GPU server support: how tickets work

GPU server support at OverGPU is available 24/7 and handled by engineers, through tickets in your dashboard, for customers with an active server. We help with incidents and with drivers, CUDA, NCCL and networking questions. There is no email address, phone line, chat or web form; before you order, answers are in the help center, the docs, the GPU pages and the calculators. The one route outside the dashboard is for third parties reporting network abuse from our IP addresses: the abuse contact published in the IP address's WHOIS record.

Who can open a ticket

You can open a ticket while you have an active server: a server that has been delivered and is running, including the 72-hour grace period when your balance does not cover a renewal. Support is tied to an active server because the engineer who handles your ticket sees that server and its history.

How to open a ticket

• Support section of your dashboard: for incidents, technical questions, billing questions and SLA credit requests.
• The server's page: to request a reboot, a reinstall or an upgrade. Each request opens a ticket for that server.

Our engineers reply in the ticket, and you are notified by email when they do. Never send passwords, private SSH keys or two-factor codes in a ticket. To protect your account, we recommend turning on two-factor authentication with an authenticator app. We do not access the data on your servers except when necessary to operate or repair the service at your request, or when required by law.

What to include in a ticket

A complete first message saves a round trip. Include:

• the server's public IP address;
• when the problem started, with your time zone (UTC is simplest);
• what you were running and what you expected to happen;
• the output of nvidia-smi, or of amd-smi on AMD Instinct servers;
• any Xid lines from the kernel log. Xid messages are error reports the NVIDIA driver writes to the kernel log, and they help tell a hardware fault from a software one.

nvidia-smi
nvidia-smi -q > nvidia-smi.txt
sudo dmesg -T | grep -i xid

Our GPU monitoring guide explains these tools in more detail.

What needs no ticket

Some things need no ticket, because you do them yourself:

• Top-ups, invoices and receipts: add funds and download invoices and receipts in your dashboard.
• Canceling: choose "Cancel at end of period" on the server's page.
• Refunds of unused paid credit: request one from the Billing page, paid to your wallet in USDT (TRC-20) or in the coin you used. Bonus credit is not refundable; see refunds.
• A payment sent to a closed top-up: if the top-up had expired or been canceled, report the transaction ID from that top-up's page, and we check it on the blockchain.
• Signing in: if you forgot your password, use "Forgot password" on the login page to get a reset link at your account's email address.

Incidents and the SLA

Every server is covered by a 99.9% monthly availability commitment for power, network and hardware. Downtime is counted from when we detect an incident or you report it, so open a ticket as soon as you see a problem. Failed GPUs and components are replaced as a priority, and when a repair cannot be completed quickly, we offer an equivalent server where available.

If availability falls below 99.9%, request a service credit with a ticket from your dashboard within 30 days after the end of the affected month. Credits are added to your account balance, or refunded if your service ends. See SLA credits and our service level agreement.

Questions before you order

Before you order, answers are in the help center, the docs, the GPU pages and the calculators; for a first sizing estimate, try the VRAM calculator. When you are ready, deploy a server: in one form, you choose a configuration, set up the OS image, optional preinstalled software and your login (root password or SSH key), create a free account or log in, and pay the first month from your balance. The order form has optional notes for our engineers, such as your workload, a required country or region, or private networking between servers. Customers with an active server can ask for volume or term pricing, for several servers or 6–12 months, by ticket.

Single-GPU and 8-GPU servers are delivered in under 10 minutes after payment, and nothing is binding until the first month is paid. Rack-scale systems are ordered by reservation request from the deployment page instead: nothing is charged when you send it, and we confirm the allocation, price, term and location in writing before you accept and pay.

Reporting abuse

To report abuse coming from one of our IP addresses, such as attacks, spam or phishing, customers open a ticket with the "Abuse report" topic, and anyone else uses the abuse contact published in the WHOIS record of the IP address. Include as much detail as possible: the IP address, the time and any evidence. We investigate reports of abuse and, depending on severity, may ask the customer to stop, suspend the server or terminate the service. The rules are in our acceptable use policy.