### What this PR does / why we need it?
Based on the RFC:https://github.com/vllm-project/vllm-ascend/issues/5604
This PR is a refactoring of vllm_ascend/distributed, moving all
kv_transfer realtaed codes into a dedicated folder, which has already
been done in vLLM
### Does this PR introduce _any_ user-facing change?
NA
### How was this patch tested?
- vLLM version: v0.13.0
- vLLM main:
2f4e6548ef
---------
Signed-off-by: lty <linhebiwen@gmail.com>
38 lines
1.1 KiB
Python
38 lines
1.1 KiB
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_connector():
|
|
from vllm_ascend.distributed.kv_transfer import register_connector
|
|
register_connector()
|
|
|
|
|
|
def register_model_loader():
|
|
from .model_loader.netloader import register_netloader
|
|
register_netloader()
|
|
|
|
|
|
def register_service_profiling():
|
|
from .profiling_config import generate_service_profiling_config
|
|
generate_service_profiling_config()
|