44a8301424
### What this PR does / why we need it? Adapt Disaggregated Prefill feature onto Ascend device ### Does this PR introduce _any_ user-facing change? no ### How was this patch tested? The test usage has been provided alongwith the PR, in examples/offline_disaggregated_prefill_npu.py To run it, do this ``` export PROMPT_DEVICE_ID=0,1 export DECODE_DEVICE_ID=2,3 python examples/offline_disaggregated_prefill_npu.py ``` --------- Signed-off-by: ZihuiQian <qianzihui@huawei.com> Co-authored-by: ZihuiQian <qianzihui@huawei.com>
35 lines
1.3 KiB
Python
35 lines
1.3 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)
|
|
# init device according to rank
|
|
self.device = torch.npu.current_device()
|