Snapshot and migrate your workloads across instances

Command your compute_

Request API Access Documentation

Backed by

Supports your cloud-native stack, tools, and containers. For CPU and GPU workloads

Why Cedana?

Cedana (/ce'dana/) is a save/migrate/resume system for compute. We leverage insight into the Linux Kernel (through CRIU and other methods) to checkpoint and restore workloads across instances and vendors.

Reduce compute costs by 20%-80%

Eliminate idle compute. Automatically suspends and resumes your workloads based on activity. Automatically bin-packs containers across instances, freeing up resources at fine-grain resolution.

Never lose work — even if hardware fails

Upon hardware or OOM failure, automatically resume workload on a new instance without losing work.

‍
‍

3x your performance
‍

Accelerate cold start and time to first token by resuming your CPU/GPU workload from it's previous state. Eliminate boot time, initialization and other steps.

"We reduced our cloud cost by 50% by integrating Cedana's Save, Migrate, and Resume capability into our product. If an instance fails, we can continue workloads without losing work, increasing reliability."

Debo Ray

CEO, DevZero

Use Cases

2-10x Faster Time to First Token

Drive customer experience gains and stickier customers

Conquer your cold starts: eliminate library/ model initialization and optimization time.

Fast image pulls: unlock network/storage efficiency, break registry bottlenecks

Maximize SLAs: seamlessly handle traffic surges and spikes

Reduce costs - reduce over-provisioning by over 2x

Eliminate training disruptions. Never lose work.

Drive customer experience gains and stickier customers

Relentless: Self-healing through GPU failures. no manual intervention.

Designed for large-scale training: automatically synchronizes multi-GPU and multi-node training jobs.

Checkpoint autopilot: Automatic versioning and intelligent storage and networking

Increase utilization: Less downtime, no loss of training progress

Kubernetes redefined for stateful workloads

Scale Smarter. Run Faster. Spend Less.

AI-driven observability: auto-detects idle resources

Optimization that just works: Intelligent bin-packing and dynamically right-size pods

Seamless live-migration: pods, nodes, or entire clusters

Scale elastically and responsively: warm boots enable greater elasticity and faster performance

Higher SLAs, less costs: automatically resumes pods through catastrophic failures, while reducing over-provisioning

High Performance Computing

Accelerate time to insights while reducing TCO

A simple Helm chart provides a complete solution

Improve TCO: increase GPU utilization with self-healing workloads.

Efficient resource sharing across groups: faster draining and replenishing of nodes any time, without losing work

Checkpoint autopilot: automatic versioning and intelligent storage and networking

Maximize your CPU/GPU Utilization

See Cedana in Action

Request API Access

How it Works?

Save

Save a process or container using our API. Saves the complete state of the workload including process and filesystem state, open network connections, in-memory (RAM and VRAM), data, namespaces and everything in between

Migrate

Migrate the workload onto another instance.

Resume

Resume workloads as new process/container on another instance. Realtime performance with not service disruption.

Bin Packing

Use Save, Migrate, Resume (SMR) to implement policy-based automation. Cedana automatically suspends and resumes workloads based on activity, enabling fine-grained bin packing of containers. This saves up to 80% of compute costs.

Easy Integration

Use Cedana REST API to checkpoint your application’s state, transfer it to a new instance, cloud or resource, and resume operations. No code modifications needed.

curl -X POST -H "Content-Type: application/json" -d '{
  "checkpoint_data": {
    "container_name": "$CHECKPOINT_CONTAINER",
    "sandbox_name": "$CHECKPOINT_SANDBOX",
    "namespace": "$NAMESPACE",
    "checkpoint_path": "$CHECKPOINT_PATH",
    "root": "$ROOT"
  }
}' http://$CONTROLLER_URL:1324/checkpoint

curl -X POST -H "Content-Type: application/json" -d '{
  "checkpoint_data": {
    "container_name": "$CHECKPOINT_CONTAINER",
    "sandbox_name": "$CHECKPOINT_SANDBOX",
    "namespace": "$NAMESPACE",
    "checkpoint_path": "$CHECKPOINT_PATH",
    "root": "$ROOT"
  }
}' http://$CONTROLLER_URL:1324/restore

2-10x faster cold starts. Increase utilization up to 3x. Automated, stateful reliability