66b67f9cf2
### What this PR does / why we need it? This PR aims to fix weak memory ordering problem in share memory by patching message queue with an additional lock. The detailed issue can be found here https://github.com/vllm-project/vllm/issues/27858. The key point is to use the writer lock to enforce memory fence before the ready flag `metadata_buffer[0] = 1` is set. This is a temporary solution, and you can use it by setting env `SHM_BARRIER=true`. By default, we disable this modification. ### Does this PR introduce _any_ user-facing change? `SHM_BARRIER=true` enables this change while `SHM_BARRIER=false` disables this change. The latter is the default choice. ### How was this patch tested? by ci --------- Signed-off-by: Zetong Li <slippersss@126.com>
31 lines
1.2 KiB
Python
31 lines
1.2 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
|
|
|
|
import vllm_ascend.patch.platform.patch_config # noqa
|
|
import vllm_ascend.patch.platform.patch_distributed # noqa
|
|
import vllm_ascend.patch.platform.patch_mamba_config # noqa
|
|
import vllm_ascend.patch.platform.patch_sched_yield # noqa
|
|
|
|
if os.getenv("DYNAMIC_EPLB", "false") == "true" or os.getenv(
|
|
"EXPERT_MAP_RECORD", "false") == "true":
|
|
import vllm_ascend.patch.platform.patch_multiproc_executor # noqa
|
|
|
|
if os.getenv("SHM_BARRIER", "false") == "true":
|
|
import vllm_ascend.patch.platform.patch_core # noqa
|
|
import vllm_ascend.patch.platform.patch_message_queue # noqa
|