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 8, 14:13 UTC
[UX nit] Fix non-default api_server_count message (#34152)
Signed-off-by: mgoin <mgoin64@gmail.com>
Michael Goin committed
Feb 10, 2026 at 13:35 UTC
1f5febb4b8587378a38ea7050503c3cf0431eef6
1 file changed
+1
vllm/entrypoints/cli/serve.py
+1
@@ -108,6 +108,7 @@ class ServeSubcommand(CLISubcommand):
108
run_multi_api_server(args)
109
else:
110
# Single API server (this process).
111
+ args.api_server_count = None
112
uvloop.run(run_server(args))
113
114
def validate(self, args: argparse.Namespace) -> None: