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 14, 05:30 UTC
[BugFix] Exclude self when checking for port collision (#25286)
Signed-off-by: Nick Hill <nhill@redhat.com>
Nick Hill committed
Sep 19, 2025 at 21:28 UTC
b7f186bbb3101e97bb9ad42b7ffb3cdb4bb590fd
1 file changed
+3
-1
vllm/utils/__init__.py
+3
-1
@@ -987,8 +987,10 @@ def find_process_using_port(port: int) -> Optional[psutil.Process]:
987
if sys.platform.startswith("darwin"):
988
return None
989
990
+ our_pid = os.getpid()
991
for conn in psutil.net_connections():
991
- if conn.laddr.port == port:
992
+ if conn.laddr.port == port and (conn.pid is not None
993
+ and conn.pid != our_pid):
994
try:
995
return psutil.Process(conn.pid)
996
except psutil.NoSuchProcess: