Index

A

AlgoConfig (class in quark.torch.pruning.config) (class in quark.torch.quantization.config.config)

AlgoConfigBase (class in quark.torch.pruning.config) AutoSmoothQuantConfig (class in quark.torch.quantization.config.config) AWQConfig (class in quark.torch.quantization.config.config)

B

Bfloat16Spec (class in quark.torch.quantization.config.config) BFP16Scheme (class in quark.torch.quantization.config.template)

BFP16Spec (class in quark.torch.quantization.config.config) BlockwiseTuningConfig (class in quark.torch.pruning.config)

C

Config (class in quark.torch.pruning.config)

ConfigBase (class in quark.torch.pruning.config)

D

DataTypeSpec (class in quark.torch.quantization.config.config)

E

export_gguf() (in module quark.torch.export.api) export_onnx() (in module quark.torch.export.api)

export_safetensors() (in module quark.torch.export.api) ExporterConfig (class in quark.torch.export.config.config)

F

Float16Spec (class in quark.torch.quantization.config.config) FP4PerGroupSpec (class in quark.torch.quantization.config.config) FP6E2M3PerGroupSpec (class in quark.torch.quantization.config.config) FP6E3M2PerGroupSpec (class in quark.torch.quantization.config.config) FP8E4M3PerChannelSpec (class in quark.torch.quantization.config.config) FP8E4M3PerGroupSpec (class in quark.torch.quantization.config.config) FP8E4M3PerTensorSpec (class in quark.torch.quantization.config.config)

FP8E5M2PerChannelSpec (class in quark.torch.quantization.config.config) FP8E5M2PerGroupSpec (class in quark.torch.quantization.config.config) FP8E5M2PerTensorSpec (class in quark.torch.quantization.config.config) FP8Scheme (class in quark.torch.quantization.config.template) freeze() (quark.torch.quantization.api.ModelQuantizer static method) from_dict() (quark.torch.quantization.config.config.QLayerConfig class method) (quark.torch.quantization.config.config.QTensorConfig class method)

G

get() (quark.torch.quantization.config.template.LLMTemplate class method) get_config() (quark.torch.quantization.config.template.LLMTemplate method) get_scheme() (quark.torch.quantization.config.template.QuantizationSchemeCollection method)

get_supported_schemes() (quark.torch.quantization.config.template.LLMTemplate class method) (quark.torch.quantization.config.template.QuantizationSchemeCollection method) GPTAQConfig (class in quark.torch.quantization.config.config) GPTQConfig (class in quark.torch.quantization.config.config)

I

import_model_from_safetensors() (in module quark.torch.export.api) Int2PerGroupSpec (class in quark.torch.quantization.config.config) Int3PerChannelSpec (class in quark.torch.quantization.config.config) Int3PerGroupSpec (class in quark.torch.quantization.config.config) Int4PerChannelSpec (class in quark.torch.quantization.config.config) Int4PerGroupSpec (class in quark.torch.quantization.config.config)

Int4PerTensorSpec (class in quark.torch.quantization.config.config) Int4WeightOnlyPerChannelScheme (class in quark.torch.quantization.config.template) Int4WeightOnlyScheme (class in quark.torch.quantization.config.template) Int8PerChannelSpec (class in quark.torch.quantization.config.config) Int8PerGroupSpec (class in quark.torch.quantization.config.config) Int8PerTensorSpec (class in quark.torch.quantization.config.config) Int8Scheme (class in quark.torch.quantization.config.template)

J

JsonExporterConfig (class in quark.torch.export.config.config)

L

LayerImportancePruneConfig (class in quark.torch.pruning.config) list_available() (quark.torch.quantization.config.template.LLMTemplate class method) LLMTemplate (class in quark.torch.quantization.config.template)

load_params() (in module quark.torch.quantization.api) load_pre_optimization_config_from_file() (in module quark.torch.quantization.config.config) load_quant_algo_config_from_file() (in module quark.torch.quantization.config.config)

M

ModelPruner (class in quark.torch.pruning.api) ModelQuantizer (class in quark.torch.quantization.api) module quark.torch.export.api quark.torch.export.config.config quark.torch.pruning.api quark.torch.pruning.config quark.torch.quantization.api quark.torch.quantization.config.config quark.torch.quantization.config.template

MX6Scheme (class in quark.torch.quantization.config.template) MX6Spec (class in quark.torch.quantization.config.config) MX9Spec (class in quark.torch.quantization.config.config) MXFP4_FP8Scheme (class in quark.torch.quantization.config.template) MXFP4_MXFP6E2M3Scheme (class in quark.torch.quantization.config.template) MXFP4Scheme (class in quark.torch.quantization.config.template) MXFP6E2M3Scheme (class in quark.torch.quantization.config.template) MXFP6E3M2Scheme (class in quark.torch.quantization.config.template)

O

OCP_MXFP4DiffsSpec (class in quark.torch.quantization.config.config) OCP_MXFP4Spec (class in quark.torch.quantization.config.config) OCP_MXFP6E2M3Spec (class in quark.torch.quantization.config.config) OCP_MXFP6E3M2Spec (class in quark.torch.quantization.config.config) OCP_MXFP8E4M3Spec (class in quark.torch.quantization.config.config)

OCP_MXFP8E5M2Spec (class in quark.torch.quantization.config.config) OCP_MXINT8Spec (class in quark.torch.quantization.config.config) OCP_MXSpec (class in quark.torch.quantization.config.config) OnlineRotationConfig (class in quark.torch.quantization.config.config) OnnxExporterConfig (class in quark.torch.export.config.config) OSSCARConfig (class in quark.torch.pruning.config)

P

PreQuantOptConfig (class in quark.torch.quantization.config.config) ProgressiveSpec (class in quark.torch.quantization.config.config)

pruning_model() (quark.torch.pruning.api.ModelPruner method) PTPCFP8Scheme (class in quark.torch.quantization.config.template)

Q

QATSpec (class in quark.torch.quantization.config.config) QConfig (class in quark.torch.quantization.config.config) QLayerConfig (class in quark.torch.quantization.config.config) QronosConfig (class in quark.torch.quantization.config.config) QTensorConfig (class in quark.torch.quantization.config.config) QuantizationScheme (class in quark.torch.quantization.config.template) QuantizationSchemeCollection (class in quark.torch.quantization.config.template) quantize_model() (quark.torch.quantization.api.ModelQuantizer method) quark.torch.export.api module quark.torch.export.config.config module

quark.torch.pruning.api module quark.torch.pruning.config module quark.torch.quantization.api module quark.torch.quantization.config.config module quark.torch.quantization.config.template module

R

register_scheme() (quark.torch.quantization.config.template.LLMTemplate class method) (quark.torch.quantization.config.template.QuantizationSchemeCollection method)

register_template() (quark.torch.quantization.config.template.LLMTemplate class method) RotationConfig (class in quark.torch.quantization.config.config)

S

save_params() (in module quark.torch.export.api)

ScaleQuantSpec (class in quark.torch.quantization.config.config) SmoothQuantConfig (class in quark.torch.quantization.config.config)

T

to_dict() (quark.torch.quantization.config.config.QLayerConfig method) (quark.torch.quantization.config.config.QTensorConfig method)

TQTSpec (class in quark.torch.quantization.config.config) TwoStageSpec (class in quark.torch.quantization.config.config)

U

Uint4PerChannelSpec (class in quark.torch.quantization.config.config) Uint4PerGroupSpec (class in quark.torch.quantization.config.config) Uint4PerTensorSpec (class in quark.torch.quantization.config.config) Uint4WeightOnlyPerChannelScheme (class in quark.torch.quantization.config.template) Uint4WeightOnlyScheme (class in quark.torch.quantization.config.template)

Uint8PerChannelSpec (class in quark.torch.quantization.config.config) Uint8PerGroupSpec (class in quark.torch.quantization.config.config) Uint8PerTensorSpec (class in quark.torch.quantization.config.config) unregister_scheme() (quark.torch.quantization.config.template.LLMTemplate class method) (quark.torch.quantization.config.template.QuantizationSchemeCollection method)