Configuration for weight scale search.
More...
|
| "SearchWeightScaleConfig" | with_updates (self, **kwargs) |
| | Return a copy with updated fields.
|
Configuration for weight scale search.
Defines which transformer components should have their weight scales searched for optimal quantization.
- Parameters
-
| apply | bool. If true, apply weight scale search |
| transformer | Transformer. Transformer components for weight scale search |
Definition at line 1324 of file models.py.
◆ with_updates()
| "SearchWeightScaleConfig" qbcompiler.configs.models.SearchWeightScaleConfig.with_updates |
( |
| self, |
|
|
** | kwargs ) |
Return a copy with updated fields.
Definition at line 1361 of file models.py.
◆ model_config
| qbcompiler.configs.models.SearchWeightScaleConfig.model_config |
|
static |
Initial value:= ConfigDict(
populate_by_name=True,
extra="forbid",
)
Definition at line 1335 of file models.py.
◆ apply
| bool qbcompiler.configs.models.SearchWeightScaleConfig.apply = Field(default=False, description="If true, apply weight scale search") |
|
static |
◆ Transformer
| qbcompiler.configs.models.SearchWeightScaleConfig.Transformer |
|
static |
◆ default_factory
| qbcompiler.configs.models.SearchWeightScaleConfig.default_factory |
|
static |
◆ alias
| qbcompiler.configs.models.SearchWeightScaleConfig.alias |
|
static |
The documentation for this class was generated from the following file: