24 GB VRAM, 3,840 CUDA cores, passed through to one server over PCIe. GPU servers are not orderable yet; contact us to be notified when they are.
$ nvidia-smi
# Example install command
The NVIDIA Tesla P40 is a Pascal-generation data center GPU designed for inference. It has 24 GB of GDDR5 memory and 3,840 CUDA cores. It is older than current GPUs, and some newer frameworks no longer support it.
Enough VRAM for mid-sized models and larger datasets.
Parallel processing for GPU-accelerated workloads.
NVIDIA rates the P40 at 12 TFLOPS in FP32 and 47 TOPS in INT8.
Check that your framework version still supports Pascal GPUs before you plan around it.
NVIDIA Tesla P40 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. NVIDIA Tesla P40 is a general GPU-accelerated workload. Make sure your software has CUDA support and that your driver / runtime versions match the workload requirements for NVIDIA Tesla P40.
GPU servers are not available to order yet. Today you can run NVIDIA Tesla P40 on a regular CPU plan, where it works far more slowly than on a GPU: SSH in and run nvidia-smi.
VRAM needs for NVIDIA Tesla P40 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 NVIDIA Tesla P40 within the server's RAM and storage.
Every VPS.org server comes with full root SSH access, so you can install drivers, libraries and NVIDIA Tesla P40 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 NVIDIA Tesla P40 needs yourself.
Yes. VPS.org servers are persistent virtual machines, not ephemeral instances: NVIDIA Tesla P40 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 NVIDIA Tesla P40 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 NVIDIA Tesla P40 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 NVIDIA Tesla P40 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.