New customers can spin up VMs, build with AI, and query data at no cost.
Put your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
Start Free
Host LLMs in Production With On-Demand GPUs
NVIDIA L4 GPUs. 5-second cold starts. Scale to zero when idle.
Deploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
A python script with modules that help send benchmarking jobs over the grid.
Provides a wrapper around the grid middleware for easy sending and retrieving informations. Uses mostly lmbench suite but more benchmarking tools will be included.
GL O.B.S. is based around a PyGTK interface that launches OpenGL programs feeding them with a common CLI options set which will affect their behaviour, then receives back their statistical output. Benchmarks are easy to create and add.