b321e3846a
### What this PR does / why we need it? On Arm systems, os.sched_yield() does not take effect, causing the GIL (Global Interpreter Lock) to remain unrelinquished and resulting in CPU bound issues. This PR applies a patch to sched_yield in vLLM, making the process execute time.sleep(0) instead to release the GIL. ### Does this PR introduce _any_ user-facing change? Signed-off-by: fems14 <1804143737@qq.com> Co-authored-by: fems14 <74094523+fems14@users.noreply.github.com>
32 lines
1.3 KiB
Python
32 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 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 |