9b2a7d8866
Currently, the vllm pr: https://github.com/vllm-project/vllm/pull/24252
is causing operator fusion to fail, which can be mitigated by patching
the backend. Once the problem is completely resolved, I will submit a
new pull request to remove the patch.
- vLLM version: release/v0.13.0
- vLLM main:
5fbfa8d9ef
---------
Signed-off-by: wxsIcey <1790571317@qq.com>
33 lines
1.4 KiB
Python
33 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
|
|
|
|
import vllm_ascend.patch.platform.patch_compile_backend # noqa
|
|
import vllm_ascend.patch.platform.patch_distributed # noqa
|
|
import vllm_ascend.patch.platform.patch_ec_connector # noqa
|
|
import vllm_ascend.patch.platform.patch_mamba_config # noqa
|
|
import vllm_ascend.patch.platform.patch_sched_yield # noqa
|
|
from vllm_ascend import envs
|
|
from vllm_ascend.utils import vllm_version_is
|
|
|
|
if os.getenv("DYNAMIC_EPLB", "false").lower() in ("true", "1") or os.getenv(
|
|
"EXPERT_MAP_RECORD", "false") == "true":
|
|
import vllm_ascend.patch.platform.patch_multiproc_executor # noqa
|
|
|
|
if envs.VLLM_ASCEND_BALANCE_SCHEDULING and vllm_version_is('0.13.0'):
|
|
import vllm_ascend.patch.platform.patch_balance_schedule # noqa
|