IP bind error

[qyhdt]

Hi, vllm team
I hit an error when I start a service according to your documentation, gives me below error.
Anyone can help me to take a look.

Documentation:

Error

[qyhdt]

It needs to add two arguments -- host xxxx --port 8000, and also if anyone want to let this service can be access from other machine, host need to be set as 0.0.0.0

[viktor-ferenczi]

You have some other process running on port 8000 or your previous instance still keep that port blocked for a few more seconds (TCP/IP stack (mis)feature).

How to find the existing process running on port 8000:

netstat -nlp | grep 8000

Then just kill it and try starting vLLM again.

[hmellor]

Closing this issue as stale as there has been no discussion in the past 3 months.

If you are still experiencing the issue you describe, feel free to re-open this issue.

[pchunduru10]

Using the same forum.As I am encountering the same error on 0.5.0.post1 version.

I am launching openai.api server using the following command and consistently seeing the IP-Bind error. It works on 0.4.2 version which is my current image. I am looking to upgrade to newer vllm version to access features/fixes that were failing on earlier version.

CMD="python -u -m vllm.entrypoints.openai.api_server \
        -- host 0.0.0.0 \
         --port $VLLM_PORT \
        --model $launch_model \
        --tensor-parallel-size $NUM_GPUS \
        --download-dir /data"

Appreciate any help with this.