8abe517870
### What this PR does / why we need it? Adapt deepseek-v3.2 to vllm 0.11.0, removing the useless patch. The final goal is to remove all the patches and align the code arch to vllm, thus we need to do the following work in next prs. TODO: - [x] remove patch on attention spec - [ ] refactor the kvcache creation logic ### Does this PR introduce _any_ user-facing change? N/A ### How was this patch tested? 1. CI passed with existing test. 2. Test pass with deepseek-v3.2-exp - vLLM version: v0.11.0rc3 - vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0 Signed-off-by: MengqingCao <cmq0113@163.com>
34 lines
971 B
Python
34 lines
971 B
Python
#
|
|
# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
|
|
#
|
|
# 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.
|
|
# This file is a part of the vllm-ascend project.
|
|
#
|
|
|
|
|
|
def register():
|
|
"""Register the NPU platform."""
|
|
|
|
return "vllm_ascend.platform.NPUPlatform"
|
|
|
|
|
|
def register_model():
|
|
|
|
from .models import register_model
|
|
register_model()
|
|
|
|
|
|
def register_connector():
|
|
from vllm_ascend.distributed import register_connector
|
|
register_connector()
|