PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
# Copyright (c) 2026 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
"""Pure recommendation resolution, independent of model loading and execution."""
import copy
from auto_round.recipes.recipe import Recipe, calibration_defaults
from auto_round.recipes.registry import get_recipe
def merge_layer_defaults(defaults: dict, overrides: dict | None) -> dict:
"""Merge per-pattern fields; scalar scheme entries replace the whole entry."""
result = copy.deepcopy(defaults)
for name, value in (overrides or {}).items():
if isinstance(value, dict) and isinstance(result.get(name), dict):
result[name].update(copy.deepcopy(value))
else:
result[name] = copy.deepcopy(value)
return result
def resolve_recipe(
recipe: str | Recipe = "auto-round", *, scheme="W4A16", model=None, model_config=None, trust_remote_code=True
) -> Recipe:
"""Apply a recipe's processing function to an isolated copy of its defaults."""
definition = get_recipe(recipe) if isinstance(recipe, str) else copy.deepcopy(recipe)
if not isinstance(definition, Recipe):
raise TypeError("recipe must be a registered name or Recipe instance.")
definition.calibration = {**calibration_defaults(), **definition.calibration}
if definition.process is not None:
if model_config is None:
model_config = getattr(model, "config", None)
if model_config is None and isinstance(model, str):
from transformers import AutoConfig
from auto_round.logger import logger
try:
model_config = AutoConfig.from_pretrained(model, trust_remote_code=trust_remote_code)
except (OSError, ValueError) as error:
logger.debug("Could not load recipe model metadata for %s: %s", model, error)
definition.process(
definition,
scheme=scheme.upper() if isinstance(scheme, str) else scheme,
model_config=copy.deepcopy(model_config),
)
# The returned plan is already processed; resolving it again must not rerun the callback.
definition.process = None
pipeline = definition.pipeline
calibration = definition.calibration
if not pipeline or len({stage.name for stage in pipeline}) != len(pipeline):
raise ValueError("Recipe pipeline must have nonempty, unique stage names and at least one stage.")
if any(not stage.name for stage in pipeline):
raise ValueError("Recipe stage names must be nonempty.")
invalid_calibration = set(calibration) - {"dataset", "seqlen", "nsamples", "batch_size"}
if invalid_calibration:
raise ValueError(f"Unsupported recipe calibration fields: {sorted(invalid_calibration)}")
return definition