17da96658f
### What this PR does / why we need it?
Support an new load format: RFORK
For implementation details of this feature, please refer to #7441
### Does this PR introduce _any_ user-facing change?
add an new options for load-format: rfork
e.g.
```bash
vllm serve /workspace/models/Qwen3-8B --load-format rfork
```
### How was this patch tested?
- vLLM version: v0.17.0
- vLLM main:
4034c3d32e
Signed-off-by: Marck <1412354149@qq.com>
43 lines
1.2 KiB
Python
43 lines
1.2 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
|
|
from .model_loader.rfork import register_rforkloader
|
|
|
|
register_netloader()
|
|
register_rforkloader()
|
|
|
|
|
|
def register_service_profiling():
|
|
from .profiling_config import generate_service_profiling_config
|
|
|
|
generate_service_profiling_config()
|