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 17, 04:15 UTC
Add args for mTLS support (#3410)
Co-authored-by: Daniel Clark <daniel.clark@ibm.com>
Dan Clark committed
Mar 14, 2024 at 13:11 UTC
c17ca8ef186b5e90a500d3e37724b220944450f7
1 file changed
+11
-1
vllm/entrypoints/api_server.py
+11
-1
@@ -82,6 +82,14 @@ if __name__ == "__main__":
82
parser.add_argument("--port", type=int, default=8000)
83
parser.add_argument("--ssl-keyfile", type=str, default=None)
84
parser.add_argument("--ssl-certfile", type=str, default=None)
85
+ parser.add_argument("--ssl-ca-certs",
86
+ type=str,
87
+ default=None,
88
+ help="The CA certificates file")
89
+ parser.add_argument("--ssl-cert-reqs",
90
+ type=int,
91
+ default=0,
92
+ help="Whether client certificate is required")
93
parser.add_argument(
94
"--root-path",
95
type=str,
@@ -100,4 +108,6 @@ if __name__ == "__main__":
108
log_level="debug",
109
timeout_keep_alive=TIMEOUT_KEEP_ALIVE,
110
ssl_keyfile=args.ssl_keyfile,
103
- ssl_certfile=args.ssl_certfile)
111
+ ssl_certfile=args.ssl_certfile,
112
+ ssl_ca_certs=args.ssl_ca_certs,
113
+ ssl_cert_reqs=args.ssl_cert_reqs)