52abd47f8c
### What this PR does / why we need it? This PR aims to remove env introduced by #3988 and use lock by default. As described in https://github.com/vllm-project/vllm/issues/27858, we have tested the writer lock method in various scenarios and the performance is almost unaffected. Therefore, we believe that it would be safe to enable the lock by default and remove the redundant env `SHM_BARRIER` now. After discussion, we decide to preserve env and set it as true by default. ### Does this PR introduce _any_ user-facing change? `SHM_BARRIER` is set as true by default. ### How was this patch tested? by ci --------- Signed-off-by: Zetong Li <slippersss@126.com>
38 lines
1.4 KiB
Python
38 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.
|
|
#
|
|
|
|
import os
|
|
|
|
from vllm.triton_utils import HAS_TRITON
|
|
|
|
if HAS_TRITON:
|
|
import vllm_ascend.patch.worker.patch_triton
|
|
|
|
# isort: off
|
|
import vllm_ascend.patch.platform.patch_sched_yield # noqa
|
|
import vllm_ascend.patch.worker.patch_distributed # noqa
|
|
import vllm_ascend.patch.worker.patch_logits # noqa
|
|
import vllm_ascend.patch.worker.patch_roberta # noqa
|
|
import vllm_ascend.patch.worker.patch_weight_loader # noqa
|
|
import vllm_ascend.patch.worker.patch_multimodal_merge # noqa
|
|
import vllm_ascend.patch.worker.patch_minicpm # noqa
|
|
import vllm_ascend.patch.worker.patch_deepseek_mtp # noqa
|
|
import vllm_ascend.patch.worker.patch_attention_layer # noqa
|
|
|
|
if os.getenv("SHM_BARRIER", "true") == "true":
|
|
import vllm_ascend.patch.platform.patch_message_queue # noqa
|