292fb8f696
There is lot of torchair code in model runner leading the code hard for
maintenance. We'll create new torchair_model_runner to split torchair
related logic. Following the workflow #2203, this is the first PR.
What this PR does:
create the new torchair model runner, more function will be added later
- vLLM version: v0.10.0
- vLLM main:
586f286789
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
30 lines
1.0 KiB
Python
30 lines
1.0 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.
|
|
# This file is a part of the vllm-ascend project.
|
|
# Adapted from vllm-project/vllm/vllm/worker/gpu_model_runner.py
|
|
#
|
|
|
|
import torch
|
|
from vllm.config import VllmConfig
|
|
|
|
from vllm_ascend.worker.model_runner_v1 import NPUModelRunner
|
|
|
|
|
|
class NPUTorchairModelRunner(NPUModelRunner):
|
|
|
|
def __init__(self, vllm_config: VllmConfig, device: torch.device):
|
|
super().__init__(vllm_config, device)
|