A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 07:00 UTC
[Frontend] Add --version flag to CLI (#10369)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Russell Bryant committed
Nov 15, 2024 at 16:13 UTC
a067f85e08f6604b328a16efe3ead4629e0ead5b
1 file changed
+6
vllm/scripts.py
+6
@@ -9,6 +9,7 @@ import uvloop
9
from openai import OpenAI
10
from openai.types.chat import ChatCompletionMessageParam
11
12
+import vllm.version
13
from vllm.engine.arg_utils import EngineArgs
14
from vllm.entrypoints.openai.api_server import run_server
15
from vllm.entrypoints.openai.cli_args import (make_arg_parser,
@@ -143,6 +144,11 @@ def main():
144
env_setup()
145
146
parser = FlexibleArgumentParser(description="vLLM CLI")
147
+ parser.add_argument('-v',
148
+ '--version',
149
+ action='version',
150
+ version=vllm.version.__version__)
151
+
152
subparsers = parser.add_subparsers(required=True, dest="subparser")
153
154
serve_parser = subparsers.add_parser(