mirror of
https://github.com/vllm-project/vllm-ascend.git
synced 2025-10-20 13:43:53 +08:00
c3d1a3782a
This is the first step to support trl vllm serve on Ascend NPU https://github.com/vllm-project/vllm-ascend/issues/459. This PR can work properly only when https://github.com/vllm-project/vllm/pull/16464 is merged into vLLM. --------- Signed-off-by: hzji210@gmail.com <hzji210@gmail.com>
36 lines
1.4 KiB
Python
36 lines
1.4 KiB
Python
#
|
|
# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
|
|
# This file is a part of the vllm-ascend project.
|
|
#
|
|
# 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 typing import Optional
|
|
|
|
import torch
|
|
from torch.distributed import ProcessGroup
|
|
from vllm.distributed.device_communicators.base_device_communicator import \
|
|
DeviceCommunicatorBase
|
|
|
|
|
|
class NPUCommunicator(DeviceCommunicatorBase):
|
|
|
|
def __init__(self,
|
|
cpu_group: ProcessGroup,
|
|
device: Optional[torch.device] = None,
|
|
device_group: Optional[ProcessGroup] = None,
|
|
unique_name: str = ""):
|
|
super().__init__(cpu_group, device, device_group, unique_name)
|
|
# TODO(hz): Refer to CudaCommunicator's implementation to integrate PyHcclCommunicator
|
|
# init device according to rank
|
|
self.device = torch.npu.current_device()
|