mode#

This module contains the mode descriptor for the quantization mode.

Classes

DFlashModeDescriptor

Class to describe the "dflash" mode.

EagleModeDescriptor

Class to describe the "eagle" mode.

MedusaModeDescriptor

Class to describe the "medusa" mode.

class DFlashModeDescriptor#

Bases: ModeDescriptor

Class to describe the "dflash" mode.

The properties of this mode can be inspected via the source code.

property config_class: type[ModeloptBaseConfig]#

Specifies the config class for the mode.

property convert: Callable[[Module, ModeloptBaseConfig], tuple[Module, dict[str, Any]]] | Callable[[Module, ModeloptBaseConfig, Any], tuple[Module, dict[str, Any]]]#

The mode’s entrypoint for converting a model.

property name: str#

Returns the value (str representation) of the mode.

property restore: Callable[[Module, ModeloptBaseConfig, dict[str, Any]], Module]#

The mode’s entrypoint for restoring a model.

class EagleModeDescriptor#

Bases: ModeDescriptor

Class to describe the "eagle" mode.

The properties of this mode can be inspected via the source code.

property config_class: type[ModeloptBaseConfig]#

Specifies the config class for the mode.

property convert: Callable[[Module, ModeloptBaseConfig], tuple[Module, dict[str, Any]]] | Callable[[Module, ModeloptBaseConfig, Any], tuple[Module, dict[str, Any]]]#

The mode’s entrypoint for converting a model.

property name: str#

Returns the value (str representation) of the mode.

property restore: Callable[[Module, ModeloptBaseConfig, dict[str, Any]], Module]#

The mode’s entrypoint for restoring a model.

class MedusaModeDescriptor#

Bases: ModeDescriptor

Class to describe the "medusa" mode.

The properties of this mode can be inspected via the source code.

property config_class: type[ModeloptBaseConfig]#

Specifies the config class for the mode.

property convert: Callable[[Module, ModeloptBaseConfig], tuple[Module, dict[str, Any]]] | Callable[[Module, ModeloptBaseConfig, Any], tuple[Module, dict[str, Any]]]#

The mode’s entrypoint for converting a model.

property name: str#

Returns the value (str representation) of the mode.

property restore: Callable[[Module, ModeloptBaseConfig, dict[str, Any]], Module]#

The mode’s entrypoint for restoring a model.