common.py 1.54 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# 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.


import os
from dataclasses import dataclass, field

from huggingface_hub import snapshot_download
from vllm.engine.arg_utils import AsyncEngineArgs
from vllm.utils import FlexibleArgumentParser


@dataclass
class NvAsyncEngineArgs(AsyncEngineArgs):
    model_path: str = field(default="")


def parse_vllm_args() -> NvAsyncEngineArgs:
    parser = FlexibleArgumentParser()
    parser = AsyncEngineArgs.add_cli_args(parser)
    parser.add_argument(
        "--model-path",
        type=str,
        default="",
    )
    args = parser.parse_args()
    if args.model_path == "":
        if os.environ.get("HF_TOKEN"):
            args.model_path = snapshot_download(args.model)
        else:
            raise ValueError(
                "Please set HF_TOKEN environment variable "
                "or pass --model-path to load the model"
            )
    return NvAsyncEngineArgs.from_cli_args(args)