@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / ab0f5e2823
Fork 0

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, 19:30 UTC

Fixes typo in function name (#7275)

Signed-off-by: Rafael Vasquez <rafvasq21@gmail.com>

Rafael Vasquez committed Aug 7, 2024 at 12:29 UTC ab0f5e2823d31c150c01fc30c146b6ea801d6bdd
1 file changed +2 -2
vllm/scripts.py
+2 -2
@@ -14,7 +14,7 @@ from vllm.entrypoints.openai.cli_args import make_arg_parser
14 from vllm.utils import FlexibleArgumentParser
15
16
17 -def registrer_signal_handlers():
17 +def register_signal_handlers():
18
19 def signal_handler(sig, frame):
20 sys.exit(0)
@@ -31,7 +31,7 @@ def serve(args: argparse.Namespace) -> None:
31
32
33 def interactive_cli(args: argparse.Namespace) -> None:
34 - registrer_signal_handlers()
34 + register_signal_handlers()
35
36 base_url = args.url
37 api_key = args.api_key or os.environ.get("OPENAI_API_KEY", "EMPTY")