Serve AI models from an NVIDIA Tesla P40 (24 GB VRAM, Pascal architecture): LLMs, image models and other predictions. GPU servers are not orderable yet; contact us to be notified when they are.
$ pip install vllm && vllm serve meta-llama/Llama-3-8B-Instruct
# Example install command
AI inference means running trained models to produce predictions. A GPU inference server keeps a model loaded on the GPU and answers requests much faster than a CPU.
The GPU is passed through to your server alone, so latency is not affected by other customers' GPU jobs.
Use Ollama, llama.cpp, Triton or your own API. Some frameworks, such as vLLM, need newer GPUs than the Pascal P40.
Run several servers behind your own load balancer if one GPU is not enough.
Serve one mid-sized model or several smaller ones.
AI Inference can use an NVIDIA GPU to speed up its work. VPS.org GPU servers are not available to order yet; contact us to hear when they are. AI Inference is a general GPU-accelerated workload. Make sure your software has CUDA support and that your driver / runtime versions match the workload requirements for AI Inference.
GPU servers are not available to order yet. Today you can run AI Inference on a regular CPU plan, where it works far more slowly than on a GPU: SSH in and run pip install vllm && vllm serve meta-llama/Llama-3-8B-Instruct.
VRAM needs for AI Inference depend on the model and batch size; check the project documentation for current figures.
GPU pricing will be published when GPU servers can be ordered. Contact us if you want to hear when that happens.
Yes. Every VPS.org server comes with full root access, so you can run other tools alongside AI Inference within the server's RAM and storage.
Every VPS.org server comes with full root SSH access, so you can install drivers, libraries and AI Inference however you need.
No. No server comes with a CUDA runtime or NVIDIA driver preinstalled, and GPU servers are not available to order yet. You install the versions AI Inference needs yourself.
Yes. VPS.org servers are persistent virtual machines, not ephemeral instances: AI Inference models, configs and data stay on the server's SSD storage until you delete them.
Keep working data on the server's SSD for fast access during AI Inference runs, and copy finished artifacts (weights, generations, embeddings) to storage outside VPS.org; snapshots and backups stay on the same storage cluster.
You can upgrade any VPS.org server to a larger plan from the control panel; the resize restarts it and your AI Inference install carries over. GPU servers are not available yet.
Yes. Backups are a paid add-on (daily +30% of the plan price, kept 7 days; weekly +20%, kept 28 days) and snapshots are free, which is useful before long AI Inference runs. Both stay on the same storage cluster as the server.
Contact support within 30 days of your first purchase to request a refund. GPU servers are not sold yet, so no GPU order is involved.
GPU servers are not orderable yet. Tell us about your workload and we will let you know when they are.