b69b04d3a9
### What this PR does / why we need it?
This PR aim to implement model runner v2 basic framework in vllm-ascend,
the e2e function is not guaranteed by this pr.
### Does this PR introduce _any_ user-facing change?
use envs.VLLM_USE_V2_MODEL_RUNNER to decide if choose model_runenr_v2.
### How was this patch tested?
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: Ronald1995 <ronaldautomobile@163.com>
27 lines
1.1 KiB
Python
27 lines
1.1 KiB
Python
#
|
|
# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
|
|
# Copyright 2023 The vLLM team.
|
|
#
|
|
# 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_ascend.worker.worker import NPUWorker
|
|
from vllm_ascend.xlite.xlite_model_runner import XliteModelRunner
|
|
|
|
|
|
class XliteWorker(NPUWorker):
|
|
"""Xlite worker bases on NPUWorker. Only xlite specified code should be added in this class."""
|
|
|
|
def init_device(self):
|
|
"""Override init_device to init xlite model runner"""
|
|
self.device = self._init_device()
|
|
self.model_runner = XliteModelRunner(self.vllm_config, self.device)
|