Skip to content

PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度

473 B
Raw Blame
# Copyright (c) 2026 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
"""Built-in and context-aware recommended quantization plans."""

from auto_round.recipes.recipe import AlgorithmSpec, Recipe
from auto_round.recipes.registry import get_recipe, list_recipes, register_recipe
from auto_round.recipes.resolver import resolve_recipe

__all__ = [
    "AlgorithmSpec",
    "Recipe",
    "get_recipe",
    "list_recipes",
    "register_recipe",
    "resolve_recipe",
]