@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / a979d9771e
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 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: