We just launched Cloud Acropolis Kubernetes, where the GPU option is a shared NVIDIA V100 sliced into 8, 16 or 32 GB of VRAM per workload. We'd like to hear from people running inference or fine-tuning: is a fraction of a GPU enough for your workloads, or do you always need a whole card? And which VRAM size would cover most of your models? https://cloudacropolis.com/kuber...
Cloud Acropolis Kubernetes pools from €29/month. Every package includes dedicated vCPU, Ceph-backed NVMe storage, a dedicated public IPv4, S3-compatible object storage, nested Kubernetes clusters (KubeVirt) and unlimited 1 Gbit/s bandwidth. Optional shared NVIDIA V100 GPU slices (8, 16 or 32 GB VRAM) for containers. Run containers and Linux or Windows VMs from the web UI, API or kubectl. Term discounts up to 40%. 24/7 email and ticket support, 4-hour MTTR..
