0d14f635b4
vLLM graph feature now rely on torch >=2.8. To make graph mode work, we need upgrade torch version as well. For long term support, upgrade torch to a newer one is good to go as well. Related vLLM change: https://github.com/vllm-project/vllm/pull/25110 - vLLM version: v0.11.2 - vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2
27 lines
1.1 KiB
Python
27 lines
1.1 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").lower() in ("true", "1") or os.getenv(
|
|
"EXPERT_MAP_RECORD", "false") == "true":
|
|
import vllm_ascend.patch.platform.patch_multiproc_executor # noqa
|