (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.conv_reshape) correct_number() (in module inference) Cos (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.cos) CPU_INSTANCE (C macro) create_chat_completion() (in module fastchat.serve.api) create_distillers() (intel_extension_for_transformers.transformers.mixture.auto_distillation.AutoDistillation method) create_optimizer_builtin() (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) 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_speaker_embedding() (intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.tts.TextToSpeech method) create_tf_node() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.tf_utils) Criterion (class in intel_extension_for_transformers.transformers.distillation) crossover() (intel_extension_for_transformers.transformers.dynamic.evolution.Evolution method) CumSum (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops)

D

data_augment() (intel_extension_for_transformers.utils.data_augmentation.DataAugmentation method) DataArguments (class in intel_extension_for_transformers.neural_chat.config) DataAugmentation (class in intel_extension_for_transformers.utils.data_augmentation) DataCollatorForSupervisedDataset (class in cnn_dailymail) (class in intel_extension_for_transformers.llm.evaluation.hf_eval.hf_datasets.cnn_dailymail) debug() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.logger) DecoderAttnReshape (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.decoder_attn_reshape) decompress() (in module fastchat.serve.compression) deep_get() (in module intel_extension_for_transformers.neural_chat.utils.dotdict) deep_set() (in module intel_extension_for_transformers.neural_chat.utils.dotdict) del_environ_var() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.graph_utils) del_environ_vars() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.graph_utils) Dequantize (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) DequantizeLinear (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) DeviceOptions (class in intel_extension_for_transformers.neural_chat.config)

disable_torch_init() (in module fastchat.utils) DispatchMethod (class in fastchat.serve.controller) distill() (intel_extension_for_transformers.transformers.optimizer.NoTrainerOptimizer method) (intel_extension_for_transformers.transformers.optimizer_tf.TFOptimization method) (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) DistillationConfig (class in intel_extension_for_transformers.transformers.config) DistillationCriterionMode (class in intel_extension_for_transformers.transformers.distillation) distributed_init() (in module intel_extension_for_transformers.transformers.utils.utility) (in module intel_extension_for_transformers.transformers.utils.utility_tf) DotDict (class in intel_extension_for_transformers.neural_chat.utils.dotdict) dpo_forward() (intel_extension_for_transformers.transformers.dpo_trainer.DPOTrainer method) dpo_loss() (intel_extension_for_transformers.transformers.dpo_trainer.DPOTrainer method) DPOTrainer (class in intel_extension_for_transformers.transformers.dpo_trainer) dropout_add() (in module intel_extension_for_transformers.transformers.modeling.bloom.modeling_bloom) dump_tensor() (intel_extension_for_transformers.llm.runtime.deprecated.compile.graph.graph.Graph method) DynamicLengthConfig (class in intel_extension_for_transformers.transformers.config)

E

Einsum (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) EinsumwithArange (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.einsumwitharange) EmbeddingBag (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.embeddingbag) EmbeddingsTo2DBeforeInnerProduct (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.embeddings_to_2d_before_inner_product) engine_init() (intel_extension_for_transformers.llm.runtime.deprecated.compile.graph.graph.Graph method) environ_info_init() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.graph_utils) Erf (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) error() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.logger) estimate() (intel_extension_for_transformers.transformers.mixture.auto_distillation.AutoDistillation method) (intel_extension_for_transformers.transformers.nas.basic_nas.BasicNAS method) eval_gpt_review module evaluate() (in module intel_extension_for_transformers.llm.evaluation.lm_code_eval.evaluator) (in module intel_extension_for_transformers.llm.evaluation.lm_eval.evaluator) Evolution (class in intel_extension_for_transformers.transformers.dynamic.evolution) execute() (intel_extension_for_transformers.neural_chat.cli.base_executor.BaseCommandExecutor method) (intel_extension_for_transformers.neural_chat.cli.cli_commands.BaseCommand method) (intel_extension_for_transformers.neural_chat.cli.cli_commands.FinetuingExecutor method) (intel_extension_for_transformers.neural_chat.cli.cli_commands.HelpCommand method) (intel_extension_for_transformers.neural_chat.cli.cli_commands.TextVoiceChatExecutor method), [1] (intel_extension_for_transformers.neural_chat.server.base_executor.BaseCommandExecutor method) (intel_extension_for_transformers.neural_chat.server.neuralchat_client.FinetuningClientExecutor method) (intel_extension_for_transformers.neural_chat.server.neuralchat_client.TextChatClientExecutor method) (intel_extension_for_transformers.neural_chat.server.neuralchat_client.VoiceChatClientExecutor method) (intel_extension_for_transformers.neural_chat.server.neuralchat_server.NeuralChatServerExecutor method) (intel_extension_for_transformers.transformers.nas.basic_nas.BasicNAS method)

Expand (class in intel_extension_for_transformers.llm.runtime.deprecated.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.llm.runtime.deprecated.compile.ops.expand_dims) ExpandIndices (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) ExplicitNHWCTransposeForConv (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.stableDiffusion_ExplicitNHWCTranspose) ExplicitNHWCTransposeForConvQAT (class in intel_extension_for_transformers.llm.runtime.deprecated.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.llm.runtime.deprecated.compile.ops.onnx_input.ONNXINPUT method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.op.Operator method) Extractor (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.extractors.extractor)

F

fastchat module fastchat.client module fastchat.client.api module fastchat.client.test_client module fastchat.constants module fastchat.conversation module fastchat.data module fastchat.data.alpaca-converter module fastchat.data.clean_sharegpt module fastchat.data.hardcoded_questions module fastchat.data.inspect module fastchat.data.merge module fastchat.data.optional_clean module fastchat.data.pretty_json module fastchat.data.sample module fastchat.data.split_long_conversation module fastchat.model module fastchat.model.apply_delta module fastchat.model.apply_lora module fastchat.model.convert_fp16 module fastchat.model.make_delta module fastchat.serve module fastchat.serve.api module fastchat.serve.cacheflow_worker module fastchat.serve.cli module fastchat.serve.compression module fastchat.serve.controller module fastchat.serve.gradio_block_arena_anony module fastchat.serve.gradio_block_arena_named module fastchat.serve.gradio_css module fastchat.serve.gradio_patch module fastchat.serve.gradio_web_server module fastchat.serve.gradio_web_server_multi module fastchat.serve.huggingface_api module fastchat.serve.inference module fastchat.serve.model_worker module fastchat.serve.monkey_patch_non_inplace module fastchat.serve.register_worker module fastchat.serve.serve_chatglm module fastchat.serve.test_message module fastchat.serve.test_throughput module

fastchat.utils module fatal() (in module intel_extension_for_transformers.llm.runtime.deprecated.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.llm.runtime.deprecated.compile.ops.empty_ops) find_class() (intel_extension_for_transformers.llm.runtime.graph.scripts.convert_llama.LazyUnpickler method) find_multifile_paths() (in module intel_extension_for_transformers.llm.runtime.graph.scripts.convert_llama) FinetuingExecutor (class in intel_extension_for_transformers.neural_chat.cli.cli_commands) finetune module finetune_clm module finetune_model() (in module intel_extension_for_transformers.neural_chat.chatbot) finetune_seq2seq module FinetuningArguments (class in intel_extension_for_transformers.neural_chat.config) FinetuningClientExecutor (class in intel_extension_for_transformers.neural_chat.server.neuralchat_client) fit() (intel_extension_for_transformers.transformers.optimizer.Orchestrate_optimizer method) FlashDistillationConfig (class in intel_extension_for_transformers.transformers.config) FlatMapDataset (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) Flatten (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) Floor_divide (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) forward() (in module llama_flash_attn_monkey_patch) (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.gpt_neox.modeling_gpt_neox.GPTNeoXForCausalLM method) (intel_extension_for_transformers.transformers.modeling.gpt_neox.modeling_gpt_neox.GPTNeoXForSequenceClassification method) (intel_extension_for_transformers.transformers.modeling.gpt_neox.modeling_gpt_neox.GPTNeoXModel method) (intel_extension_for_transformers.transformers.modeling.gptj.modeling_gptj.GPTJForCausalLM method) (intel_extension_for_transformers.transformers.modeling.gptj.modeling_gptj.GPTJForQuestionAnswering method) (intel_extension_for_transformers.transformers.modeling.gptj.modeling_gptj.GPTJForSequenceClassification 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_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) (intel_extension_for_transformers.transformers.modeling.opt.modeling_opt.OPTAttention method) (intel_extension_for_transformers.transformers.modeling.opt.modeling_opt.OPTDecoder method) (intel_extension_for_transformers.transformers.modeling.opt.modeling_opt.OPTLearnedPositionalEmbedding method) Frame (class in intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.utils.split_audio) frame_generator() (in module intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.utils.split_audio) from_pretrained() (intel_extension_for_transformers.transformers.modeling.model.OptimizedModel class method) FusedBatchNormV3 (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.fused_batch_norm_v3) FusedGemm (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.fused_gemm) FusedMatMul (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.fused_matmul)

G

Gather (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.gather) GatherElements (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.gather_elements) GatherV2 (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.gather) gaudi_spawn module Gelu (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.gelu) (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.gelu) Gemm (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.gemm) generate_dummy_past_key_values() (in module intel_extension_for_transformers.transformers.utils.utility) generate_webpage_data_from_table module GenerateSequence (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.generate_sequence) get_augmenter_from_type() (in module intel_extension_for_transformers.utils.utils) get_autocast_info() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.graph_utils) get_batch_metrics() (intel_extension_for_transformers.transformers.dpo_trainer.DPOTrainer method) get_checkpoint_files() (in module intel_extension_for_transformers.neural_chat.models.model_utils) get_children() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.onnx_utils) get_chuck_data() (in module intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.indexing.context_utils) get_conv_template() (in module fastchat.conversation) (intel_extension_for_transformers.neural_chat.models.base_model.BaseModel method) get_data_dtype() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.graph_utils) get_default_conv_template() (intel_extension_for_transformers.neural_chat.models.base_model.BaseModel method) (intel_extension_for_transformers.neural_chat.models.llama_model.LlamaModel method) (intel_extension_for_transformers.neural_chat.models.neuralchat_model.NeuralChatModel method) get_environ_info() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.graph_utils) get_example_inputs() (in module intel_extension_for_transformers.transformers.benchmark) get_example_inputs_for_trace() (in module intel_extension_for_transformers.transformers.utils.utility) get_filepath() (in module intel_extension_for_transformers.transformers.utils.utility_tf) get_initializer_children_names() (in module intel_extension_for_transformers.llm.runtime.deprecated.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.llm.runtime.deprecated.compile.logger.Logger method) get_model_adapter() (in module intel_extension_for_transformers.neural_chat.models.base_model) get_model_answer module get_model_fwk_name() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.graph_utils) get_next_node_names() (intel_extension_for_transformers.llm.runtime.deprecated.compile.graph.graph.Graph method)

get_node_by_name() (intel_extension_for_transformers.llm.runtime.deprecated.compile.graph.graph.Graph method) get_node_children_names() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.onnx_utils) get_node_id() (intel_extension_for_transformers.llm.runtime.deprecated.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_pre_node_names() (intel_extension_for_transformers.llm.runtime.deprecated.compile.graph.graph.Graph method) get_prompt() (fastchat.conversation.Conversation method) get_quant_info() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.graph_utils) get_repo_root() (in module intel_extension_for_transformers.neural_chat.models.model_utils) get_sparse_nodes_name() (intel_extension_for_transformers.llm.runtime.deprecated.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.llm.runtime.deprecated.compile.tf_utils) get_tensor_idx() (intel_extension_for_transformers.llm.runtime.deprecated.compile.graph.graph.Graph method) 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) GPTJForCausalLM (class in intel_extension_for_transformers.transformers.modeling.gptj.modeling_gptj) GPTJForQuestionAnswering (class in intel_extension_for_transformers.transformers.modeling.gptj.modeling_gptj) GPTJForSequenceClassification (class in intel_extension_for_transformers.transformers.modeling.gptj.modeling_gptj) GPTJModel (class in intel_extension_for_transformers.transformers.modeling.gptj.modeling_gptj) GPTJPreTrainedModel (class in intel_extension_for_transformers.transformers.modeling.gptj.modeling_gptj) GPTNeoXForCausalLM (class in intel_extension_for_transformers.transformers.modeling.gpt_neox.modeling_gpt_neox) GPTNeoXForSequenceClassification (class in intel_extension_for_transformers.transformers.modeling.gpt_neox.modeling_gpt_neox) GPTNeoXModel (class in intel_extension_for_transformers.transformers.modeling.gpt_neox.modeling_gpt_neox) GPTNeoXPreTrainedModel (class in intel_extension_for_transformers.transformers.modeling.gpt_neox.modeling_gpt_neox) Graph (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.graph.graph) graph_dispatch() (intel_extension_for_transformers.llm.runtime.deprecated.compile.graph.graph.Graph method) graph_init() (intel_extension_for_transformers.llm.runtime.deprecated.compile.graph.graph.Graph method) graph_node_names_details() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.onnx_utils) (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.tf_utils) GroupNorm (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.groupNorm) GroupNormSwish (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.groupNormSwish)

H

handle_quantization() (in module intel_extension_for_transformers.llm.runtime.graph.scripts.convert_llama)

HelpCommand (class in intel_extension_for_transformers.neural_chat.cli.cli_commands)

I

Identity (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) identity_questions() (in module fastchat.data.hardcoded_questions) INCDecoder (class in intel_extension_for_transformers.transformers.modeling.modeling_seq2seq) INCEncoder (class in intel_extension_for_transformers.transformers.modeling.modeling_seq2seq) infer_framework_load_model() (in module intel_extension_for_transformers.transformers.pipeline) inference module inference() (intel_extension_for_transformers.llm.runtime.deprecated.compile.graph.graph.Graph method) info() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.logger) init() (intel_extension_for_transformers.neural_chat.server.neuralchat_server.NeuralChatServerExecutor method) init_by_cfg() (intel_extension_for_transformers.transformers.mixture.auto_distillation.AutoDistillation method) (intel_extension_for_transformers.transformers.nas.basic_nas.BasicNAS method) init_distiller() (intel_extension_for_transformers.transformers.optimizer.NoTrainerOptimizer method) (intel_extension_for_transformers.transformers.optimizer_tf.TFOptimization method) (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) init_prune_config() (intel_extension_for_transformers.transformers.config.PruningConfig method) init_pruner() (intel_extension_for_transformers.transformers.optimizer.NoTrainerOptimizer method) (intel_extension_for_transformers.transformers.optimizer_tf.TFOptimization method) (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) init_quantizer() (intel_extension_for_transformers.transformers.optimizer.NoTrainerOptimizer method) (intel_extension_for_transformers.transformers.optimizer_tf.TFOptimization method) (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) InnerProduct (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) InnerproductReshapeFusion (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.InnerproductReshapeFusion) InnerproductWithBiasGelu (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.innerproductwithbiasgelu) InnerproductwithSlice (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.innerproductwithslice) InnerproductWithSwish (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.innerproductwithswish) Input (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) InputData (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.input_data) InputFile (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.input_file) inquire_config_item() (intel_extension_for_transformers.llm.runtime.deprecated.compile.graph.graph.Graph method) insert_environ_info() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.graph_utils) insert_nodes() (intel_extension_for_transformers.llm.runtime.deprecated.compile.graph.graph.Graph method) insert_pattern() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.graph_utils) insert_quant_info() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.graph_utils) InsertBF16Node (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.insert_bf16_node) InsertQuantNode (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.insert_quant_node) Int8BF16MixedPrecisionChecker (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.int8_bf16_mixed_precision_checker) intel_extension_for_transformers module intel_extension_for_transformers.llm module intel_extension_for_transformers.llm.amp module intel_extension_for_transformers.llm.evaluation module intel_extension_for_transformers.llm.evaluation.hf_eval module intel_extension_for_transformers.llm.evaluation.hf_eval.evaluator module intel_extension_for_transformers.llm.evaluation.hf_eval.hf_datasets module intel_extension_for_transformers.llm.evaluation.hf_eval.hf_datasets.cnn_dailymail module intel_extension_for_transformers.llm.evaluation.lm_code_eval module intel_extension_for_transformers.llm.evaluation.lm_code_eval.evaluator module intel_extension_for_transformers.llm.evaluation.lm_eval module intel_extension_for_transformers.llm.evaluation.lm_eval.evaluator module intel_extension_for_transformers.llm.evaluation.lm_eval.models module intel_extension_for_transformers.llm.evaluation.lm_eval.models.huggingface module intel_extension_for_transformers.llm.evaluation.lm_eval.tasks module intel_extension_for_transformers.llm.evaluation.lm_eval.tasks.lambada module intel_extension_for_transformers.llm.finetuning module intel_extension_for_transformers.llm.finetuning.data_utils module intel_extension_for_transformers.llm.finetuning.eval_utils module intel_extension_for_transformers.llm.finetuning.finetuning module intel_extension_for_transformers.llm.quantization module intel_extension_for_transformers.llm.quantization.autograd module intel_extension_for_transformers.llm.quantization.autograd.functions module intel_extension_for_transformers.llm.quantization.nn module intel_extension_for_transformers.llm.quantization.nn.modules module intel_extension_for_transformers.llm.quantization.optimization module intel_extension_for_transformers.llm.quantization.utils module intel_extension_for_transformers.llm.runtime module intel_extension_for_transformers.llm.runtime.deprecated module intel_extension_for_transformers.llm.runtime.deprecated.compile module intel_extension_for_transformers.llm.runtime.deprecated.compile.compile module intel_extension_for_transformers.llm.runtime.deprecated.compile.dynamic_quantize module intel_extension_for_transformers.llm.runtime.deprecated.compile.extractors module intel_extension_for_transformers.llm.runtime.deprecated.compile.extractors.extractor module intel_extension_for_transformers.llm.runtime.deprecated.compile.extractors.onnx_extractor module intel_extension_for_transformers.llm.runtime.deprecated.compile.extractors.tf_extractor module intel_extension_for_transformers.llm.runtime.deprecated.compile.extractors.torch_extractor module intel_extension_for_transformers.llm.runtime.deprecated.compile.graph module intel_extension_for_transformers.llm.runtime.deprecated.compile.graph.graph module intel_extension_for_transformers.llm.runtime.deprecated.compile.graph_utils module intel_extension_for_transformers.llm.runtime.deprecated.compile.loaders module intel_extension_for_transformers.llm.runtime.deprecated.compile.loaders.loader module intel_extension_for_transformers.llm.runtime.deprecated.compile.logger module intel_extension_for_transformers.llm.runtime.deprecated.compile.onnx_utils module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.all module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.assert module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.baddbmm module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.batch_matmul module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.batch_matmul_v2 module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.bias_add module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.binary_op module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.cast module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.concat module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.conv module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.cos module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.expand_dims module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.fused_batch_matmul_v2 module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.fused_batch_norm_v3 module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.fused_gemm module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.fused_matmul module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.gather module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.gather_elements module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.gelu module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.gemm module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.iterator_get_next module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.iterator_v2 module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.layer_normalization module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.log_softmax module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.map_and_batch_dataset module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.matmul module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.mean module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.mkl_layer_norm module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.model_dataset module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.one_hot module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.onnx_input module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.op module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.optimize_dataset module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.pack module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.padding_sequence module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.placeholder module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.pos_embed module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.pow module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.quantize_linear module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.quantize_v2 module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.quantized_fused_matmul_and_dequantize module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.quantized_matmul_with_bias_and_dequantize module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.reduce_mean module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.reduce_sum module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.reorder module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.reshape module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.resize module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.rsub module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.scatter_elements module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.shape module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.sin module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.size module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.slice module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.slice_position_ids module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.softmax module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.split module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.squeeze module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.strided_slice module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.tensor module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.top_k module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.transpose module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.unpack module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.unsqueeze module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.view module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.where module intel_extension_for_transformers.llm.runtime.deprecated.compile.optimizer module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.add_cls_token module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.add_embeddings module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.arangewithreciprocal module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.attention_mask_length_adaptive_keep_indices module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.attention_output_layer_norm_length_adaptive_keep_indices module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.attention_reshape module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.attentionBlock_AttentionMaskAddReshape module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.attentionBlock_ConstantOfShapeWithMul module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.attentionBlock_QKVPreReshape module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.attentionBlock_QKVReshape module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.attentionBlock_WeightReshapeTo4D module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.cast_to module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.collect_quant_info module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.conv_reshape module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.decoder_attn_reshape module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.einsumwitharange module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.embeddingbag module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.embeddings_to_2d_before_inner_product module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.gelu module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.generate_sequence module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.groupNorm module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.groupNormSwish module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.InnerproductReshapeFusion module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.innerproductwithbiasgelu module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.innerproductwithslice module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.innerproductwithswish module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.input_data module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.input_file module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.insert_bf16_node module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.insert_quant_node module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.int8_bf16_mixed_precision_checker module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.interact_features module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.last_layer_shape module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.layer_norm module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.layer_norm_with_reduce_mean module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.layer_norm_with_transpose module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.llama_embeding module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.llama_matmulwithtranspose module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.llama_postprocess module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.llama_rotary_pos_emb module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.lower_all_tuples module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.matmul_with_bias module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.matmul_with_bias_add module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.matmul_with_bias_gelu module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.matmul_with_bias_relu module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.matmul_with_bias_sigmoid module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.matmul_with_bias_tanh module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.matmul_with_bias_unsqueeze module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.matmul_with_transpose module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.matmul_with_transpose_scale_add module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.merged_embeddingbag module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.multi_head_attention module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.neox_reorder_change module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.neox_rotary_pos_emb module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.operator_adaptor module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.output_data module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.padding_sequence module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.pattern module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.position_embeddings module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.position_embeddings_v1 module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.qkv_merge module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.qkv_reshape module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.quant_gather_to_bf16 module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.quantize_fusion module

intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.quantized_graph_dtype_refactor module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.remove_constant_op module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.remove_last_view module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.remove_range module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.remove_unused_operator module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.remove_zeros module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.removeslice module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.reshape_after_restore_hidden_states module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.reshape_before_and_after_attention_out_layer_norm_gather_elements module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.reshape_before_restore_hidden_states module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.reshape_fusion module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.restore_hidden_states_in_length_adaptive_update_indices module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.rms_norm module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.rotary_pos_emb module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.slicemask module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.stableDiffusion_bf16Convert module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.stableDiffusion_collectQDQInfo module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.stableDiffusion_ExplicitNHWCTranspose module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.stableDiffusion_ExplicitNHWCTransposeQAT module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.stableDiffusion_insertQuantNode module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.stableDiffusion_MHA module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.stableDiffusion_MHAReshape module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.stableDiffusion_QuantizeFusion module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.stableDiffusion_ReshapeFusion module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.start_end_logits module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.subgraph_matcher module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.textEncdoer_word_embedding module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.textEncoder_AttentionMaskAddReshape module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.textEncoder_AttentionReshape module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.textEncoder_causal_attention_mask module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.textEncoder_KVReshape module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.textEncoder_MulReshape module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.textEncoder_QReshape module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.textEncoder_SoftmaxReshape module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.token_type_embeddings module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.token_type_embeddings_v1 module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.torch_embedding module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.torch_ip_insert_bias module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.torch_unpack_baddbmm module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.torchinsertbf16node module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.torchpaddingsquence module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transformer2Dmodel_AttentionMaskAddReshape module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transformer2Dmodel_ConstantOfShapeWithMul module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transformer2Dmodel_encoderHiddenStatesReshape module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transformer2Dmodel_FFNSlice module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transformer2Dmodel_FFNSlice_1 module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transformer2Dmodel_getSampleBatch module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transformer2Dmodel_QKVPreReshape module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transformer2Dmodel_QKVReshape module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transformer2Dmodel_QKVReshape4D module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transformer2Dmodel_sampleSlice module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transpose_batch_matmul module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.word_embeddings module intel_extension_for_transformers.llm.runtime.deprecated.compile.tf_utils module intel_extension_for_transformers.llm.runtime.deprecated.compile.torch_utils module intel_extension_for_transformers.llm.runtime.graph module intel_extension_for_transformers.llm.runtime.graph.scripts module intel_extension_for_transformers.llm.runtime.graph.scripts.clang-format module intel_extension_for_transformers.llm.runtime.graph.scripts.convert module intel_extension_for_transformers.llm.runtime.graph.scripts.convert_bloom module intel_extension_for_transformers.llm.runtime.graph.scripts.convert_chatglm module intel_extension_for_transformers.llm.runtime.graph.scripts.convert_dolly module intel_extension_for_transformers.llm.runtime.graph.scripts.convert_falcon module intel_extension_for_transformers.llm.runtime.graph.scripts.convert_gptj module intel_extension_for_transformers.llm.runtime.graph.scripts.convert_gptneox module intel_extension_for_transformers.llm.runtime.graph.scripts.convert_llama module intel_extension_for_transformers.llm.runtime.graph.scripts.convert_mpt module intel_extension_for_transformers.llm.runtime.graph.scripts.convert_opt module intel_extension_for_transformers.llm.runtime.graph.scripts.convert_starcoder module intel_extension_for_transformers.llm.runtime.graph.scripts.inference module intel_extension_for_transformers.llm.runtime.graph.scripts.python_api_example module intel_extension_for_transformers.llm.runtime.graph.scripts.quantize module intel_extension_for_transformers.llm.runtime.graph.scripts.run module intel_extension_for_transformers.llm.utils module intel_extension_for_transformers.llm.utils.mpt_trace module intel_extension_for_transformers.neural_chat module intel_extension_for_transformers.neural_chat.chatbot module intel_extension_for_transformers.neural_chat.cli module intel_extension_for_transformers.neural_chat.cli.base_executor module intel_extension_for_transformers.neural_chat.cli.cli_commands module intel_extension_for_transformers.neural_chat.cli.log module intel_extension_for_transformers.neural_chat.config module intel_extension_for_transformers.neural_chat.models module intel_extension_for_transformers.neural_chat.models.base_model module intel_extension_for_transformers.neural_chat.models.chatglm_model module intel_extension_for_transformers.neural_chat.models.llama_model module intel_extension_for_transformers.neural_chat.models.model_utils module intel_extension_for_transformers.neural_chat.models.mpt_model module intel_extension_for_transformers.neural_chat.models.neuralchat_model module intel_extension_for_transformers.neural_chat.pipeline module intel_extension_for_transformers.neural_chat.pipeline.plugins module intel_extension_for_transformers.neural_chat.pipeline.plugins.audio module intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.asr module intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.asr_chinese module intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.tts module intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.tts_chinese module intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.utils module intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.utils.cut_video module intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.utils.english_normalizer module intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.utils.split_audio module intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.utils.video_to_wav module intel_extension_for_transformers.neural_chat.pipeline.plugins.caching module intel_extension_for_transformers.neural_chat.pipeline.plugins.caching.cache module intel_extension_for_transformers.neural_chat.pipeline.plugins.memory module intel_extension_for_transformers.neural_chat.pipeline.plugins.memory.memory module intel_extension_for_transformers.neural_chat.pipeline.plugins.prompt module intel_extension_for_transformers.neural_chat.pipeline.plugins.prompt.prompt_template module intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval module intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.detector module intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.detector.intent_detection module intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.indexing module intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.indexing.context_utils module intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.indexing.indexing module intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.retrieval_agent module intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.retrieval_base module intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.retrieval_bm25 module intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.retrieval_chroma module intel_extension_for_transformers.neural_chat.pipeline.plugins.security module intel_extension_for_transformers.neural_chat.pipeline.plugins.security.safety_checker module intel_extension_for_transformers.neural_chat.plugins module intel_extension_for_transformers.neural_chat.prompts module intel_extension_for_transformers.neural_chat.prompts.prompt module intel_extension_for_transformers.neural_chat.server module intel_extension_for_transformers.neural_chat.server.base_executor module intel_extension_for_transformers.neural_chat.server.neuralchat_client module intel_extension_for_transformers.neural_chat.server.neuralchat_server module intel_extension_for_transformers.neural_chat.server.restful module intel_extension_for_transformers.neural_chat.server.restful.api module intel_extension_for_transformers.neural_chat.server.restful.finetune_api module intel_extension_for_transformers.neural_chat.server.restful.openai_protocol module intel_extension_for_transformers.neural_chat.server.restful.request module intel_extension_for_transformers.neural_chat.server.restful.response module intel_extension_for_transformers.neural_chat.server.restful.retrieval_api module intel_extension_for_transformers.neural_chat.server.restful.text2image_api module intel_extension_for_transformers.neural_chat.server.restful.textchat_api module intel_extension_for_transformers.neural_chat.server.restful.voicechat_api module intel_extension_for_transformers.neural_chat.server.server_commands module intel_extension_for_transformers.neural_chat.utils module intel_extension_for_transformers.neural_chat.utils.command module intel_extension_for_transformers.neural_chat.utils.common module intel_extension_for_transformers.neural_chat.utils.dotdict module intel_extension_for_transformers.neural_chat.version module intel_extension_for_transformers.transformers module intel_extension_for_transformers.transformers.benchmark module intel_extension_for_transformers.transformers.config module intel_extension_for_transformers.transformers.distillation module intel_extension_for_transformers.transformers.dpo_trainer 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.mixture module intel_extension_for_transformers.transformers.mixture.auto_distillation module intel_extension_for_transformers.transformers.modeling module intel_extension_for_transformers.transformers.modeling.bloom module intel_extension_for_transformers.transformers.modeling.bloom.modeling_bloom module intel_extension_for_transformers.transformers.modeling.gpt_bigcode module intel_extension_for_transformers.transformers.modeling.gpt_bigcode.modeling_gpt_bigcode module intel_extension_for_transformers.transformers.modeling.gpt_neox module intel_extension_for_transformers.transformers.modeling.gpt_neox.modeling_gpt_neox module intel_extension_for_transformers.transformers.modeling.gptj module intel_extension_for_transformers.transformers.modeling.gptj.modeling_gptj module intel_extension_for_transformers.transformers.modeling.llama module intel_extension_for_transformers.transformers.modeling.llama.modeling_llama module intel_extension_for_transformers.transformers.modeling.model module intel_extension_for_transformers.transformers.modeling.modeling_auto module intel_extension_for_transformers.transformers.modeling.modeling_base_seq2seq module intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic module intel_extension_for_transformers.transformers.modeling.modeling_map module intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic module intel_extension_for_transformers.transformers.modeling.modeling_seq2seq module intel_extension_for_transformers.transformers.modeling.opt module intel_extension_for_transformers.transformers.modeling.opt.modeling_opt module intel_extension_for_transformers.transformers.nas module intel_extension_for_transformers.transformers.nas.basic_nas module intel_extension_for_transformers.transformers.nas.nas module intel_extension_for_transformers.transformers.optimizer module intel_extension_for_transformers.transformers.optimizer_tf 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.pruning module intel_extension_for_transformers.transformers.quantization module intel_extension_for_transformers.transformers.trainer module intel_extension_for_transformers.transformers.utils 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.quantization_config module intel_extension_for_transformers.transformers.utils.utility module intel_extension_for_transformers.transformers.utils.utility_tf module intel_extension_for_transformers.utils module intel_extension_for_transformers.utils.data_augmentation module intel_extension_for_transformers.utils.utils module InteractFeatures (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.interact_features) inverse() (in module intel_extension_for_transformers.transformers.dynamic.evolution) is_supported_onnx_graph() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.onnx_utils) is_supported_onnx_node() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.onnx_utils) IteratorGetNext (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.iterator_get_next) IteratorV2 (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.iterator_v2)

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::bsc_data_t (C++ class) jd::bsr_data_t (C++ class) 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::csrp_data_t (C++ class) 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)

K

keras2SavedModel() (in module intel_extension_for_transformers.transformers.utils.utility_tf)

L

LambadaOpenAI (class in intel_extension_for_transformers.llm.evaluation.lm_eval.tasks.lambada) LambadaStandard (class in intel_extension_for_transformers.llm.evaluation.lm_eval.tasks.lambada) laod_structured_data() (in module intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.indexing.context_utils) LastLayerShape (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.last_layer_shape) LatRange (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) LayerNorm (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.layer_normalization) (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.layer_norm) LayerNormalization (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.layer_normalization) LayerNormWithReduceMean (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.layer_norm_with_reduce_mean) LayerNormWithTranspose (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.layer_norm_with_transpose) LazyImport (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.graph_utils) LazySupervisedDataset (class in train) LazyUnpickler (class in intel_extension_for_transformers.llm.runtime.graph.scripts.convert_llama) list2str() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.graph_utils) ListConstruct (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) ListUnpack (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) llama_flash_attn_monkey_patch module LlamaAttention (class in intel_extension_for_transformers.transformers.modeling.llama.modeling_llama) LlamaEmbeddings (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.llama_embeding)

LlamaMatMulWithTranspose (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.llama_matmulwithtranspose) LlamaModel (class in intel_extension_for_transformers.neural_chat.models.llama_model) (class in intel_extension_for_transformers.transformers.modeling.llama.modeling_llama) LlamaPostprocess (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.llama_postprocess) LlamaRoraryPosEmb (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.llama_rotary_pos_emb) load_json() (in module intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.indexing.context_utils) load_model() (in module intel_extension_for_transformers.neural_chat.models.model_utils) (intel_extension_for_transformers.neural_chat.models.base_model.BaseModel method) load_search_results() (intel_extension_for_transformers.transformers.mixture.auto_distillation.AutoDistillation method) load_some_model() (in module intel_extension_for_transformers.llm.runtime.graph.scripts.convert_llama) 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) load_unstructured_data() (in module intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.indexing.context_utils) load_xlsx() (in module intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.indexing.context_utils) Loader (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.loaders.loader) log() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.logger) (intel_extension_for_transformers.transformers.dpo_trainer.DPOTrainer method) Logger (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.logger) LogSoftmax (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.log_softmax) Loop (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) LowerAllTuples (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.lower_all_tuples)

M

main module make_supervised_data_module() (in module train) MakeIterator (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) MapAndBatchDataset (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.map_and_batch_dataset) Masked_fill (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) match() (intel_extension_for_transformers.neural_chat.models.base_model.BaseModel method) (intel_extension_for_transformers.neural_chat.models.llama_model.LlamaModel method) (intel_extension_for_transformers.neural_chat.models.neuralchat_model.NeuralChatModel method) Matmul (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) MatMul (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.matmul) MatMulWithBias (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.matmul_with_bias) MatMulWithBiasAdd (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.matmul_with_bias_add) MatMulWithBiasGelu (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.matmul_with_bias_gelu) MatMulWithBiasRelu (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.matmul_with_bias_relu) MatMulWithBiasSigmoid (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.matmul_with_bias_sigmoid) MatMulWithBiasTanh (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) MatmulWithBiasTanh (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.matmul_with_bias_tanh) MatMulWithBiasUnsqueeze (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.matmul_with_bias_unsqueeze) MatMulWithTranspose (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.matmul_with_transpose) (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.matmul_with_transpose_scale_add) Max (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) Mean (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.mean) MergedEmbeddingbag (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.merged_embeddingbag) Metric (class in intel_extension_for_transformers.transformers.utils.metrics) mit_data_augmentation() (intel_extension_for_transformers.utils.data_augmentation.DataAugmentation method) model (intel_extension_for_transformers.transformers.pruner.pruning.Pruning attribute) model_builder_builtin() (intel_extension_for_transformers.transformers.optimizer_tf.TFOptimization method) (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) model_is_optimized() (in module intel_extension_for_transformers.neural_chat.models.model_utils) model_on_meta() (in module intel_extension_for_transformers.neural_chat.models.model_utils) ModelArguments (class in intel_extension_for_transformers.neural_chat.config) ModelDataset (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.model_dataset) modelsize() (intel_extension_for_transformers.transformers.utils.objectives.Objective static method) modify_node_connections() (intel_extension_for_transformers.llm.runtime.deprecated.compile.graph.graph.Graph method) module app asr chat_completion cnn_dailymail eval_gpt_review fastchat fastchat.client fastchat.client.api fastchat.client.test_client fastchat.constants fastchat.conversation fastchat.data fastchat.data.alpaca-converter fastchat.data.clean_sharegpt fastchat.data.hardcoded_questions fastchat.data.inspect fastchat.data.merge fastchat.data.optional_clean fastchat.data.pretty_json fastchat.data.sample fastchat.data.split_long_conversation fastchat.model fastchat.model.apply_delta fastchat.model.apply_lora fastchat.model.convert_fp16 fastchat.model.make_delta fastchat.serve fastchat.serve.api fastchat.serve.cacheflow_worker fastchat.serve.cli fastchat.serve.compression fastchat.serve.controller fastchat.serve.gradio_block_arena_anony fastchat.serve.gradio_block_arena_named fastchat.serve.gradio_css fastchat.serve.gradio_patch fastchat.serve.gradio_web_server fastchat.serve.gradio_web_server_multi fastchat.serve.huggingface_api fastchat.serve.inference fastchat.serve.model_worker fastchat.serve.monkey_patch_non_inplace fastchat.serve.register_worker fastchat.serve.serve_chatglm fastchat.serve.test_message fastchat.serve.test_throughput fastchat.utils finetune finetune_clm finetune_seq2seq gaudi_spawn generate_webpage_data_from_table get_model_answer inference intel_extension_for_transformers intel_extension_for_transformers.llm intel_extension_for_transformers.llm.amp intel_extension_for_transformers.llm.evaluation intel_extension_for_transformers.llm.evaluation.hf_eval intel_extension_for_transformers.llm.evaluation.hf_eval.evaluator intel_extension_for_transformers.llm.evaluation.hf_eval.hf_datasets intel_extension_for_transformers.llm.evaluation.hf_eval.hf_datasets.cnn_dailymail intel_extension_for_transformers.llm.evaluation.lm_code_eval intel_extension_for_transformers.llm.evaluation.lm_code_eval.evaluator intel_extension_for_transformers.llm.evaluation.lm_eval intel_extension_for_transformers.llm.evaluation.lm_eval.evaluator intel_extension_for_transformers.llm.evaluation.lm_eval.models intel_extension_for_transformers.llm.evaluation.lm_eval.models.huggingface intel_extension_for_transformers.llm.evaluation.lm_eval.tasks intel_extension_for_transformers.llm.evaluation.lm_eval.tasks.lambada intel_extension_for_transformers.llm.finetuning intel_extension_for_transformers.llm.finetuning.data_utils intel_extension_for_transformers.llm.finetuning.eval_utils intel_extension_for_transformers.llm.finetuning.finetuning intel_extension_for_transformers.llm.quantization intel_extension_for_transformers.llm.quantization.autograd intel_extension_for_transformers.llm.quantization.autograd.functions intel_extension_for_transformers.llm.quantization.nn intel_extension_for_transformers.llm.quantization.nn.modules intel_extension_for_transformers.llm.quantization.optimization intel_extension_for_transformers.llm.quantization.utils intel_extension_for_transformers.llm.runtime intel_extension_for_transformers.llm.runtime.deprecated intel_extension_for_transformers.llm.runtime.deprecated.compile intel_extension_for_transformers.llm.runtime.deprecated.compile.compile intel_extension_for_transformers.llm.runtime.deprecated.compile.dynamic_quantize intel_extension_for_transformers.llm.runtime.deprecated.compile.extractors intel_extension_for_transformers.llm.runtime.deprecated.compile.extractors.extractor intel_extension_for_transformers.llm.runtime.deprecated.compile.extractors.onnx_extractor intel_extension_for_transformers.llm.runtime.deprecated.compile.extractors.tf_extractor intel_extension_for_transformers.llm.runtime.deprecated.compile.extractors.torch_extractor intel_extension_for_transformers.llm.runtime.deprecated.compile.graph intel_extension_for_transformers.llm.runtime.deprecated.compile.graph.graph intel_extension_for_transformers.llm.runtime.deprecated.compile.graph_utils intel_extension_for_transformers.llm.runtime.deprecated.compile.loaders intel_extension_for_transformers.llm.runtime.deprecated.compile.loaders.loader intel_extension_for_transformers.llm.runtime.deprecated.compile.logger intel_extension_for_transformers.llm.runtime.deprecated.compile.onnx_utils intel_extension_for_transformers.llm.runtime.deprecated.compile.ops intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.all intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.assert intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.baddbmm intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.batch_matmul intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.batch_matmul_v2 intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.bias_add intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.binary_op intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.cast intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.concat intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.conv intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.cos intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.expand_dims intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.fused_batch_matmul_v2 intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.fused_batch_norm_v3 intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.fused_gemm intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.fused_matmul intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.gather intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.gather_elements intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.gelu intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.gemm intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.iterator_get_next intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.iterator_v2 intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.layer_normalization intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.log_softmax intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.map_and_batch_dataset intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.matmul intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.mean intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.mkl_layer_norm intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.model_dataset intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.one_hot intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.onnx_input intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.op intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.optimize_dataset intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.pack intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.padding_sequence intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.placeholder intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.pos_embed intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.pow intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.quantize_linear intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.quantize_v2 intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.quantized_fused_matmul_and_dequantize intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.quantized_matmul_with_bias_and_dequantize intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.reduce_mean intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.reduce_sum intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.reorder intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.reshape intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.resize intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.rsub intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.scatter_elements intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.shape intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.sin intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.size intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.slice intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.slice_position_ids intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.softmax intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.split intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.squeeze intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.strided_slice intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.tensor intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.top_k intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.transpose intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.unpack intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.unsqueeze intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.view intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.where intel_extension_for_transformers.llm.runtime.deprecated.compile.optimizer intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.add_cls_token intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.add_embeddings intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.arangewithreciprocal intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.attention_mask_length_adaptive_keep_indices intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.attention_output_layer_norm_length_adaptive_keep_indices intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.attention_reshape intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.attentionBlock_AttentionMaskAddReshape intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.attentionBlock_ConstantOfShapeWithMul intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.attentionBlock_QKVPreReshape intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.attentionBlock_QKVReshape intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.attentionBlock_WeightReshapeTo4D intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.cast_to intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.collect_quant_info intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.conv_reshape intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.decoder_attn_reshape intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.einsumwitharange intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.embeddingbag intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.embeddings_to_2d_before_inner_product intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.gelu intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.generate_sequence intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.groupNorm intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.groupNormSwish intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.InnerproductReshapeFusion intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.innerproductwithbiasgelu intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.innerproductwithslice intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.innerproductwithswish intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.input_data intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.input_file intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.insert_bf16_node intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.insert_quant_node intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.int8_bf16_mixed_precision_checker intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.interact_features intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.last_layer_shape intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.layer_norm intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.layer_norm_with_reduce_mean intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.layer_norm_with_transpose intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.llama_embeding intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.llama_matmulwithtranspose intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.llama_postprocess intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.llama_rotary_pos_emb intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.lower_all_tuples intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.matmul_with_bias intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.matmul_with_bias_add intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.matmul_with_bias_gelu intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.matmul_with_bias_relu intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.matmul_with_bias_sigmoid intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.matmul_with_bias_tanh intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.matmul_with_bias_unsqueeze intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.matmul_with_transpose intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.matmul_with_transpose_scale_add intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.merged_embeddingbag intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.multi_head_attention intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.neox_reorder_change intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.neox_rotary_pos_emb intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.operator_adaptor intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.output_data intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.padding_sequence intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.pattern intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.position_embeddings intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.position_embeddings_v1 intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.qkv_merge intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.qkv_reshape intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.quant_gather_to_bf16 intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.quantize_fusion intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.quantized_graph_dtype_refactor intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.remove_constant_op intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.remove_last_view intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.remove_range intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.remove_unused_operator intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.remove_zeros intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.removeslice intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.reshape_after_restore_hidden_states intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.reshape_before_and_after_attention_out_layer_norm_gather_elements intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.reshape_before_restore_hidden_states intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.reshape_fusion intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.restore_hidden_states_in_length_adaptive_update_indices intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.rms_norm intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.rotary_pos_emb intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.slicemask intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.stableDiffusion_bf16Convert intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.stableDiffusion_collectQDQInfo intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.stableDiffusion_ExplicitNHWCTranspose intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.stableDiffusion_ExplicitNHWCTransposeQAT intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.stableDiffusion_insertQuantNode intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.stableDiffusion_MHA intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.stableDiffusion_MHAReshape intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.stableDiffusion_QuantizeFusion intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.stableDiffusion_ReshapeFusion intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.start_end_logits intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.subgraph_matcher intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.textEncdoer_word_embedding intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.textEncoder_AttentionMaskAddReshape intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.textEncoder_AttentionReshape intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.textEncoder_causal_attention_mask intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.textEncoder_KVReshape intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.textEncoder_MulReshape intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.textEncoder_QReshape intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.textEncoder_SoftmaxReshape intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.token_type_embeddings intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.token_type_embeddings_v1 intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.torch_embedding intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.torch_ip_insert_bias intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.torch_unpack_baddbmm intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.torchinsertbf16node intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.torchpaddingsquence intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transformer2Dmodel_AttentionMaskAddReshape intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transformer2Dmodel_ConstantOfShapeWithMul intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transformer2Dmodel_encoderHiddenStatesReshape intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transformer2Dmodel_FFNSlice intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transformer2Dmodel_FFNSlice_1 intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transformer2Dmodel_getSampleBatch intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transformer2Dmodel_QKVPreReshape intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transformer2Dmodel_QKVReshape intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transformer2Dmodel_QKVReshape4D intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transformer2Dmodel_sampleSlice intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transpose_batch_matmul intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.word_embeddings intel_extension_for_transformers.llm.runtime.deprecated.compile.tf_utils intel_extension_for_transformers.llm.runtime.deprecated.compile.torch_utils intel_extension_for_transformers.llm.runtime.graph intel_extension_for_transformers.llm.runtime.graph.scripts intel_extension_for_transformers.llm.runtime.graph.scripts.clang-format intel_extension_for_transformers.llm.runtime.graph.scripts.convert intel_extension_for_transformers.llm.runtime.graph.scripts.convert_bloom intel_extension_for_transformers.llm.runtime.graph.scripts.convert_chatglm intel_extension_for_transformers.llm.runtime.graph.scripts.convert_dolly intel_extension_for_transformers.llm.runtime.graph.scripts.convert_falcon intel_extension_for_transformers.llm.runtime.graph.scripts.convert_gptj intel_extension_for_transformers.llm.runtime.graph.scripts.convert_gptneox intel_extension_for_transformers.llm.runtime.graph.scripts.convert_llama intel_extension_for_transformers.llm.runtime.graph.scripts.convert_mpt intel_extension_for_transformers.llm.runtime.graph.scripts.convert_opt intel_extension_for_transformers.llm.runtime.graph.scripts.convert_starcoder intel_extension_for_transformers.llm.runtime.graph.scripts.inference intel_extension_for_transformers.llm.runtime.graph.scripts.python_api_example intel_extension_for_transformers.llm.runtime.graph.scripts.quantize intel_extension_for_transformers.llm.runtime.graph.scripts.run intel_extension_for_transformers.llm.utils intel_extension_for_transformers.llm.utils.mpt_trace intel_extension_for_transformers.neural_chat intel_extension_for_transformers.neural_chat.chatbot intel_extension_for_transformers.neural_chat.cli intel_extension_for_transformers.neural_chat.cli.base_executor intel_extension_for_transformers.neural_chat.cli.cli_commands intel_extension_for_transformers.neural_chat.cli.log intel_extension_for_transformers.neural_chat.config intel_extension_for_transformers.neural_chat.models intel_extension_for_transformers.neural_chat.models.base_model intel_extension_for_transformers.neural_chat.models.chatglm_model intel_extension_for_transformers.neural_chat.models.llama_model intel_extension_for_transformers.neural_chat.models.model_utils intel_extension_for_transformers.neural_chat.models.mpt_model intel_extension_for_transformers.neural_chat.models.neuralchat_model intel_extension_for_transformers.neural_chat.pipeline intel_extension_for_transformers.neural_chat.pipeline.plugins intel_extension_for_transformers.neural_chat.pipeline.plugins.audio intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.asr intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.asr_chinese intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.tts intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.tts_chinese intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.utils intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.utils.cut_video intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.utils.english_normalizer intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.utils.split_audio intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.utils.video_to_wav intel_extension_for_transformers.neural_chat.pipeline.plugins.caching intel_extension_for_transformers.neural_chat.pipeline.plugins.caching.cache intel_extension_for_transformers.neural_chat.pipeline.plugins.memory intel_extension_for_transformers.neural_chat.pipeline.plugins.memory.memory intel_extension_for_transformers.neural_chat.pipeline.plugins.prompt intel_extension_for_transformers.neural_chat.pipeline.plugins.prompt.prompt_template intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.detector intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.detector.intent_detection intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.indexing intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.indexing.context_utils intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.indexing.indexing intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.retrieval_agent intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.retrieval_base intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.retrieval_bm25 intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.retrieval_chroma intel_extension_for_transformers.neural_chat.pipeline.plugins.security intel_extension_for_transformers.neural_chat.pipeline.plugins.security.safety_checker intel_extension_for_transformers.neural_chat.plugins intel_extension_for_transformers.neural_chat.prompts intel_extension_for_transformers.neural_chat.prompts.prompt intel_extension_for_transformers.neural_chat.server intel_extension_for_transformers.neural_chat.server.base_executor intel_extension_for_transformers.neural_chat.server.neuralchat_client intel_extension_for_transformers.neural_chat.server.neuralchat_server intel_extension_for_transformers.neural_chat.server.restful intel_extension_for_transformers.neural_chat.server.restful.api intel_extension_for_transformers.neural_chat.server.restful.finetune_api intel_extension_for_transformers.neural_chat.server.restful.openai_protocol intel_extension_for_transformers.neural_chat.server.restful.request intel_extension_for_transformers.neural_chat.server.restful.response intel_extension_for_transformers.neural_chat.server.restful.retrieval_api intel_extension_for_transformers.neural_chat.server.restful.text2image_api intel_extension_for_transformers.neural_chat.server.restful.textchat_api intel_extension_for_transformers.neural_chat.server.restful.voicechat_api intel_extension_for_transformers.neural_chat.server.server_commands intel_extension_for_transformers.neural_chat.utils intel_extension_for_transformers.neural_chat.utils.command intel_extension_for_transformers.neural_chat.utils.common intel_extension_for_transformers.neural_chat.utils.dotdict intel_extension_for_transformers.neural_chat.version intel_extension_for_transformers.transformers intel_extension_for_transformers.transformers.benchmark intel_extension_for_transformers.transformers.config intel_extension_for_transformers.transformers.distillation intel_extension_for_transformers.transformers.dpo_trainer 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.mixture intel_extension_for_transformers.transformers.mixture.auto_distillation intel_extension_for_transformers.transformers.modeling intel_extension_for_transformers.transformers.modeling.bloom intel_extension_for_transformers.transformers.modeling.bloom.modeling_bloom intel_extension_for_transformers.transformers.modeling.gpt_bigcode intel_extension_for_transformers.transformers.modeling.gpt_bigcode.modeling_gpt_bigcode intel_extension_for_transformers.transformers.modeling.gpt_neox intel_extension_for_transformers.transformers.modeling.gpt_neox.modeling_gpt_neox intel_extension_for_transformers.transformers.modeling.gptj intel_extension_for_transformers.transformers.modeling.gptj.modeling_gptj intel_extension_for_transformers.transformers.modeling.llama intel_extension_for_transformers.transformers.modeling.llama.modeling_llama intel_extension_for_transformers.transformers.modeling.model intel_extension_for_transformers.transformers.modeling.modeling_auto intel_extension_for_transformers.transformers.modeling.modeling_base_seq2seq intel_extension_for_transformers.transformers.modeling.modeling_bert_dynamic intel_extension_for_transformers.transformers.modeling.modeling_map intel_extension_for_transformers.transformers.modeling.modeling_roberta_dynamic intel_extension_for_transformers.transformers.modeling.modeling_seq2seq intel_extension_for_transformers.transformers.modeling.opt intel_extension_for_transformers.transformers.modeling.opt.modeling_opt intel_extension_for_transformers.transformers.nas intel_extension_for_transformers.transformers.nas.basic_nas intel_extension_for_transformers.transformers.nas.nas intel_extension_for_transformers.transformers.optimizer intel_extension_for_transformers.transformers.optimizer_tf intel_extension_for_transformers.transformers.pipeline intel_extension_for_transformers.transformers.pruner intel_extension_for_transformers.transformers.pruner.pruning intel_extension_for_transformers.transformers.pruning intel_extension_for_transformers.transformers.quantization intel_extension_for_transformers.transformers.trainer intel_extension_for_transformers.transformers.utils 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.quantization_config intel_extension_for_transformers.transformers.utils.utility intel_extension_for_transformers.transformers.utils.utility_tf intel_extension_for_transformers.utils intel_extension_for_transformers.utils.data_augmentation intel_extension_for_transformers.utils.utils llama_flash_attn_monkey_patch main qa_baseline_gpt35 retrieval_chat run_text_chat sparsity_all talkingbot test_add_cls_token test_add_embeddings test_add_zeros test_asr test_attention_output_layer_norm_length_adaptive_keep_indices test_attention_reshape test_baddbmm test_bert_mini_fp32 test_binary_op test_binaryop test_cast_to test_chatbot_build_api test_cli test_concat test_conv test_conv_int8 test_conv_reshape test_decoder_attn_reshape test_dispatcher_tuning_acc test_dispatcher_tuning_throughput test_dolly_pattern test_dynamic_quantization test_electra test_embedding test_embeddingbag test_english_normalizer test_execution_options test_finetuning test_fwk test_gather test_gelu test_gpt_int8 test_graph_dispatch test_graph_optimizer test_inference test_insert_input_output_data test_is_supported_onnx_graph test_last_layer_shape test_layer_norm_with_reduce_mean test_layer_norm_with_transpose test_layernorm test_linear test_linear_int8 test_llama_pattern test_main test_matmul test_matmul_int8 test_matmul_with_bias_relu test_matmul_with_bias_sigmoid test_matmul_with_bias_tanh test_merged_embeddingbag test_model test_neox_rotary_pos_emb test_onnx_utils test_operator_adaptor test_ops test_optimization test_padding_seq test_padding_sequence test_pattern_dispatch test_permute test_position_embeddings test_pow test_primitive_cache_acc test_primitive_cache_throughput test_qkv_merge test_qkv_reshape test_quant_onnx_execute test_rag test_reshape_after_restore_hidden_states test_reshape_before_and_after_attention_out_layer_norm_gather_elements test_reshape_before_restore_hidden_states test_size test_slice test_softmax test_start_end_logits test_static_compressed_buffer test_tanh test_text_encoder test_text_encoder_bf16 test_textchat_server test_textchat_with_retrieval_server test_tf_utils test_token_type_embeddings test_transpose test_transpose_batch_matmul test_tts test_two_linear test_unet test_unet_bf16 test_unet_qat test_unsqueeze test_vae_decoder test_vae_decoder_bf16 test_voicechat_server test_weight_sharing_acc test_weight_sharing_dispatcher_tuning_acc test_weight_sharing_dispatcher_tuning_throughtput test_weight_sharing_throughput train train_lora train_mem tts_finetuning weightonly_test

MultiHeadAttenion (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) MultiHeadAttention (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.multi_head_attention) MultiTokenEOSCriteria (class in intel_extension_for_transformers.llm.evaluation.lm_eval.models.huggingface) mutate() (intel_extension_for_transformers.transformers.dynamic.evolution.Evolution method)

N

names_from_input() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.graph_utils) NAS (class in intel_extension_for_transformers.transformers.nas.nas) nas() (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) NASConfig (class in intel_extension_for_transformers.transformers.config) NEFileType (class in intel_extension_for_transformers.llm.runtime.graph.scripts.convert_llama) NeoxReorderChange (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.neox_reorder_change) NeoxRoraryPosEmb (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.neox_rotary_pos_emb) neural_engine_bin() (in module intel_extension_for_transformers.llm.runtime.deprecated) NeuralChatCommandDict (class in intel_extension_for_transformers.neural_chat.utils.command)

NeuralChatModel (class in intel_extension_for_transformers.neural_chat.models.neuralchat_model) NeuralChatServerExecutor (class in intel_extension_for_transformers.neural_chat.server.neuralchat_server) NLPSeq2SeqTrainer (class in intel_extension_for_transformers.transformers.trainer) NLPTrainer (class in intel_extension_for_transformers.transformers.trainer) None (intel_extension_for_transformers.neural_chat.cli.cli_commands.BaseCommand attribute) (intel_extension_for_transformers.neural_chat.cli.cli_commands.HelpCommand attribute) NoTrainerOptimizer (class in intel_extension_for_transformers.transformers.optimizer) nth_multifile_path() (in module intel_extension_for_transformers.llm.runtime.graph.scripts.convert_llama) NULL_INSTANCE (C macro)

O

Objective (class in intel_extension_for_transformers.transformers.utils.objectives) 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.llm.runtime.deprecated.compile.ops.empty_ops) OneHot (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.one_hot) onnx_extract_operator() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.onnx_utils) ONNXExtractor (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.extractors.onnx_extractor) ONNXINPUT (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.onnx_input)

OpAny (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) Operator (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.op) operator_registry() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.op) OperatorAdaptor (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.operator_adaptor) OPTAttention (class in intel_extension_for_transformers.transformers.modeling.opt.modeling_opt) OPTDecoder (class in intel_extension_for_transformers.transformers.modeling.opt.modeling_opt) optimize() (intel_extension_for_transformers.llm.runtime.deprecated.compile.optimizer.Optimizer method) optimize_model() (in module intel_extension_for_transformers.neural_chat.chatbot) OptimizeDataset (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.optimize_dataset) OptimizedModel (class in intel_extension_for_transformers.transformers.modeling.model) Optimizer (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.optimizer) OPTLearnedPositionalEmbedding (class in intel_extension_for_transformers.transformers.modeling.opt.modeling_opt) orchestrate_optimizations() (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) Orchestrate_optimizer (class in intel_extension_for_transformers.transformers.optimizer) Output (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) OutputData (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.output_data)

P

Pack (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.pack) PackagePositionEmbedding (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.pos_embed) PaddingSequence (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.padding_sequence) (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.padding_sequence) pareto_frontier() (intel_extension_for_transformers.transformers.dynamic.evolution.Evolution method) parse_args() (in module gaudi_spawn) parser (intel_extension_for_transformers.neural_chat.cli.cli_commands.TextVoiceChatExecutor attribute) Pattern (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.pattern) pattern_mapping() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.graph_utils) pattern_mapping_conf_validation() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.graph_utils) pattern_match() (in module intel_extension_for_transformers.llm.evaluation.lm_code_eval.evaluator) pattern_registry() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.pattern) performance() (intel_extension_for_transformers.transformers.utils.objectives.Objective static method) Placeholder (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.placeholder) PositionEmbeddings (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.position_embeddings) PositionEmbeddingsV1 (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.position_embeddings_v1) PositionIds (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) postprocess() (fastchat.serve.gradio_patch.Chatbot method) Pow (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.pow) predict() (in module intel_extension_for_transformers.neural_chat.models.model_utils) (intel_extension_for_transformers.neural_chat.models.base_model.BaseModel method) predict_stream() (in module intel_extension_for_transformers.neural_chat.models.model_utils) (intel_extension_for_transformers.neural_chat.models.base_model.BaseModel method)

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() (in module cnn_dailymail) (in module intel_extension_for_transformers.llm.evaluation.hf_eval.hf_datasets.cnn_dailymail) preprocess_model() (in module intel_extension_for_transformers.transformers.benchmark) prompt_for_input() (fastchat.serve.inference.ChatIO method) prompt_for_output() (fastchat.serve.inference.ChatIO method) Provider (class in intel_extension_for_transformers.transformers.config) prune() (intel_extension_for_transformers.transformers.optimizer.NoTrainerOptimizer method) (intel_extension_for_transformers.transformers.optimizer_tf.TFOptimization method) (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) PrunerConfig (class in intel_extension_for_transformers.transformers.pruning) 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) PruningConfig (class in intel_extension_for_transformers.transformers.config) PruningMode (class in intel_extension_for_transformers.transformers.pruning)

Q

qa_baseline_gpt35 module QKVMerge (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.qkv_merge) QKVReshape (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.qkv_reshape) QLinearAdd (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) QLinearMatMul (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) QLinearMul (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) quant_info_init() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.graph_utils) QuantizationConfig (class in intel_extension_for_transformers.transformers.config)

QuantizationMode (class in intel_extension_for_transformers.transformers.quantization) Quantize (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.quantize_linear) quantize() (intel_extension_for_transformers.transformers.optimizer.NoTrainerOptimizer method) (intel_extension_for_transformers.transformers.optimizer_tf.TFOptimization method) (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) QuantizedGraphDtypeCheck (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.quantized_graph_dtype_refactor) QuantizedMatMulWithBiasAndDequantize (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.quantized_matmul_with_bias_and_dequantize) QuantizeFusion (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.quantize_fusion) QuantizeLinear (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.quantize_linear) QuantizeV2 (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.quantize_v2)

R

Range (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) read_docx() (in module intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.indexing.context_utils) read_html() (in module intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.indexing.context_utils) read_md() (in module intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.indexing.context_utils) read_pdf() (in module intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.indexing.context_utils) read_txt() (in module intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.indexing.context_utils) read_wave() (in module intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.utils.split_audio) RealDiv (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) Reciprocal (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) ReduceMean (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.reduce_mean) ReduceSum (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.reduce_sum) refactor_batch_size() (in module intel_extension_for_transformers.transformers.benchmark) register_conv_template() (in module fastchat.conversation) register_model_adapter() (in module intel_extension_for_transformers.neural_chat.models.base_model) register_plugin_instance() (intel_extension_for_transformers.neural_chat.models.base_model.BaseModel method) Relu (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) remove_environ_info_item() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.graph_utils) remove_environ_info_items() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.graph_utils) remove_nodes() (intel_extension_for_transformers.llm.runtime.deprecated.compile.graph.graph.Graph method) RemoveConstantOP (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.remove_constant_op) RemoveLastView (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.remove_last_view) RemoveRange (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.remove_range) RemoveSlice (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.removeslice) RemoveUnusedOperator (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.remove_unused_operator) RemoveZeros (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.remove_zeros) rename_node() (intel_extension_for_transformers.llm.runtime.deprecated.compile.graph.graph.Graph method) Reorder (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.reorder) Repeat (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) replace_llama_attn_with_non_inplace_operations() (in module fastchat.serve.monkey_patch_non_inplace) Reshape (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.reshape) ReshapeAfterRestoreHiddenStates (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.reshape_after_restore_hidden_states) ReshapeBeforeAndAfterAttentionOutLayerNormGatherElements (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.reshape_before_and_after_attention_out_layer_norm_gather_elements) ReshapeBeforeRestoreHiddenStates (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.reshape_before_restore_hidden_states) ReshapeFusion (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.reshape_fusion)

Resize (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.resize) RestoreHiddenStatesInLengthAdaptive (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.restore_hidden_states_in_length_adaptive_update_indices) retrieval_chat module RetrievalTypeOptions (class in intel_extension_for_transformers.neural_chat.config) Retriever (class in intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.retrieval_base) RmsNorm (class in intel_extension_for_transformers.llm.runtime.deprecated.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.llm.runtime.deprecated.compile.sub_graph.rotary_pos_emb) rotate_half() (in module fastchat.serve.monkey_patch_non_inplace) (in module intel_extension_for_transformers.transformers.modeling.gpt_neox.modeling_gpt_neox) (in module intel_extension_for_transformers.transformers.modeling.llama.modeling_llama) Rsqrt (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) Rsub (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.rsub) run_evolutionary_search() (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) run_text_chat module

S

safe_save_model_for_hf_trainer() (in module train) 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) save() (intel_extension_for_transformers.llm.runtime.deprecated.compile.graph.graph.Graph method) save_model() (intel_extension_for_transformers.transformers.optimizer.NoTrainerOptimizer method) (intel_extension_for_transformers.transformers.optimizer.Orchestrate_optimizer method) save_population() (intel_extension_for_transformers.transformers.dynamic.evolution.Evolution method) save_store() (intel_extension_for_transformers.transformers.dynamic.evolution.Evolution method) ScatterElements (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.scatter_elements) search() (intel_extension_for_transformers.transformers.mixture.auto_distillation.AutoDistillation method) search_pattern() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.graph_utils) search_straight_pattern() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.graph_utils) select (fastchat.serve.gradio_patch.Chatbot attribute) SeparatorStyle (class in fastchat.conversation) SequenceLength (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) set_attr() (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.all.All method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.assert.Assert method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.baddbmm.Baddbmm method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.batch_matmul.BatchMatMul method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.batch_matmul_v2.BatchMatMulV2 method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.bias_add.BiasAdd method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.cast.Cast method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.concat.Concat method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.conv.Conv method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.cos.Cos method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.expand_dims.ExpandDims method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.fused_batch_norm_v3.FusedBatchNormV3 method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.fused_gemm.FusedGemm method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.fused_matmul.FusedMatMul method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.gather.Gather method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.gather.GatherV2 method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.gather_elements.GatherElements method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.gelu.Gelu method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.gemm.Gemm method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.iterator_get_next.IteratorGetNext method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.iterator_v2.IteratorV2 method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.layer_normalization.LayerNormalization method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.log_softmax.LogSoftmax method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.map_and_batch_dataset.MapAndBatchDataset method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.matmul.MatMul method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.mean.Mean method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.model_dataset.ModelDataset method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.one_hot.OneHot method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.op.Operator method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.optimize_dataset.OptimizeDataset method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.pack.Pack method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.padding_sequence.PaddingSequence method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.placeholder.Placeholder method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.pos_embed.PackagePositionEmbedding method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.pow.Pow method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.quantize_linear.Quantize method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.quantize_linear.QuantizeLinear method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.quantize_v2.QuantizeV2 method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.quantized_matmul_with_bias_and_dequantize.QuantizedMatMulWithBiasAndDequantize method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.reduce_mean.ReduceMean method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.reduce_sum.ReduceSum method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.reorder.Reorder method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.reshape.Reshape method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.resize.Resize method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.rsub.Rsub method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.scatter_elements.ScatterElements method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.shape.Shape method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.sin.Sin method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.size.Size method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.slice_position_ids.SlicePositionIds method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.softmax.Softmax method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.split.Split method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.squeeze.Squeeze method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.strided_slice.StridedSlice method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.top_k.TopK method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.transpose.Transpose method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.unpack.Unpack method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.unsqueeze.Unsqueeze method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.view.View method) (intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.where.Where method) set_autocast() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.graph_utils) set_dynamic_config() (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) set_environ_var() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.graph_utils) set_environ_vars() (in module intel_extension_for_transformers.llm.runtime.deprecated.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_system_message() (fastchat.conversation.Conversation method) set_upper_constraint() (intel_extension_for_transformers.transformers.dynamic.evolution.Evolution method) setUp() (test_chatbot_build_api.TestChatbotBuilder method) (test_inference.UnitTest method) (test_optimization.TestChatbotBuilder method) (test_rag.TestChatbotBuilder method) (test_textchat_server.UnitTest method) (test_textchat_with_retrieval_server.UnitTest method) (test_voicechat_server.UnitTest method) setup_router() (in module intel_extension_for_transformers.neural_chat.server.restful.api) setUpClass() (test_add_cls_token.TestAddClsToken class method) (test_add_embeddings.TestAddEmbeddings class method) (test_add_zeros.TestTorchOP class method) (test_asr.TestASR class method) (test_attention_output_layer_norm_length_adaptive_keep_indices.TestAttentionReshape class method) (test_attention_reshape.TestAttentionReshape class method) (test_baddbmm.TestTorchOP class method) (test_bert_mini_fp32.TestTorchModel class method) (test_binary_op.TestBinaryOp class method) (test_binaryop.TestTorchOP class method) (test_cast_to.TestCastTo class method) (test_concat.TestTorchOP class method) (test_conv.TestTorchOP class method) (test_conv_int8.TestTorchOP class method) (test_conv_reshape.TestConvReshape class method) (test_decoder_attn_reshape.TestDecoderAttnReshape class method) (test_dispatcher_tuning_acc.TestDispatcherTuningAcc class method) (test_dispatcher_tuning_throughput.TestDispatcherTuningThroughput class method) (test_dolly_pattern.TestTorchOP class method) (test_dynamic_quantization.TestDynamicQuantization class method) (test_electra.TestElectra class method) (test_embedding.TestTorchOP class method) (test_embeddingbag.TestEmbeddingBag class method) (test_english_normalizer.TestTTS class method) (test_execution_options.TestExecutionOptions class method) (test_finetuning.TestFinetuning class method) (test_fwk.TestFWK class method) (test_gather.TestTorchOP class method) (test_gelu.TestTorchOP class method) (test_gpt_int8.TestTorchModel class method) (test_graph_dispatch.TestGraphDispatch class method) (test_graph_optimizer.TestExecutionOptions class method) (test_insert_input_output_data.TestInsertInputOuputData class method) (test_is_supported_onnx_graph.TestIsSupportedOnnxGraph class method) (test_last_layer_shape.TestLastLayerShape class method) (test_layer_norm_with_reduce_mean.TestLayerNormWithReduceMean class method) (test_layer_norm_with_transpose.TestLayerNormWithTranspose class method) (test_layernorm.TestTorchOP class method) (test_linear.TestTorchOP class method) (test_linear_int8.TestTorchLinear class method) (test_llama_pattern.TestTorchOP class method) (test_main.TestMain class method) (test_matmul.TestTorchOP class method) (test_matmul_int8.TestTorchOP class method) (test_matmul_with_bias_relu.TestMatmulWithBiasRelu class method) (test_matmul_with_bias_sigmoid.TestMatMulWithBiasSigmoid class method) (test_matmul_with_bias_tanh.TestMatmulWithBiasTanh class method) (test_merged_embeddingbag.TestMergedEmbeddingbag class method) (test_neox_rotary_pos_emb.TestTorchOP class method) (test_onnx_utils.TestOnnxUtils class method) (test_operator_adaptor.TestOperatorAdaptor class method) (test_ops.TestOps class method) (test_padding_seq.TestTorchOP class method) (test_padding_sequence.TestPaddingSequence class method) (test_pattern_dispatch.TestPatternDispatch class method) (test_permute.TestTorchOP class method) (test_position_embeddings.TestPositionEmbeddings class method) (test_pow.TestTorchOP class method) (test_primitive_cache_acc.TestPrimitiveCacheAcc class method) (test_primitive_cache_throughput.TestPrimitiveCacheThroughput class method) (test_qkv_merge.TestQKVMerge class method) (test_qkv_reshape.TestAttentionReshape class method) (test_quant_onnx_execute.TestQuantOnnxExecute class method) (test_reshape_after_restore_hidden_states.TestLayerNormWithReduceMean class method) (test_reshape_before_and_after_attention_out_layer_norm_gather_elements.TestAttentionReshape class method) (test_reshape_before_restore_hidden_states.TestLayerNormWithReduceMean class method) (test_size.TestTorchOP class method) (test_slice.TestTorchOP class method) (test_softmax.TestTorchOP class method) (test_start_end_logits.TestStartEndLogits class method) (test_static_compressed_buffer.TestSCBuffer class method) (test_tanh.TestTorchOP class method) (test_text_encoder.TestTextEncoder class method) (test_text_encoder_bf16.TestTextEncoderBF16 class method) (test_tf_utils.TestTfUtils class method) (test_token_type_embeddings.TestTokenTypeEmbeddings class method) (test_transpose.TestTorchOP class method) (test_transpose_batch_matmul.TestTransposeBatchMatMul class method) (test_tts.TestTTS class method) (test_two_linear.TestTorchLinear class method) (test_unet.TestUnet class method) (test_unet_bf16.TestUnetBF16 class method) (test_unet_qat.TestUnet class method) (test_unsqueeze.TestTorchOP class method) (test_vae_decoder.TestVaeDecoder class method) (test_vae_decoder_bf16.TestVaeDecoderBF16 class method) (test_weight_sharing_acc.TestWeightSharingAcc class method) (test_weight_sharing_dispatcher_tuning_acc.TestWeightSharingDispatcherTuningAcc class method) (test_weight_sharing_dispatcher_tuning_throughtput.TestWeightSharingDispatcherTuningThroughput class method) (test_weight_sharing_throughput.TestWeightSharingThroughput class method)

Shape (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.shape) Sigmoid (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) Silu (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) Sin (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.sin) Size (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.size) SliceMask (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.slicemask) SlicePositionIds (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.slice_position_ids) Softmax (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.softmax) SparseBM25Retriever (class in intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.retrieval_bm25) sparsity_all module Split (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.split) split_all() (in module fastchat.data.split_long_conversation) Sqrt (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) Square (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) SquaredDifference (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) Squeeze (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.squeeze) StableDiffusion_bf16Convert (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.stableDiffusion_bf16Convert) StableDiffusion_CollectQuantInfo (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.stableDiffusion_collectQDQInfo) StableDiffusion_InsertQuantNode (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.stableDiffusion_insertQuantNode) StableDiffusion_MHA (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.stableDiffusion_MHA) StableDiffusion_MHAReshape (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.stableDiffusion_MHAReshape) StableDiffusion_QuantizeFusion (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.stableDiffusion_QuantizeFusion) StableDiffusion_ReshapeFusion (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.stableDiffusion_ReshapeFusion) Stack (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) start_pipeline() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.compile) StartEndLogits (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.start_end_logits) StopGradient (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) store2str() (in module intel_extension_for_transformers.transformers.dynamic.evolution) str2list() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.graph_utils) stream_output() (fastchat.serve.inference.ChatIO method) stream_text2speech() (intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.tts.TextToSpeech method) StreamToLogger (class in fastchat.utils) StridedSlice (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.strided_slice) style() (fastchat.serve.gradio_patch.Chatbot method) SubGraphMatcher (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.subgraph_matcher) SupervisedDataset (class in train)

T

talkingbot module Tanh (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) tearDown() (test_chatbot_build_api.TestChatbotBuilder method) (test_inference.UnitTest method) (test_optimization.TestChatbotBuilder method) (test_rag.TestChatbotBuilder method) (test_voicechat_server.UnitTest method) tearDownClass() (test_add_cls_token.TestAddClsToken class method) (test_add_embeddings.TestAddEmbeddings class method) (test_add_zeros.TestTorchOP class method) (test_attention_output_layer_norm_length_adaptive_keep_indices.TestAttentionReshape class method) (test_attention_reshape.TestAttentionReshape class method) (test_baddbmm.TestTorchOP class method) (test_bert_mini_fp32.TestTorchModel class method) (test_binary_op.TestBinaryOp class method) (test_binaryop.TestTorchOP class method) (test_cast_to.TestCastTo class method) (test_concat.TestTorchOP class method) (test_conv.TestTorchOP class method) (test_conv_int8.TestTorchOP class method) (test_conv_reshape.TestConvReshape class method) (test_decoder_attn_reshape.TestDecoderAttnReshape class method) (test_dispatcher_tuning_acc.TestDispatcherTuningAcc class method) (test_dispatcher_tuning_throughput.TestDispatcherTuningThroughput class method) (test_dolly_pattern.TestTorchOP class method) (test_dynamic_quantization.TestDynamicQuantization class method) (test_electra.TestElectra class method) (test_embedding.TestTorchOP class method) (test_embeddingbag.TestEmbeddingBag class method) (test_english_normalizer.TestTTS class method) (test_execution_options.TestExecutionOptions class method) (test_finetuning.TestFinetuning class method) (test_fwk.TestFWK class method) (test_gather.TestTorchOP class method) (test_gelu.TestTorchOP class method) (test_gpt_int8.TestTorchModel class method) (test_graph_dispatch.TestGraphDispatch class method) (test_graph_optimizer.TestExecutionOptions class method) (test_insert_input_output_data.TestInsertInputOuputData class method) (test_is_supported_onnx_graph.TestIsSupportedOnnxGraph class method) (test_last_layer_shape.TestLastLayerShape class method) (test_layer_norm_with_reduce_mean.TestLayerNormWithReduceMean class method) (test_layer_norm_with_transpose.TestLayerNormWithTranspose class method) (test_layernorm.TestTorchOP class method) (test_linear.TestTorchOP class method) (test_linear_int8.TestTorchLinear class method) (test_llama_pattern.TestTorchOP class method) (test_main.TestMain class method) (test_matmul.TestTorchOP class method) (test_matmul_int8.TestTorchOP class method) (test_matmul_with_bias_relu.TestMatmulWithBiasRelu class method) (test_matmul_with_bias_sigmoid.TestMatMulWithBiasSigmoid class method) (test_matmul_with_bias_tanh.TestMatmulWithBiasTanh class method) (test_merged_embeddingbag.TestMergedEmbeddingbag class method) (test_neox_rotary_pos_emb.TestTorchOP class method) (test_onnx_utils.TestOnnxUtils class method) (test_operator_adaptor.TestOperatorAdaptor class method) (test_ops.TestOps class method) (test_padding_seq.TestTorchOP class method) (test_padding_sequence.TestPaddingSequence class method) (test_pattern_dispatch.TestPatternDispatch class method) (test_permute.TestTorchOP class method) (test_position_embeddings.TestPositionEmbeddings class method) (test_pow.TestTorchOP class method) (test_primitive_cache_acc.TestPrimitiveCacheAcc class method) (test_primitive_cache_throughput.TestPrimitiveCacheThroughput class method) (test_qkv_merge.TestQKVMerge class method) (test_qkv_reshape.TestAttentionReshape class method) (test_quant_onnx_execute.TestQuantOnnxExecute class method) (test_reshape_after_restore_hidden_states.TestLayerNormWithReduceMean class method) (test_reshape_before_and_after_attention_out_layer_norm_gather_elements.TestAttentionReshape class method) (test_reshape_before_restore_hidden_states.TestLayerNormWithReduceMean class method) (test_size.TestTorchOP class method) (test_slice.TestTorchOP class method) (test_softmax.TestTorchOP class method) (test_start_end_logits.TestStartEndLogits class method) (test_static_compressed_buffer.TestSCBuffer class method) (test_tanh.TestTorchOP class method) (test_text_encoder.TestTextEncoder class method) (test_text_encoder_bf16.TestTextEncoderBF16 class method) (test_tf_utils.TestTfUtils class method) (test_token_type_embeddings.TestTokenTypeEmbeddings class method) (test_transpose.TestTorchOP class method) (test_transpose_batch_matmul.TestTransposeBatchMatMul class method) (test_tts.TestTTS class method) (test_two_linear.TestTorchLinear class method) (test_unet.TestUnet class method) (test_unet_bf16.TestUnetBF16 class method) (test_unet_qat.TestUnet class method) (test_unsqueeze.TestTorchOP class method) (test_vae_decoder.TestVaeDecoder class method) (test_vae_decoder_bf16.TestVaeDecoderBF16 class method) (test_weight_sharing_acc.TestWeightSharingAcc class method) (test_weight_sharing_dispatcher_tuning_acc.TestWeightSharingDispatcherTuningAcc class method) (test_weight_sharing_dispatcher_tuning_throughtput.TestWeightSharingDispatcherTuningThroughput class method) (test_weight_sharing_throughput.TestWeightSharingThroughput class method) Tensor (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.tensor) TensorflowExtractor (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.extractors.tf_extractor) TensorSliceDataset (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) test_add_cls_token module test_add_embeddings module test_add_zeros module test_asr module test_attention_output_layer_norm_length_adaptive_keep_indices module test_attention_reshape module test_baddbmm module test_bert_mini_fp32 module test_binary_op module test_binaryop module test_cast_to module test_chatbot_build_api module test_cli module test_concat module test_conv module test_conv_int8 module test_conv_reshape module test_decoder_attn_reshape module test_dispatcher_tuning_acc module test_dispatcher_tuning_throughput module test_dolly_pattern module test_dynamic_quantization module test_electra module test_embedding module test_embeddingbag module test_english_normalizer module test_execution_options module test_finetuning module test_fwk module test_gather module test_gelu module test_gpt_int8 module test_graph_dispatch module test_graph_optimizer module test_inference module test_insert_input_output_data module test_is_supported_onnx_graph module test_is_supported_onnx_graph() (test_is_supported_onnx_graph.TestIsSupportedOnnxGraph method) test_last_layer_shape module test_layer_norm_with_reduce_mean module test_layer_norm_with_transpose module test_layernorm module test_linear module test_linear_int8 module test_llama_pattern module test_main module test_matmul module test_matmul_int8 module test_matmul_with_bias_relu module test_matmul_with_bias_sigmoid module test_matmul_with_bias_tanh module test_merged_embeddingbag module test_model module test_neox_rotary_pos_emb module test_onnx_utils module test_operator_adaptor module test_ops module test_optimization module test_padding_seq module test_padding_sequence module test_pattern_dispatch module test_permute module test_position_embeddings module test_pow module

test_primitive_cache_acc module test_primitive_cache_throughput module test_qkv_merge module test_qkv_reshape module test_quant_onnx_execute module test_rag module test_reshape_after_restore_hidden_states module test_reshape_before_and_after_attention_out_layer_norm_gather_elements module test_reshape_before_restore_hidden_states module test_size module test_slice module test_softmax module test_start_end_logits module test_static_compressed_buffer module test_tanh module test_text_encoder module test_text_encoder_bf16 module test_textchat_server module test_textchat_with_retrieval_server module test_tf_utils module test_token_type_embeddings module test_transpose module test_transpose_batch_matmul module test_tts module test_two_linear module test_unet module test_unet_bf16 module test_unet_qat module test_unsqueeze module test_vae_decoder module test_vae_decoder_bf16 module test_voicechat_server module test_weight_sharing_acc module test_weight_sharing_dispatcher_tuning_acc module test_weight_sharing_dispatcher_tuning_throughtput module test_weight_sharing_throughput module TestAddClsToken (class in test_add_cls_token) TestAddEmbeddings (class in test_add_embeddings) TestASR (class in test_asr) TestAttentionReshape (class in test_attention_output_layer_norm_length_adaptive_keep_indices) (class in test_attention_reshape) (class in test_qkv_reshape) (class in test_reshape_before_and_after_attention_out_layer_norm_gather_elements) TestBinaryOp (class in test_binary_op) TestCastTo (class in test_cast_to) TestChatbotBuilder (class in test_chatbot_build_api) (class in test_optimization) (class in test_rag) TestConvReshape (class in test_conv_reshape) TestDecoderAttnReshape (class in test_decoder_attn_reshape) TestDispatcherTuningAcc (class in test_dispatcher_tuning_acc) TestDispatcherTuningThroughput (class in test_dispatcher_tuning_throughput) TestDynamicQuantization (class in test_dynamic_quantization) TestElectra (class in test_electra) TestEmbeddingBag (class in test_embeddingbag) TestExecutionOptions (class in test_execution_options) (class in test_graph_optimizer) TestFinetuning (class in test_finetuning) TestFWK (class in test_fwk) TestGraphDispatch (class in test_graph_dispatch) TestInsertInputOuputData (class in test_insert_input_output_data) TestIsSupportedOnnxGraph (class in test_is_supported_onnx_graph) TestLastLayerShape (class in test_last_layer_shape) TestLayerNormWithReduceMean (class in test_layer_norm_with_reduce_mean) (class in test_reshape_after_restore_hidden_states) (class in test_reshape_before_restore_hidden_states) TestLayerNormWithTranspose (class in test_layer_norm_with_transpose) TestMain (class in test_main) TestMatmulWithBiasRelu (class in test_matmul_with_bias_relu) TestMatMulWithBiasSigmoid (class in test_matmul_with_bias_sigmoid) TestMatmulWithBiasTanh (class in test_matmul_with_bias_tanh) TestMergedEmbeddingbag (class in test_merged_embeddingbag) TestOnnxUtils (class in test_onnx_utils) TestOperatorAdaptor (class in test_operator_adaptor) TestOps (class in test_ops) TestPaddingSequence (class in test_padding_sequence) TestPatternDispatch (class in test_pattern_dispatch) TestPositionEmbeddings (class in test_position_embeddings) TestPrimitiveCacheAcc (class in test_primitive_cache_acc) TestPrimitiveCacheThroughput (class in test_primitive_cache_throughput) TestQKVMerge (class in test_qkv_merge) TestQuantOnnxExecute (class in test_quant_onnx_execute) TestSCBuffer (class in test_static_compressed_buffer) TestStartEndLogits (class in test_start_end_logits) TestTextEncoder (class in test_text_encoder) TestTextEncoderBF16 (class in test_text_encoder_bf16) TestTfUtils (class in test_tf_utils) TestTokenTypeEmbeddings (class in test_token_type_embeddings) TestTorchLinear (class in test_linear_int8) (class in test_two_linear) TestTorchModel (class in test_bert_mini_fp32) (class in test_gpt_int8) TestTorchOP (class in test_add_zeros) (class in test_baddbmm) (class in test_binaryop) (class in test_concat) (class in test_conv) (class in test_conv_int8) (class in test_dolly_pattern) (class in test_embedding) (class in test_gather) (class in test_gelu) (class in test_layernorm) (class in test_linear) (class in test_llama_pattern) (class in test_matmul) (class in test_matmul_int8) (class in test_neox_rotary_pos_emb) (class in test_padding_seq) (class in test_permute) (class in test_pow) (class in test_size) (class in test_slice) (class in test_softmax) (class in test_tanh) (class in test_transpose) (class in test_unsqueeze) TestTransposeBatchMatMul (class in test_transpose_batch_matmul) TestTTS (class in test_english_normalizer) (class in test_tts) TestUnet (class in test_unet) (class in test_unet_qat) TestUnetBF16 (class in test_unet_bf16) TestVaeDecoder (class in test_vae_decoder) TestVaeDecoderBF16 (class in test_vae_decoder_bf16) TestWeightSharingAcc (class in test_weight_sharing_acc) TestWeightSharingDispatcherTuningAcc (class in test_weight_sharing_dispatcher_tuning_acc) TestWeightSharingDispatcherTuningThroughput (class in test_weight_sharing_dispatcher_tuning_throughtput) TestWeightSharingThroughput (class in test_weight_sharing_throughput) text2speech() (intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.tts.TextToSpeech method) text_generation_augmentation() (intel_extension_for_transformers.utils.data_augmentation.DataAugmentation method) TextChatClientExecutor (class in intel_extension_for_transformers.neural_chat.server.neuralchat_client) TextEncoder_AttentionMaskAddReshape (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.textEncoder_AttentionMaskAddReshape) TextEncoder_AttentionReshape (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.textEncoder_AttentionReshape) TextEncoder_CasualAttentionMask (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.textEncoder_causal_attention_mask) TextEncoder_KVReshape (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.textEncoder_KVReshape) TextEncoder_MulReshape (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.textEncoder_MulReshape) TextEncoder_QReshape (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.textEncoder_QReshape) TextEncoder_SoftmaxReshape (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.textEncoder_SoftmaxReshape) TextEncoder_WordEmbedding (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.textEncdoer_word_embedding) TextToSpeech (class in intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.tts) TextVoiceChatExecutor (class in intel_extension_for_transformers.neural_chat.cli.cli_commands) TF_DTYPE_ID (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.tf_utils) tf_extract_operator() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.tf_utils) TFDataloader (class in intel_extension_for_transformers.transformers.utils.utility_tf) TFDistillationConfig (class in intel_extension_for_transformers.transformers.config) TFOptimization (class in intel_extension_for_transformers.transformers.optimizer_tf) Tile (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) to_gradio_chatbot() (fastchat.conversation.Conversation method) to_openai_api_messages() (fastchat.conversation.Conversation method) TokenTypeEmbeddings (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.token_type_embeddings) TokenTypeEmbeddingsV1 (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.token_type_embeddings_v1) TokenTypeIds (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) TopK (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.top_k) torch_extract_operator() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.torch_utils) TorchEmbedding (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.torch_embedding) TorchExtractor (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.extractors.torch_extractor) TorchInnerProductInsertBias (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.torch_ip_insert_bias) TorchInsertBF16Node (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.quant_gather_to_bf16) (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.torchinsertbf16node) TorchPaddingSequence (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.torchpaddingsquence) TorchUnpackBaddbmm (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.torch_unpack_baddbmm) train module train() (intel_extension_for_transformers.transformers.trainer.BaseTrainer method) train_lora module train_mem module 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.llm.runtime.deprecated.compile.sub_graph.transformer2Dmodel_AttentionMaskAddReshape) Transformer2Dmodel_ConstantOfShapeWithMul (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transformer2Dmodel_ConstantOfShapeWithMul) Transformer2Dmodel_EncoderHiddenStatesReshape (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transformer2Dmodel_encoderHiddenStatesReshape) Transformer2Dmodel_FFNInputSlice (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transformer2Dmodel_FFNSlice) Transformer2Dmodel_FFNInputSlice_1 (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transformer2Dmodel_FFNSlice_1) Transformer2Dmodel_GetSampleBatch (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transformer2Dmodel_getSampleBatch) Transformer2Dmodel_QKVPreReshape (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transformer2Dmodel_QKVPreReshape) Transformer2Dmodel_QKVReshape (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transformer2Dmodel_QKVReshape) Transformer2Dmodel_QKVReshapeTo4D (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transformer2Dmodel_QKVReshape4D) Transformer2Dmodel_SampleSlice (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transformer2Dmodel_sampleSlice) Transpose (class in intel_extension_for_transformers.llm.runtime.deprecated.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.llm.runtime.deprecated.compile.graph.graph.Graph method) TransposeBatchMatMul (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops) (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.transpose_batch_matmul) tts_finetuning module

U

uni_pro() (in module intel_extension_for_transformers.neural_chat.pipeline.plugins.retrieval.indexing.context_utils) UnitTest (class in test_cli) (class in test_inference) (class in test_textchat_server) (class in test_textchat_with_retrieval_server) (class in test_voicechat_server)

Unpack (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.unpack) Unsqueeze (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.unsqueeze) 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() (fastchat.conversation.Conversation method)

V

vad_collector() (in module intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.utils.split_audio) View (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.view)

violates_moderation() (in module fastchat.utils) VoiceChatClientExecutor (class in intel_extension_for_transformers.neural_chat.server.neuralchat_client)

W

warn() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.logger) warning() (in module intel_extension_for_transformers.llm.runtime.deprecated.compile.logger) weight_optimization() (intel_extension_for_transformers.llm.runtime.deprecated.compile.optimizer.Optimizer method) weightonly_test module

WeightPruningConfig (class in intel_extension_for_transformers.transformers.config) Where (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.where) WordEmbeddings (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.sub_graph.word_embeddings) write_checkpoints_json() (in module intel_extension_for_transformers.neural_chat.models.model_utils) write_wave() (in module intel_extension_for_transformers.neural_chat.pipeline.plugins.audio.utils.split_audio)

Z

Zeros (class in intel_extension_for_transformers.llm.runtime.deprecated.compile.ops.empty_ops)