qbcompiler.configs.models.LoadScaleConfig Class Reference#
|
Mobilint SDK qb Compiler v1.3
MCS002-KR
|
qbcompiler.configs.models.LoadScaleConfig Class Reference
Inheritance diagram for qbcompiler.configs.models.LoadScaleConfig:
Public Member Functions | |
| "LoadScaleConfig" | with_updates (self, **kwargs) |
| Return a copy with updated fields. | |
Static Public Attributes | |
| model_config | |
| bool | apply |
| Any | entries |
Detailed Description
@brief QAT activation scale loading configuration @details Loads pre-trained activation scales from safetensors files and applies them to specified layers before scale/zeropoint computation. NOTE: entries is stored as raw JSON (type: list) because the generator does not support list[CustomStruct]. The schema records the field shape; parsing is done manually in applyQATLoadScaleQuantType / applyQATLoadScales. @param apply bool. If true, load and apply QAT scales from safetensors files @param entries List. List of file entries. Each entry is a dict:
{ path: str, scales: [ { key: str, layers: [str] } ] } path: safetensors file path; key: tensor name in the file; layers: layer names whose activation scale will be overridden.
Member Function Documentation
◆ with_updates()
| "LoadScaleConfig" qbcompiler.configs.models.LoadScaleConfig.with_updates | ( | self, | |
| ** | kwargs ) |
Member Data Documentation
◆ model_config
|
static |
◆ apply
|
static |
◆ entries
|
static |
Initial value:
= Field(
default=[],
description="List of file entries. Each entry is a dict: { path: str, scales: [ { key: str, layers: [str] } ] } path: safetensors file path; key: tensor name in the file; layers: layer names whose activation scale will be overridden.",
)
The documentation for this class was generated from the following file:
Generated by