# # 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_npu.patch.worker.patch_triton # isort: off import vllm_npu.patch.platform.patch_sched_yield # noqa import vllm_npu.patch.worker.patch_distributed # noqa import vllm_npu.patch.worker.patch_logits # noqa import vllm_npu.patch.worker.patch_roberta # noqa import vllm_npu.patch.worker.patch_weight_loader # noqa import vllm_npu.patch.worker.patch_multimodal_merge # noqa import vllm_npu.patch.worker.patch_minicpm # noqa import vllm_npu.patch.worker.patch_deepseek_mtp # noqa import vllm_npu.patch.worker.patch_attention_layer # noqa if os.getenv("SHM_BARRIER", "true") == "true": import vllm_npu.patch.platform.patch_message_queue # noqa