Bases: ABC, RegistryMixin
Methods:
-
from_modifiers
–
Infer which calibration pipeline to use based on the available modifiers and
from_modifiers
classmethod
from_modifiers(
modifiers: list[Modifier], user: str | None = None
) -> CalibrationPipeline
Infer which calibration pipeline to use based on the available modifiers and
any user specifications
Parameters:
-
modifiers
(list[Modifier])
–
modifiers to apply to model
-
user
(str | None, default:
None
)
–
pipeline name passed by user
Returns:
Source code in src/llmcompressor/pipelines/registry.py
| @classmethod
def from_modifiers(
cls, modifiers: list[Modifier], user: str | None = None
) -> "CalibrationPipeline":
"""
Infer which calibration pipeline to use based on the available modifiers and
any user specifications
:param modifiers: modifiers to apply to model
:param user: pipeline name passed by user
:return: CalibrationPipeline instance to be called with data (if not datafree)
"""
user = standardize_lookup_name(user) if user else None
inferred = standardize_lookup_name(cls._infer_pipeline(modifiers))
independent = standardize_lookup_name("independent")
deferred_transform = cls._deferred_transform_precedes_quantization(modifiers)
if deferred_transform is not None or user == independent:
inferred = independent
if user is not None and user != inferred:
if deferred_transform is not None:
logger.warning(
f"User requested pipeline {user} but when {deferred_transform} "
"is followed by a quantization modifier, the independent "
"calibration pipeline is recommended. Change or remove the "
"pipeline argument in oneshot if you'd like to use the "
"recommended pipeline"
)
else:
logger.warning(
f"Calibration pipeline is set to `{user}`, but it is recommended "
f"to use `{inferred}`"
)
pipeline = user or inferred
return cls.load_from_registry(pipeline)
|