Class Index

Class Index#

Mobilint SDK qb Compiler: Class Index

Mobilint SDK qb Compiler v1.1

MCS002-KR

A | B | C | D | E | F | G | H | I | L | M | N | O | P | Q | R | S | T | U | V | W | Y

A: BitConfig.Transformer.Activation (qbcompiler.configs.models); LlmConfig.Attributes (qbcompiler.configs.models); ModConfig.Attributes (qbcompiler.configs.models); OptqConfig.Attributes (qbcompiler.configs.models)

B: BitConfig (qbcompiler.configs.models)

C: LlmConfig.Attributes.Calibration (qbcompiler.configs.models); CalibrationConfig (qbcompiler.configs.models); CenterCrop (qbcompiler.calibration.preprocess); CompileConfig (qbcompiler.configs.models)

D: LlmConfig.Attributes.Debug (qbcompiler.configs.models); Device (qbcompiler.configs.enums)

E: EquivalentTransformationConfig (qbcompiler.configs.models)

F: CalibrationConfig.FastDist (qbcompiler.configs.models); EquivalentTransformationConfig.FeedForwardMultiLut (qbcompiler.configs.models); EquivalentTransformationConfig.FlattenQuant (qbcompiler.configs.models)

G: GetImage (qbcompiler.calibration.preprocess); GetNpy (qbcompiler.calibration.preprocess); GetText

H: EquivalentTransformationConfig.HeadOutChRotation (qbcompiler.configs.models); CalibrationConfig.Histogram (qbcompiler.configs.models)

I: InferenceScheme (qbcompiler.configs.enums); EquivalentTransformationConfig.InRotation (qbcompiler.configs.models)

L: BitConfig.LayerOverrides (qbcompiler.configs.models); CalibrationConfig.LayerOverrides (qbcompiler.configs.models); ModConfig.Attributes.LearningRates (qbcompiler.configs.models); LlmConfig (qbcompiler.configs.models); ModConfig.Attributes.Loss (qbcompiler.configs.models); LutClusteringMethod (qbcompiler.configs.enums)

M: CalibrationConfig.MaxPercentile (qbcompiler.configs.models); Method (qbcompiler.configs.enums); BitConfig.Transformer.MixedPrecision (qbcompiler.configs.models); ModConfig (qbcompiler.configs.models); Model_Dict (qbcompiler.frontend)

N: Normalize (qbcompiler.calibration.preprocess); EquivalentTransformationConfig.NormConv (qbcompiler.configs.models); NpyNormalize (qbcompiler.calibration.preprocess); NpyPad (qbcompiler.calibration.preprocess)

O: EquivalentTransformationConfig.OptimizeFfn (qbcompiler.configs.models); OptqConfig (qbcompiler.configs.models)

P: Pad (qbcompiler.calibration.preprocess); ModConfig.Attributes.PostProcessing (qbcompiler.configs.models); preproc_builder (qbcompiler.calibration.preprocess); PreprocessingConfig (qbcompiler.configs.models); Preset (qbcompiler.configs.presets)

Q: EquivalentTransformationConfig.Qk (qbcompiler.configs.models); EquivalentTransformationConfig.QkRotation (qbcompiler.configs.models); QuantMethod (qbcompiler.configs.enums); QuantMode (qbcompiler.configs.enums); QuantOutput (qbcompiler.configs.enums)

R: Resize (qbcompiler.calibration.preprocess); ResizeTorch (qbcompiler.calibration.preprocess); ResourceManagementConfig (qbcompiler.configs.models); LlmConfig.Attributes.Runtime (qbcompiler.configs.models); RuntimeOptions (qbcompiler.configs.models)

S: BitConfig.SaveInfo (qbcompiler.configs.models); SaveSampleConfig (qbcompiler.configs.models); SearchType (qbcompiler.configs.enums); SearchWeightScaleConfig (qbcompiler.configs.models); SetOrder (qbcompiler.calibration.preprocess); EquivalentTransformationConfig.SpinR1 (qbcompiler.configs.models); EquivalentTransformationConfig.SpinR2 (qbcompiler.configs.models); CalibrationConfig.Statistics (qbcompiler.configs.models)

T: TokenizeToEmbedding; ModConfig.Attributes.Training (qbcompiler.configs.models); BitConfig.Transformer (qbcompiler.configs.models); SearchWeightScaleConfig.Transformer (qbcompiler.configs.models)

U: EquivalentTransformationConfig.Ud (qbcompiler.configs.models); Uint8InputConfig (qbcompiler.configs.models)

V: EquivalentTransformationConfig.Vo (qbcompiler.configs.models)

W: BitConfig.Transformer.Weight (qbcompiler.configs.models); ResourceManagementConfig.WeightMemory (qbcompiler.configs.models)

Y: YoloPre