# Copyright (c) 2025 Bytedance Ltd. and/or its affiliates
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
# http://www.apache.org/licenses/LICENSE-2.0
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

from functools import partial

import torch
from torch.distributed.fsdp import FullyShardedDataParallel as FSDP
from torch.distributed.fsdp import MixedPrecision, ShardingStrategy
from torch.distributed.fsdp.wrap import lambda_auto_wrap_policy


def shard_model(
    model,
    device_id,
    param_dtype=torch.bfloat16,
    reduce_dtype=torch.float32,
    buffer_dtype=torch.float32,
    process_group=None,
    sharding_strategy=ShardingStrategy.FULL_SHARD,
    sync_module_states=True,
):
    model = FSDP(
        module=model,
        process_group=process_group,
        sharding_strategy=sharding_strategy,
        auto_wrap_policy=partial(
            lambda_auto_wrap_policy, lambda_fn=lambda m: m in model.blocks),
        mixed_precision=MixedPrecision(
            param_dtype=param_dtype,
            reduce_dtype=reduce_dtype,
            buffer_dtype=buffer_dtype),
        device_id=device_id,
        sync_module_states=sync_module_states)
    return model