Class Hierarchy

Class Hierarchy#

Mobilint SDK qb Compiler: Class Hierarchy

Mobilint SDK qb Compiler v1.3

MCS002-KR

This inheritance list is sorted roughly, but not completely, alphabetically:

[detail level 12]

CBaseModel
Cqbcompiler.configs.models.BitConfig	Configuration for bit precision
Cqbcompiler.configs.models.BitConfig.LayerOverrides
Cqbcompiler.configs.models.BitConfig.SaveInfo
Cqbcompiler.configs.models.BitConfig.Transformer
Cqbcompiler.configs.models.BitConfig.Transformer.Activation
Cqbcompiler.configs.models.BitConfig.Transformer.Activation.Ffn	FFN activation bit-widths (int shorthand sets all sublayers)
Cqbcompiler.configs.models.BitConfig.Transformer.MixedPrecision
Cqbcompiler.configs.models.BitConfig.Transformer.MixedPrecision.Activation
Cqbcompiler.configs.models.BitConfig.Transformer.MixedPrecision.Weight
Cqbcompiler.configs.models.BitConfig.Transformer.Weight
Cqbcompiler.configs.models.BitConfig.Transformer.Weight.Ffn	FFN weight bit-widths (int shorthand sets all sublayers)
Cqbcompiler.configs.models.CalibrationConfig	Configuration for calibration during quantization
Cqbcompiler.configs.models.CalibrationConfig.FastDist
Cqbcompiler.configs.models.CalibrationConfig.GroupLut
Cqbcompiler.configs.models.CalibrationConfig.Histogram
Cqbcompiler.configs.models.CalibrationConfig.LayerOverrides
Cqbcompiler.configs.models.CalibrationConfig.MaxPercentile
Cqbcompiler.configs.models.CalibrationConfig.OptimizeLut
Cqbcompiler.configs.models.CalibrationConfig.Statistics
Cqbcompiler.configs.models.CompileConfig	Unified compilation configuration for Mobilint MXQ compilation
Cqbcompiler.configs.models.EquivalentTransformationConfig	Configuration for equivalent transformation techniques
Cqbcompiler.configs.models.EquivalentTransformationConfig.FeedForwardMultiLut	Feed-forward multi-LUT transformation
Cqbcompiler.configs.models.EquivalentTransformationConfig.FlattenQuant
Cqbcompiler.configs.models.EquivalentTransformationConfig.HeadOutChRotation
Cqbcompiler.configs.models.EquivalentTransformationConfig.InRotation
Cqbcompiler.configs.models.EquivalentTransformationConfig.NormConv
Cqbcompiler.configs.models.EquivalentTransformationConfig.OptimizeFfn
Cqbcompiler.configs.models.EquivalentTransformationConfig.Qk
Cqbcompiler.configs.models.EquivalentTransformationConfig.QkRotation
Cqbcompiler.configs.models.EquivalentTransformationConfig.SpinR1
Cqbcompiler.configs.models.EquivalentTransformationConfig.SpinR2
Cqbcompiler.configs.models.EquivalentTransformationConfig.Ud
Cqbcompiler.configs.models.EquivalentTransformationConfig.Vo
Cqbcompiler.configs.models.HessianQuantConfig	Configuration for HessianQuant algorithm
Cqbcompiler.configs.models.HessianQuantConfig.Attributes
Cqbcompiler.configs.models.LayerBiasCorrectionConfig	Configuration for calibration-derived layer bias correction
Cqbcompiler.configs.models.LayerBiasCorrectionConfig.Attributes
Cqbcompiler.configs.models.LlmConfig	Configuration for Large Language Model (LLM) compilation
Cqbcompiler.configs.models.LlmConfig.Attributes
Cqbcompiler.configs.models.LlmConfig.Attributes.Calibration
Cqbcompiler.configs.models.LlmConfig.Attributes.Debug
Cqbcompiler.configs.models.LlmConfig.Attributes.Runtime
Cqbcompiler.configs.models.LoadScaleConfig
Cqbcompiler.configs.models.ModConfig	Configuration for Minimum Output Difference algorithm
Cqbcompiler.configs.models.ModConfig.Attributes
Cqbcompiler.configs.models.ModConfig.Attributes.LearningRates
Cqbcompiler.configs.models.ModConfig.Attributes.Loss
Cqbcompiler.configs.models.ModConfig.Attributes.PostProcessing
Cqbcompiler.configs.models.ModConfig.Attributes.Training
Cqbcompiler.configs.models.MoeConfig	Sparse MoE expert-selection configuration (calibration only)
Cqbcompiler.configs.models.PreprocessingConfig	Configuration for input preprocessing pipeline
Cqbcompiler.configs.models.ResourceManagementConfig	Configuration for resource management during model compilation
Cqbcompiler.configs.models.ResourceManagementConfig.WeightMemory	Weight memory management configuration
Cqbcompiler.configs.models.RuntimeOptions	Runtime options for compilation
Cqbcompiler.configs.models.SaveSampleConfig	Sample data generation and saving configuration
Cqbcompiler.configs.models.SearchWeightScaleConfig	Configuration for weight scale search
Cqbcompiler.configs.models.SearchWeightScaleConfig.Transformer	Transformer components for weight scale search
Cqbcompiler.configs.models.Uint8InputConfig	Configuration for uint8 input handling
Cqbcompiler.calibration.preprocess.CenterCrop	Perform a centered crop on the image
CEnum
Cqbcompiler.configs.enums.AccumulationDevice
Cqbcompiler.configs.enums.Device
Cqbcompiler.configs.enums.HessianDtype
Cqbcompiler.configs.enums.InferenceScheme
Cqbcompiler.configs.enums.Method
Cqbcompiler.configs.enums.MoeExpertSelectionMode
Cqbcompiler.configs.enums.QuantMethod
Cqbcompiler.configs.enums.QuantMode
Cqbcompiler.configs.enums.QuantOutput
Cqbcompiler.configs.enums.SearchType
Cqbcompiler.calibration.preprocess.GetImage	Retrieve an image tensor from a file path or NumPy array using OpenCV
Cqbcompiler.calibration.preprocess.GetNpy	Load NumPy data from an in-memory array or a .npy file
CGetText	Extract text strings from raw inputs
CLegacyCompiler
Cqbcompiler.frontend.Model_Dict	Wrapper around the Mobilint compiler to support compilation and inference workflows
Cqbcompiler.calibration.preprocess.Normalize	Apply mean/std normalization to images
Cqbcompiler.calibration.preprocess.NpyNormalize
Cqbcompiler.calibration.preprocess.NpyPad	Pad NumPy arrays to a desired shape
Cqbcompiler.calibration.preprocess.Pad	Pad images to a target shape or to meet a size divisor
Cqbcompiler.calibration.preprocess.preproc_builder	Build a calibration preprocessing pipeline from a YAML or dict configuration
Cqbcompiler.configs.presets.Preset	Preset utility class
Cqbcompiler.calibration.preprocess.Resize	Resize images with optional aspect-ratio preservation
Cqbcompiler.calibration.preprocess.ResizeTorch
Cqbcompiler.calibration.preprocess.SetOrder
Cstr
Cqbcompiler.configs.enums.AccumulationDevice
Cqbcompiler.configs.enums.Device
Cqbcompiler.configs.enums.HessianDtype
Cqbcompiler.configs.enums.InferenceScheme
Cqbcompiler.configs.enums.Method
Cqbcompiler.configs.enums.MoeExpertSelectionMode
Cqbcompiler.configs.enums.QuantMethod
Cqbcompiler.configs.enums.QuantMode
Cqbcompiler.configs.enums.QuantOutput
Cqbcompiler.configs.enums.SearchType
CTokenizeToEmbedding	Convert tokenized text into embeddings using a Hugging Face model
CYoloPre	Apply YOLO-style resize, padding, and normalization to images