e32014ac1d
### What this PR does / why we need it? Support pooling models (like `bge-reranker-v2-m3`) in vllm-ascend, this pr covered the three model types of embed (cls_token, mean_token, lasttoken). After this [commit](17373dcd93), vllm has provided support for adapting pooling models on the v1 engine. This PR includes corresponding adaptations on the vllm-ascend side. Fixes #1960 - vLLM version: v0.12.0 - vLLM main:ad32e3e19c--------- Signed-off-by: lianyibo <lianyibo1@kunlunit.com> Signed-off-by: MengqingCao <cmq0113@163.com> Co-authored-by: MengqingCao <cmq0113@163.com>
35 lines
1.4 KiB
Python
35 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.
|
|
#
|
|
|
|
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_bert # noqa
|
|
import vllm_ascend.patch.worker.patch_distributed # noqa
|
|
import vllm_ascend.patch.worker.patch_deepseek # 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_qwen2_5_vl # noqa
|
|
import vllm_ascend.patch.worker.patch_qwen2_5_omni # noqa
|
|
import vllm_ascend.patch.worker.patch_qwen3_vl # noqa
|
|
import vllm_ascend.patch.worker.patch_rope # noqa
|