Index _ | A | B | C | D | E | F | G | H | I | L | M | N | O | P | Q | R | S | T | U | V | W _ __add__() (intel_npu_acceleration_library.backend.Tensor method) __len__() (intel_npu_acceleration_library.backend.Tensor method) __matmul__() (intel_npu_acceleration_library.backend.Tensor method) __mul__() (intel_npu_acceleration_library.backend.Tensor method) __neg__() (intel_npu_acceleration_library.backend.Tensor method) __repr__() (intel_npu_acceleration_library.backend.Tensor method) __str__() (intel_npu_acceleration_library.backend.Tensor method) __sub__() (intel_npu_acceleration_library.backend.Tensor method) __truediv__() (intel_npu_acceleration_library.backend.Tensor method) A acos() (intel_npu_acceleration_library.backend.Tensor method), [1] acosh() (intel_npu_acceleration_library.backend.Tensor method), [1] adapt_output_tensor() (in module intel_npu_acceleration_library.backend.runtime) adapt_weight() (in module intel_npu_acceleration_library.backend.base) add_to_map() (intel_npu_acceleration_library.backend.base.BaseNPUBackendWithPrefetch method) apply_general_optimizations() (in module intel_npu_acceleration_library.compiler) apply_horizontal_fusion() (in module intel_npu_acceleration_library.compiler) asin() (intel_npu_acceleration_library.backend.Tensor method), [1] asinh() (intel_npu_acceleration_library.backend.Tensor method), [1] atan() (intel_npu_acceleration_library.backend.Tensor method), [1] atanh() (intel_npu_acceleration_library.backend.Tensor method), [1] AutogradMatMul (class in intel_npu_acceleration_library.nn.autograd) avg_pooling() (intel_npu_acceleration_library.backend.factory.NNFactory method) (intel_npu_acceleration_library.backend.NNFactory method) B backward() (intel_npu_acceleration_library.nn.autograd.AutogradMatMul static method) BaseNPUBackend (class in intel_npu_acceleration_library.backend.base) BaseNPUBackendWithPrefetch (class in intel_npu_acceleration_library.backend.base) bias (intel_npu_acceleration_library.nn.Conv2d property) C ceiling() (intel_npu_acceleration_library.backend.Tensor method), [1] chunk() (intel_npu_acceleration_library.backend.Tensor method) clamp() (intel_npu_acceleration_library.backend.Tensor method), [1] clear_cache() (in module intel_npu_acceleration_library.backend) (in module intel_npu_acceleration_library.backend.runtime) compile() (in module intel_npu_acceleration_library) (in module intel_npu_acceleration_library.compiler) (intel_npu_acceleration_library.backend.factory.NNFactory method) (intel_npu_acceleration_library.backend.NNFactory method) CompilerConfig (class in intel_npu_acceleration_library.compiler) compress_to_i4() (in module intel_npu_acceleration_library.quantization) concat() (intel_npu_acceleration_library.backend.factory.NNFactory method) (intel_npu_acceleration_library.backend.NNFactory method) constant() (intel_npu_acceleration_library.backend.factory.NNFactory method) (intel_npu_acceleration_library.backend.NNFactory method) Conv2d (class in intel_npu_acceleration_library.nn) Convolution (class in intel_npu_acceleration_library.backend) convolution() (intel_npu_acceleration_library.backend.factory.NNFactory method) (intel_npu_acceleration_library.backend.NNFactory method) cos() (intel_npu_acceleration_library.backend.Tensor method), [1] cosh() (intel_npu_acceleration_library.backend.Tensor method), [1] create_model() (intel_npu_acceleration_library.nn.Module method) create_npu_kernels() (in module intel_npu_acceleration_library.compiler) create_parameters() (intel_npu_acceleration_library.backend.base.BaseNPUBackendWithPrefetch method) D delattr_recursively() (in module intel_npu_acceleration_library.optimizations) dim() (intel_npu_acceleration_library.backend.Tensor method) dtype (intel_npu_acceleration_library.backend.Tensor property) E elu() (intel_npu_acceleration_library.backend.Tensor method), [1] erf() (intel_npu_acceleration_library.backend.Tensor method), [1] exp() (intel_npu_acceleration_library.backend.Tensor method), [1] extract_tensors_from_arguments() (intel_npu_acceleration_library.nn.Module method) F factory (intel_npu_acceleration_library.backend.Tensor attribute) factory_forward() (intel_npu_acceleration_library.nn.Module method) flatten() (intel_npu_acceleration_library.backend.Tensor method) floor() (intel_npu_acceleration_library.backend.Tensor method), [1] forward() (in module intel_npu_acceleration_library.compiler) (intel_npu_acceleration_library.nn.autograd.AutogradMatMul static method) (intel_npu_acceleration_library.nn.Conv2d method) (intel_npu_acceleration_library.nn.Linear method) (intel_npu_acceleration_library.nn.linear.Linear method) (intel_npu_acceleration_library.nn.linear.QuantizedLinear method) (intel_npu_acceleration_library.nn.LlamaAttention method) (intel_npu_acceleration_library.nn.llm.FusedLlamaMLP method) (intel_npu_acceleration_library.nn.llm.LlamaAttention method) (intel_npu_acceleration_library.nn.llm.PhiMLP method) (intel_npu_acceleration_library.nn.Module method) (intel_npu_acceleration_library.nn.PhiMLP method) (intel_npu_acceleration_library.nn.QuantizedLinear method) from_pretrained() (intel_npu_acceleration_library.NPUAutoModel method) (intel_npu_acceleration_library.NPUModel static method) (intel_npu_acceleration_library.NPUModelForCausalLM method) (intel_npu_acceleration_library.NPUModelForSeq2SeqLM method) fromTensor() (intel_npu_acceleration_library.nn.Linear static method) (intel_npu_acceleration_library.nn.linear.Linear static method) fromTorch() (intel_npu_acceleration_library.nn.Conv2d static method) (intel_npu_acceleration_library.nn.Linear static method) (intel_npu_acceleration_library.nn.linear.Linear static method) (intel_npu_acceleration_library.nn.LlamaAttention static method) (intel_npu_acceleration_library.nn.llm.FusedLlamaMLP static method) (intel_npu_acceleration_library.nn.llm.LlamaAttention static method) (intel_npu_acceleration_library.nn.llm.PhiMLP static method) (intel_npu_acceleration_library.nn.PhiMLP static method) fuse_linear_layers() (in module intel_npu_acceleration_library.optimizations) FusedLlamaMLP (class in intel_npu_acceleration_library.nn.llm) G generate_with_static_shape() (in module intel_npu_acceleration_library.nn.llm) get_backend_dtype() (intel_npu_acceleration_library.backend.factory.NNFactory method) (intel_npu_acceleration_library.backend.NNFactory method) get_driver_version() (in module intel_npu_acceleration_library.backend) get_tensor_dtype() (intel_npu_acceleration_library.backend.factory.NNFactory method) (intel_npu_acceleration_library.backend.NNFactory method) get_tensor_recursively() (intel_npu_acceleration_library.backend.factory.NNFactory method) (intel_npu_acceleration_library.backend.NNFactory method) get_tensor_shape() (intel_npu_acceleration_library.backend.factory.NNFactory method) (intel_npu_acceleration_library.backend.NNFactory method) grn() (intel_npu_acceleration_library.backend.Tensor method), [1] H horizontal_fusion_linear() (in module intel_npu_acceleration_library.optimizations) hsigmoid() (intel_npu_acceleration_library.backend.Tensor method), [1] hswish() (intel_npu_acceleration_library.backend.Tensor method), [1] I intel_npu_acceleration_library module intel_npu_acceleration_library (C++ type) intel_npu_acceleration_library.backend module intel_npu_acceleration_library.backend.base module intel_npu_acceleration_library.backend.factory module intel_npu_acceleration_library.backend.linear module intel_npu_acceleration_library.backend.matmul module intel_npu_acceleration_library.backend.mlp module intel_npu_acceleration_library.backend.qlinear module intel_npu_acceleration_library.backend.qmatmul module intel_npu_acceleration_library.backend.runtime module intel_npu_acceleration_library.compiler module intel_npu_acceleration_library.functional module intel_npu_acceleration_library.functional.scaled_dot_product_attention module intel_npu_acceleration_library.nn module intel_npu_acceleration_library.nn.autograd module intel_npu_acceleration_library.nn.linear module intel_npu_acceleration_library.nn.llm module intel_npu_acceleration_library.optimizations module intel_npu_acceleration_library.quantization module intel_npu_acceleration_library::_isNPUAvailable (C++ function) intel_npu_acceleration_library::array_to_fp16_worker (C++ function) intel_npu_acceleration_library::compressToI4 (C++ function) intel_npu_acceleration_library::core (C++ member) intel_npu_acceleration_library::create_remote_tensor (C++ function) intel_npu_acceleration_library::driver_version (C++ function) intel_npu_acceleration_library::dtype_from_string (C++ function) intel_npu_acceleration_library::ModelFactory (C++ class) intel_npu_acceleration_library::ModelFactory::abs (C++ function) intel_npu_acceleration_library::ModelFactory::acos (C++ function) intel_npu_acceleration_library::ModelFactory::acosh (C++ function) intel_npu_acceleration_library::ModelFactory::adaptive_average_pool (C++ function) intel_npu_acceleration_library::ModelFactory::adaptive_max_pool (C++ function) intel_npu_acceleration_library::ModelFactory::asin (C++ function) intel_npu_acceleration_library::ModelFactory::asinh (C++ function) intel_npu_acceleration_library::ModelFactory::atan (C++ function) intel_npu_acceleration_library::ModelFactory::atanh (C++ function) intel_npu_acceleration_library::ModelFactory::average_pooling (C++ function) intel_npu_acceleration_library::ModelFactory::ceiling (C++ function) intel_npu_acceleration_library::ModelFactory::clamp (C++ function) intel_npu_acceleration_library::ModelFactory::compile (C++ function) intel_npu_acceleration_library::ModelFactory::concat (C++ function) intel_npu_acceleration_library::ModelFactory::constant (C++ function), [1] intel_npu_acceleration_library::ModelFactory::convert_to (C++ function) intel_npu_acceleration_library::ModelFactory::convolution (C++ function) intel_npu_acceleration_library::ModelFactory::cos (C++ function) intel_npu_acceleration_library::ModelFactory::cosh (C++ function) intel_npu_acceleration_library::ModelFactory::eltwise_add (C++ function) intel_npu_acceleration_library::ModelFactory::eltwise_div (C++ function) intel_npu_acceleration_library::ModelFactory::eltwise_mul (C++ function) intel_npu_acceleration_library::ModelFactory::elu (C++ function) intel_npu_acceleration_library::ModelFactory::erf (C++ function) intel_npu_acceleration_library::ModelFactory::exp (C++ function) intel_npu_acceleration_library::ModelFactory::floor (C++ function) intel_npu_acceleration_library::ModelFactory::gather (C++ function) intel_npu_acceleration_library::ModelFactory::gelu (C++ function) intel_npu_acceleration_library::ModelFactory::grn (C++ function) intel_npu_acceleration_library::ModelFactory::hsigmoid (C++ function) intel_npu_acceleration_library::ModelFactory::hswish (C++ function) intel_npu_acceleration_library::ModelFactory::linear (C++ function) intel_npu_acceleration_library::ModelFactory::log (C++ function) intel_npu_acceleration_library::ModelFactory::log_softmax (C++ function) intel_npu_acceleration_library::ModelFactory::matmul (C++ function) intel_npu_acceleration_library::ModelFactory::max_pooling (C++ function) intel_npu_acceleration_library::ModelFactory::mish (C++ function) intel_npu_acceleration_library::ModelFactory::ModelFactory (C++ function) intel_npu_acceleration_library::ModelFactory::negative (C++ function) intel_npu_acceleration_library::ModelFactory::normL2 (C++ function) intel_npu_acceleration_library::ModelFactory::operations (C++ member) intel_npu_acceleration_library::ModelFactory::parameter (C++ function) intel_npu_acceleration_library::ModelFactory::parameters (C++ member) intel_npu_acceleration_library::ModelFactory::power (C++ function) intel_npu_acceleration_library::ModelFactory::reduce_max (C++ function) intel_npu_acceleration_library::ModelFactory::reduce_mean (C++ function) intel_npu_acceleration_library::ModelFactory::reduce_min (C++ function) intel_npu_acceleration_library::ModelFactory::reduce_prod (C++ function) intel_npu_acceleration_library::ModelFactory::reduce_sum (C++ function) intel_npu_acceleration_library::ModelFactory::relu (C++ function) intel_npu_acceleration_library::ModelFactory::reshape (C++ function) intel_npu_acceleration_library::ModelFactory::result (C++ function) intel_npu_acceleration_library::ModelFactory::results (C++ member) intel_npu_acceleration_library::ModelFactory::round (C++ function) intel_npu_acceleration_library::ModelFactory::scaled_dot_product_attention (C++ function) intel_npu_acceleration_library::ModelFactory::sigmoid (C++ function) intel_npu_acceleration_library::ModelFactory::sign (C++ function) intel_npu_acceleration_library::ModelFactory::sin (C++ function) intel_npu_acceleration_library::ModelFactory::sinh (C++ function) intel_npu_acceleration_library::ModelFactory::slice (C++ function) intel_npu_acceleration_library::ModelFactory::softmax (C++ function) intel_npu_acceleration_library::ModelFactory::softplus (C++ function) intel_npu_acceleration_library::ModelFactory::softsign (C++ function) intel_npu_acceleration_library::ModelFactory::sqrt (C++ function) intel_npu_acceleration_library::ModelFactory::squeeze (C++ function) intel_npu_acceleration_library::ModelFactory::swish (C++ function) intel_npu_acceleration_library::ModelFactory::tan (C++ function) intel_npu_acceleration_library::ModelFactory::tanh (C++ function) intel_npu_acceleration_library::ModelFactory::transpose (C++ function) intel_npu_acceleration_library::ModelFactory::unsqueeze (C++ function) intel_npu_acceleration_library::npu_compiler_type (C++ member) intel_npu_acceleration_library::npu_parameters (C++ member) intel_npu_acceleration_library::OVInferenceModel (C++ class) intel_npu_acceleration_library::OVInferenceModel::compile_model (C++ function) intel_npu_acceleration_library::OVInferenceModel::compiled_model (C++ member) intel_npu_acceleration_library::OVInferenceModel::create_ov_model (C++ function) intel_npu_acceleration_library::OVInferenceModel::device (C++ member) intel_npu_acceleration_library::OVInferenceModel::getInputTensors (C++ function) intel_npu_acceleration_library::OVInferenceModel::getOutputTensors (C++ function) intel_npu_acceleration_library::OVInferenceModel::infer_request (C++ member) intel_npu_acceleration_library::OVInferenceModel::model (C++ member) intel_npu_acceleration_library::OVInferenceModel::Out (C++ member) intel_npu_acceleration_library::OVInferenceModel::OVInferenceModel (C++ function) intel_npu_acceleration_library::OVInferenceModel::profile (C++ member) intel_npu_acceleration_library::OVInferenceModel::run (C++ function) intel_npu_acceleration_library::OVInferenceModel::saveCompiledModel (C++ function) intel_npu_acceleration_library::OVInferenceModel::saveModel (C++ function) intel_npu_acceleration_library::OVInferenceModel::setActivations (C++ function) intel_npu_acceleration_library::OVInferenceModel::setInputTensor (C++ function) intel_npu_acceleration_library::OVInferenceModel::setOutputTensor (C++ function) intel_npu_acceleration_library::OVInferenceModel::setWeights (C++ function) intel_npu_acceleration_library::OVInferenceModel::wt_thread (C++ member) intel_npu_acceleration_library::OVInferenceModel::X (C++ member) intel_npu_acceleration_library::OVInferenceModel::~OVInferenceModel (C++ function) intel_npu_acceleration_library::Parameter (C++ class) intel_npu_acceleration_library::Parameter::data (C++ member) intel_npu_acceleration_library::Parameter::get_size (C++ function) intel_npu_acceleration_library::Parameter::Parameter (C++ function), [1], [2], [3] intel_npu_acceleration_library::Parameter::quantized (C++ member) intel_npu_acceleration_library::Parameter::set_data (C++ function) intel_npu_acceleration_library::Parameter::shape (C++ member) intel_npu_acceleration_library::Parameter::~Parameter (C++ function) intel_npu_acceleration_library::Parameters (C++ class) intel_npu_acceleration_library::Parameters::add_parameter (C++ function), [1], [2], [3] intel_npu_acceleration_library::Parameters::get_parameters (C++ function) intel_npu_acceleration_library::Parameters::parameters (C++ member) intel_npu_acceleration_library::ParameterWithConversion (C++ class) intel_npu_acceleration_library::ParameterWithConversion::data (C++ member) intel_npu_acceleration_library::ParameterWithConversion::ParameterWithConversion (C++ function) intel_npu_acceleration_library::ParameterWithConversion::scale (C++ member) intel_npu_acceleration_library::ParameterWithConversion::set_data (C++ function) intel_npu_acceleration_library::Shape (C++ class) intel_npu_acceleration_library::Shape::dimensions (C++ member) intel_npu_acceleration_library::Shape::get_size (C++ function) intel_npu_acceleration_library::Shape::operator[] (C++ function) intel_npu_acceleration_library::Shape::Shape (C++ function), [1] intel_npu_acceleration_library::to_fp16 (C++ function) intel_npu_acceleration_library::vector_to_fp16 (C++ function) L Linear (class in intel_npu_acceleration_library.backend) (class in intel_npu_acceleration_library.backend.linear) (class in intel_npu_acceleration_library.nn) (class in intel_npu_acceleration_library.nn.linear) linear() (intel_npu_acceleration_library.backend.factory.NNFactory method) (intel_npu_acceleration_library.backend.NNFactory method) LlamaAttention (class in intel_npu_acceleration_library.nn) (class in intel_npu_acceleration_library.nn.llm) load_wt_fn() (intel_npu_acceleration_library.backend.base.BaseNPUBackendWithPrefetch method) log() (intel_npu_acceleration_library.backend.Tensor method), [1] lower_linear() (in module intel_npu_acceleration_library.compiler) lshift_insert() (in module intel_npu_acceleration_library.nn.llm) M MatMul (class in intel_npu_acceleration_library.backend) (class in intel_npu_acceleration_library.backend.matmul) matmul() (intel_npu_acceleration_library.backend.factory.NNFactory method) (intel_npu_acceleration_library.backend.NNFactory method) max() (intel_npu_acceleration_library.backend.Tensor method), [1] max_pooling() (intel_npu_acceleration_library.backend.factory.NNFactory method) (intel_npu_acceleration_library.backend.NNFactory method) mean() (intel_npu_acceleration_library.backend.Tensor method), [1] min() (intel_npu_acceleration_library.backend.Tensor method), [1] mish() (intel_npu_acceleration_library.backend.Tensor method), [1] MLP (class in intel_npu_acceleration_library.backend) (class in intel_npu_acceleration_library.backend.mlp) module intel_npu_acceleration_library intel_npu_acceleration_library.backend intel_npu_acceleration_library.backend.base intel_npu_acceleration_library.backend.factory intel_npu_acceleration_library.backend.linear intel_npu_acceleration_library.backend.matmul intel_npu_acceleration_library.backend.mlp intel_npu_acceleration_library.backend.qlinear intel_npu_acceleration_library.backend.qmatmul intel_npu_acceleration_library.backend.runtime intel_npu_acceleration_library.compiler intel_npu_acceleration_library.functional intel_npu_acceleration_library.functional.scaled_dot_product_attention intel_npu_acceleration_library.nn intel_npu_acceleration_library.nn.autograd intel_npu_acceleration_library.nn.linear intel_npu_acceleration_library.nn.llm intel_npu_acceleration_library.optimizations intel_npu_acceleration_library.quantization Module (class in intel_npu_acceleration_library.nn) module_optimization() (in module intel_npu_acceleration_library.compiler) N NNFactory (class in intel_npu_acceleration_library.backend) (class in intel_npu_acceleration_library.backend.factory) node (intel_npu_acceleration_library.backend.Tensor attribute) normL2() (intel_npu_acceleration_library.backend.factory.NNFactory method) (intel_npu_acceleration_library.backend.NNFactory method) npu() (in module intel_npu_acceleration_library.compiler) npu_available() (in module intel_npu_acceleration_library.backend) NPUAutoModel (class in intel_npu_acceleration_library) NPUModel (class in intel_npu_acceleration_library) NPUModelForCausalLM (class in intel_npu_acceleration_library) NPUModelForSeq2SeqLM (class in intel_npu_acceleration_library) O optimize_llama_attention() (in module intel_npu_acceleration_library.compiler) OVNode (C++ type) P parameter() (intel_npu_acceleration_library.backend.factory.NNFactory method) (intel_npu_acceleration_library.backend.NNFactory method) permute() (intel_npu_acceleration_library.backend.Tensor method) PhiMLP (class in intel_npu_acceleration_library.nn) (class in intel_npu_acceleration_library.nn.llm) power() (intel_npu_acceleration_library.backend.factory.NNFactory method) (intel_npu_acceleration_library.backend.NNFactory method) prefetchWeights() (intel_npu_acceleration_library.backend.base.BaseNPUBackendWithPrefetch method) prod() (intel_npu_acceleration_library.backend.Tensor method), [1] Q QLinear (class in intel_npu_acceleration_library.backend) (class in intel_npu_acceleration_library.backend.qlinear) QMatMul (class in intel_npu_acceleration_library.backend) (class in intel_npu_acceleration_library.backend.qmatmul) quantize_fit() (in module intel_npu_acceleration_library.quantization) quantize_i4_model() (in module intel_npu_acceleration_library.quantization) quantize_i8_model() (in module intel_npu_acceleration_library.quantization) quantize_model() (in module intel_npu_acceleration_library.quantization) quantize_tensor() (in module intel_npu_acceleration_library.quantization) QuantizedLinear (class in intel_npu_acceleration_library.nn) (class in intel_npu_acceleration_library.nn.linear) R reduce_max() (intel_npu_acceleration_library.backend.factory.NNFactory method) (intel_npu_acceleration_library.backend.NNFactory method) reduce_mean() (intel_npu_acceleration_library.backend.factory.NNFactory method) (intel_npu_acceleration_library.backend.NNFactory method) reduce_min() (intel_npu_acceleration_library.backend.factory.NNFactory method) (intel_npu_acceleration_library.backend.NNFactory method) reduce_prod() (intel_npu_acceleration_library.backend.factory.NNFactory method) (intel_npu_acceleration_library.backend.NNFactory method) reduce_sum() (intel_npu_acceleration_library.backend.factory.NNFactory method) (intel_npu_acceleration_library.backend.NNFactory method) relu() (intel_npu_acceleration_library.backend.Tensor method), [1] reshape() (intel_npu_acceleration_library.backend.factory.NNFactory method) (intel_npu_acceleration_library.backend.NNFactory method) (intel_npu_acceleration_library.backend.Tensor method) return_tensor() (intel_npu_acceleration_library.backend.factory.NNFactory method) (intel_npu_acceleration_library.backend.NNFactory method) round() (intel_npu_acceleration_library.backend.Tensor method), [1] run() (intel_npu_acceleration_library.backend.factory.NNFactory method) (intel_npu_acceleration_library.backend.Linear method) (intel_npu_acceleration_library.backend.linear.Linear method) (intel_npu_acceleration_library.backend.MatMul method) (intel_npu_acceleration_library.backend.matmul.MatMul method) (intel_npu_acceleration_library.backend.NNFactory method) (intel_npu_acceleration_library.backend.QLinear method) (intel_npu_acceleration_library.backend.qlinear.QLinear method) (intel_npu_acceleration_library.backend.QMatMul method) (intel_npu_acceleration_library.backend.qmatmul.QMatMul method) (intel_npu_acceleration_library.backend.SDPA method) (intel_npu_acceleration_library.backend.SimpleSDPA method) run_factory() (in module intel_npu_acceleration_library.backend) (in module intel_npu_acceleration_library.backend.runtime) run_matmul() (in module intel_npu_acceleration_library.backend) (in module intel_npu_acceleration_library.backend.runtime) S save() (intel_npu_acceleration_library.backend.base.BaseNPUBackend method) saveCompiledModel() (intel_npu_acceleration_library.backend.base.BaseNPUBackend method) scaled_dot_product_attention() (in module intel_npu_acceleration_library.functional) (in module intel_npu_acceleration_library.functional.scaled_dot_product_attention) SDPA (class in intel_npu_acceleration_library.backend) set_contiguous() (in module intel_npu_acceleration_library.backend.runtime) set_input_tensor() (intel_npu_acceleration_library.backend.factory.NNFactory method) (intel_npu_acceleration_library.backend.NNFactory method) setWeights() (intel_npu_acceleration_library.backend.base.BaseNPUBackendWithPrefetch method) shape (intel_npu_acceleration_library.backend.Tensor property) sigmoid() (intel_npu_acceleration_library.backend.Tensor method), [1] sign() (intel_npu_acceleration_library.backend.Tensor method), [1] SimpleSDPA (class in intel_npu_acceleration_library.backend) sin() (intel_npu_acceleration_library.backend.Tensor method), [1] sinh() (intel_npu_acceleration_library.backend.Tensor method), [1] size() (intel_npu_acceleration_library.backend.Tensor method) slice() (intel_npu_acceleration_library.backend.factory.NNFactory method) (intel_npu_acceleration_library.backend.NNFactory method) softmax() (intel_npu_acceleration_library.backend.Tensor method), [1] softplus() (intel_npu_acceleration_library.backend.Tensor method), [1] sqrt() (intel_npu_acceleration_library.backend.Tensor method), [1] squeeze() (intel_npu_acceleration_library.backend.Tensor method), [1] sum() (intel_npu_acceleration_library.backend.Tensor method), [1] T T (intel_npu_acceleration_library.backend.Tensor property) T() (intel_npu_acceleration_library.backend.Tensor method) tan() (intel_npu_acceleration_library.backend.Tensor method), [1] tanh() (intel_npu_acceleration_library.backend.Tensor method), [1] Tensor (class in intel_npu_acceleration_library.backend) to() (intel_npu_acceleration_library.backend.factory.NNFactory method) (intel_npu_acceleration_library.backend.NNFactory method) (intel_npu_acceleration_library.backend.Tensor method) (intel_npu_acceleration_library.nn.Module method) transpose() (intel_npu_acceleration_library.backend.factory.NNFactory method) (intel_npu_acceleration_library.backend.NNFactory method) (intel_npu_acceleration_library.backend.Tensor method) type() (intel_npu_acceleration_library.backend.Tensor method) U unsqueeze() (intel_npu_acceleration_library.backend.factory.NNFactory method) (intel_npu_acceleration_library.backend.NNFactory method) (intel_npu_acceleration_library.backend.Tensor method), [1] V view() (intel_npu_acceleration_library.backend.Tensor method) W warm_up_decoder_model() (in module intel_npu_acceleration_library.nn.llm) weight (intel_npu_acceleration_library.nn.Conv2d property) weights_quantization() (in module intel_npu_acceleration_library.compiler)