mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced 2025-12-28 07:11:50 +08:00
42 lines
1.5 KiB
Python
42 lines
1.5 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
|
|
from typing import Any, Optional, Union
|
|
|
|
import torch
|
|
import torch.distributed
|
|
|
|
from .parallel_state import get_tp_group
|
|
|
|
|
|
def tensor_model_parallel_all_reduce(input_: torch.Tensor) -> torch.Tensor:
|
|
"""All-reduce the input tensor across model parallel group."""
|
|
return get_tp_group().all_reduce(input_)
|
|
|
|
|
|
def tensor_model_parallel_all_gather(input_: torch.Tensor,
|
|
dim: int = -1) -> torch.Tensor:
|
|
"""All-gather the input tensor across model parallel group."""
|
|
return get_tp_group().all_gather(input_, dim)
|
|
|
|
|
|
def tensor_model_parallel_reduce_scatter(input_: torch.Tensor,
|
|
dim: int = -1) -> torch.Tensor:
|
|
"""Reduce-Scatter the input tensor across model parallel group."""
|
|
return get_tp_group().reduce_scatter(input_, dim)
|
|
|
|
|
|
def tensor_model_parallel_gather(input_: torch.Tensor,
|
|
dst: int = 0,
|
|
dim: int = -1) -> Optional[torch.Tensor]:
|
|
"""Gather the input tensor across model parallel group."""
|
|
return get_tp_group().gather(input_, dst, dim)
|
|
|
|
|
|
def broadcast_tensor_dict(tensor_dict: Optional[dict[Any, Union[torch.Tensor,
|
|
Any]]] = None,
|
|
src: int = 0):
|
|
if not torch.distributed.is_initialized():
|
|
return tensor_dict
|
|
return get_tp_group().broadcast_tensor_dict(tensor_dict, src)
|