# FAQ ### Container Management 1. Is my data lost when I stop my container? Your data on the temporary disk will be lost and cannot be recovered. Only data on the persistent disk will be retained. Please make sure to store your important data on the persistent disk. 2. Why can’t I access my container even though it’s running? If you’re using the vLLM template, the model might still be setting up. Check the container logs to monitor the model’s initialization status. The model is considered fully loaded and ready to serve only when you see all checkpoint shards completed, like this: **`Loading safetensors checkpoint shards: 100% Completed [3/3]`** This indicates that all model files have been successfully loaded. 3. Why can’t I find my GPU using the nvidia-smi command? Ensure that your container is in the Running state before attempting to access it. If the issue persists after verifying the container status, please try again. Should the problem continue, contact our support team for further assistance. 4. Can I run Docker within my container? No, we do not support Docker-in-Docker due to security constraints. 5. Can we can change the container’s configuration after creating it? Currently, you can edit configurations such as ports, SSH key, persistent disk size (only increase), environment variables, command, and arguments if the container is in a Running, Stopped, or Failed state. ### Billing 1. Why am I charged for running a container even when I’m not using any workloads? Charges are based on the GPU’s active running hours. This means containers are billed as long as they are in the running state, regardless of whether there is any workload being processed. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://ai-docs.fptcloud.com/fpt-gpu-cloud/gpu-container/faq.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.