Traditional tech stack
Most cloud providers built their architecture for generic use cases and hosting environments rather than compute-intensive use cases.
- VMs host Kubernetes (K8s), which need to run through a hypervisor
- Difficult to scale
- Can take 5-10 min. or more to spin up instances
![](https://cdn.prod.website-files.com/62ba1fb86485b6d5029975c4/6436dd99fcf2aa06b3e29ab6_inference-service_traditional-tech-stack.png)
CoreWeave’s tech stack
Deploy containerized workloads via Kubernetes for increased portability, less complexity, and overall lower costs.
- No hypervisor layer, so K8s runs directly on bare metal (hardware)
- We leverage Kubevirt to host VMs inside K8s containers
- Easy to scale
- Spin up new instances in seconds
![](https://cdn.prod.website-files.com/62ba1fb86485b6d5029975c4/6436f504bf2b1374b7c8968a_inference-service_coreweave-tech-stack.png)