For neoclouds / inference platforms

Maximize revenue per megawatt.

Cedana restores frontier models in about a minute: a 1.6T model in 70 seconds. Run the fleet hotter, keep GPUs earning through failures and upgrades, with zero changes to your code or stack.

Schedule a demo

29.3×

faster cold starts

57–70s

restore, 229B–1.6T params

code changes

In production trials with leading AI infrastructure companies.

Benchmark / 8× B200

Native cold start grows with the model. Cedana restore doesn't.

Scale deployments for frontier inference.

8× NVIDIA B200 · 1.7TB memory · CUDA 12.9 · official sglang cookbook recipes · models ordered by parameter count

Cold start / native vs. Cedana restore

Key frontier models, measured.

Model	Params	Checkpoint (GiB)	Native	Cedana	Speedup
MiniMax-M2.7MoE	229B	244	564s	57s	9.9×
GLM-5.2-FP8MoE · Multimodal	753B	734	1322s	61s	21.7×
Kimi-K2.6MoE · Multimodal	1100B	670	1217s	63s	19.3×
DeepSeek-V4-ProMoE	1600B	873	2051s	70s	29.3×

Full benchmark: methodology and per-model results →

What it unlocks

Three problems solved. More ways to monetize your fleet.

Cold starts

More models on the same GPUs. Higher utilization.

Start multi-GPU frontier models in seconds to reduce overprovisioning.

Failures

Failures become fast, stateful resumes.

Automatically resume multi-GPU inference workloads through failures, without losing customer work.

Immobility

Defragment, rebalance, monetize across GPUs.

Ship a spot-priced preemptible tier that preserves long-running batch inference.

One always-warm 8-GPU frontier replica costs ~$175K per year before it serves a token (at $2.50/GPU-hour; plug in your rate). Scale-to-zero returns it.

How it works

What vMotion did for the datacenter, Cedana does for GPUs.

Cedana operates at the CUDA driver level, beneath your inference engines and orchestrators. Seamlessly integrates with K8s. No code, stack, or config changes.

Inference enginesvLLM · SGLang · TensorRT-LLM

OrchestratorsKubernetes · SLURM

Cedanacheckpoint · restore · migrate

CUDA driver & GPUsB200 · H100 · prior generations

GPU checkpoint and restore: how it works →

The economics

More revenue per megawatt from the fleet you already financed.

Long cold starts and model diversity result in overprovisioning. Sub-minute restore collapses the warm pool.

Recovery downtime is unserviced debt on financed GPUs. Resuming execution state turns long outages into seconds.

Sub-minute restore and stateful resiliency extend the revenue life of prior-generation silicon by making it viable inference capacity.

Why now

Inference is becoming stateful. State is becoming the bottleneck.

Agents run longer.

Long-horizon agents accumulate session state worth real money. Every eviction, failure, or cold start throws it away.

Models keep growing.

Frontier open-weight models push cold starts from seconds to half an hour, and warm pools stop being affordable.

More models, longer contexts.

Multi-model routing means constant swapping; growing context windows mean gigabytes of KV and session state per workload. More rebuilds, each one more expensive.

FAQ · What platform teams ask

Questions we hear first.

01We optimize cold start already. Why Cedana?

Because Cedana is complementary: it executes at the kernel level and leverages your existing model and kernel optimizations.

02Why should we try this now?

Inference is becoming increasingly stateful, complex, and expensive to serve, as we explain here →

03Does this work with NVIDIA Dynamo?

Cedana seamlessly integrates with Dynamo and provides additional capabilities: balancing prefill/decode with faster latency and higher granularity, and increasing reliability for higher SLA compliance.

04How long will this take to integrate and try out?

Integration happens within minutes. We work with you on a testing process to give you high confidence it works and you can scale.

05Will it work with our autoscaler and orchestrator?

Cedana works with Kubernetes and Kueue with a Helm chart. We have seamless integrations for SkyPilot and Slurm.

06How does it handle our serving framework (vLLM, SGLang, Triton)?

Cedana captures at the OS level, so the serving framework is irrelevant to the checkpoint layer. We show resume across vLLM and SGLang on the call.

07We've built our own warm-pool optimization. Why Cedana?

Most platforms have. Most result in overprovisioning as they scale across the model catalog, and this gets worse as model sizes grow. By accelerating cold starts that take 10 minutes or more to seconds, the warm-pool equation completely changes.

08What about compliance and data handling at our scale?

Cedana operates on GPU memory state inside your existing security boundary. It is SOC 2 compliant, ships on-premise, and supports fully air-gapped deployments.

09Does it handle distributed multi-GPU inference?

Yes. Distributed multi-GPU coordinated checkpoint is the differentiating capability. We show an 8-GPU model-parallel job restored as one unit on the call.

What Cedana is[primitive]

Cedana is the automation control plane for stateful inference. It checkpoints, restores, and migrates live GPU workloads across the fleet, without rebuilding state from scratch. By turning execution state into a schedulable object, Cedana lets fleets produce more tokens with higher reliability and lower cost.

save ▸ migrate ▸ resumezero code changes

More tokens per GPU.
More revenue per megawatt.

Schedule a demo Why inference is becoming stateful