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
[Bugfix] Fix ipv6 address parsing bug (#3641)
liiliiliil committed
Mar 27, 2024 at 02:58 UTC
a979d9771e9bc728c57e98efb3cf94f430822d7d
1 file changed
+1
-1
vllm/utils.py
+1
-1
@@ -205,7 +205,7 @@ def get_ip() -> str:
205
206
207
def get_distributed_init_method(ip: str, port: int) -> str:
208
- return f"tcp://{ip}:{port}"
208
+ return f"tcp://[{ip}]:{port}"
209
210
211
def get_open_port() -> int: