Class List#
|
Mobilint SDK qb Compiler v1.3
MCS002-EN
|
Class List
Here are the classes, structs, unions and interfaces with brief descriptions:
[detail level 1234567]
| Nqbcompiler | |
| Ncalibration | |
| Npreprocess | |
| CCenterCrop | Perform a centered crop on the image |
| CGetImage | Retrieve an image tensor from a file path or NumPy array using OpenCV |
| CGetNpy | Load NumPy data from an in-memory array or a .npy file |
| CNormalize | Apply mean/std normalization to images |
| CNpyNormalize | |
| CNpyPad | Pad NumPy arrays to a desired shape |
| CPad | Pad images to a target shape or to meet a size divisor |
| Cpreproc_builder | Build a calibration preprocessing pipeline from a YAML or dict configuration |
| CResize | Resize images with optional aspect-ratio preservation |
| CResizeTorch | |
| CSetOrder | |
| Nconfigs | Auto-generated config module from config_schema.yaml |
| Nenums | Auto-generated enum definitions from config_schema.yaml |
| CAccumulationDevice | |
| CDevice | |
| CHessianDtype | |
| CInferenceScheme | |
| CMethod | |
| CMoeExpertSelectionMode | |
| CQuantMethod | |
| CQuantMode | |
| CQuantOutput | |
| CSearchType | |
| Nmodels | Auto-generated Pydantic models from config_schema.yaml |
| CBitConfig | Configuration for bit precision |
| CLayerOverrides | |
| CSaveInfo | |
| CTransformer | |
| CActivation | |
| CFfn | FFN activation bit-widths (int shorthand sets all sublayers) |
| CMixedPrecision | |
| CActivation | |
| CWeight | |
| CWeight | |
| CFfn | FFN weight bit-widths (int shorthand sets all sublayers) |
| CCalibrationConfig | Configuration for calibration during quantization |
| CFastDist | |
| CGroupLut | |
| CHistogram | |
| CLayerOverrides | |
| CMaxPercentile | |
| COptimizeLut | |
| CStatistics | |
| CCompileConfig | Unified compilation configuration for Mobilint MXQ compilation |
| CEquivalentTransformationConfig | Configuration for equivalent transformation techniques |
| CFeedForwardMultiLut | Feed-forward multi-LUT transformation |
| CFlattenQuant | |
| CHeadOutChRotation | |
| CInRotation | |
| CNormConv | |
| COptimizeFfn | |
| CQk | |
| CQkRotation | |
| CSpinR1 | |
| CSpinR2 | |
| CUd | |
| CVo | |
| CHessianQuantConfig | Configuration for HessianQuant algorithm |
| CAttributes | |
| CLayerBiasCorrectionConfig | Configuration for calibration-derived layer bias correction |
| CAttributes | |
| CLlmConfig | Configuration for Large Language Model (LLM) compilation |
| CAttributes | |
| CCalibration | |
| CDebug | |
| CRuntime | |
| CLoadScaleConfig | |
| CModConfig | Configuration for Minimum Output Difference algorithm |
| CAttributes | |
| CLearningRates | |
| CLoss | |
| CPostProcessing | |
| CTraining | |
| CMoeConfig | Sparse MoE expert-selection configuration (calibration only) |
| CPreprocessingConfig | Configuration for input preprocessing pipeline |
| CResourceManagementConfig | Configuration for resource management during model compilation |
| CWeightMemory | Weight memory management configuration |
| CRuntimeOptions | Runtime options for compilation |
| CSaveSampleConfig | Sample data generation and saving configuration |
| CSearchWeightScaleConfig | Configuration for weight scale search |
| CTransformer | Transformer components for weight scale search |
| CUint8InputConfig | Configuration for uint8 input handling |
| Npresets | Auto-generated preset definitions from config_schema.yaml |
| CPreset | Preset utility class |
| Nfrontend | |
| CModel_Dict | Wrapper around the Mobilint compiler to support compilation and inference workflows |
| CGetText | Extract text strings from raw inputs |
| CTokenizeToEmbedding | Convert tokenized text into embeddings using a Hugging Face model |
| CYoloPre | Apply YOLO-style resize, padding, and normalization to images |
Generated by
1.14.0