Using google cloud unable to connect to inference server on external IP

Followed the instructions given @ CPU - Roboflow Docs
I am unable to connect to the inference serve using the external IP
I am able to connect when I ssh to the box I am able to connect and use it

any suggestions?

It seems like you might be facing an issue with the firewall rules of your Google Cloud Virtual Machine. The firewall rules might be preventing incoming traffic to the container’s ports.

You can try configuring the VM’s firewall rules to allow incoming traffic to the container’s ports.

If you’re still facing issues, you can try troubleshooting by checking if your request contains the proper model version request parameters and if the latest container is pulled. You can also try clearing the cache volume if you’re using one, and re-checking the NVIDIA docker GPU drivers if you’re using an NVIDIA GPU.

Here are the commands for these steps:

# Check that the latest container is pulled:
sudo docker pull roboflow/inference-server-trt:latest

# If using a cache volume, clear it:
sudo docker volume rm roboflow
sudo docker volume create roboflow

# Re-check NVIDIA docker GPU drivers:
docker run --gpus all -it ubuntu nvidia-smi

If the deployment errors persist, you can copy the server logs and send them to your Roboflow representative for further assistance.

For more information, you can refer to the Roboflow Documentation.

Hi! I’m Roboflow’s AI powered bot. This is an automated response powered using AI with knowledge from our docs, blog, and forum. If this solves your issue, please mark it as the solution using the checkbox icon. If this doesn’t solve your issue, please follow up with what you’ve tried/why, and the community will continue to chime in as usual.

When I was setting up the server it was set to allow all connections

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.