LoginSchedule demo
cedana / throughput · v1.4 · build 2826

GPU Migration Infrastructure
for Inference.

Cedana checkpoints, migrates, and resumes running inference across your fleet, any engine, any model, any orchestrator, raising throughput, reliability, and AI revenue per MW.
Schedule a demoRead the docs
~ / cedana / migrate · livenode-A ─▸ node-B
The Problem → The Fix

AI workloads cannot move once running.
Cedana makes them liquid.

Four ways stranded compute drains budgets — and how Cedana resolves each, live and in place.

~ / cedana / problem ─▸ fix · live● 4 resolved
✕Idle GPUs:: 75% idle└▸Maximize throughput:: 88% util✕Expensive failures:: 65% lost└▸Automated reliability:: 0 lost✕Overprovisioned GPUs:: 50% over└▸Eliminate overprovisioning:: 0% buffer✕Rigid infrastructure:: no adapt└▸Adaptive infrastructure:: real-time
— the problemstatus: degraded
→ with cedanastatus: ok
01ERR.IDLE

Idle GPUs

75% idle
01RESOLVED

Maximize throughput

up to 88% utilization
02FATAL.RESTART

Expensive failures

65% compute lost
02RESOLVED

Automated reliability

0 lost progress
03WASTE.30%

Overprovisioned GPUs

10–50% overprovisioned
03RESOLVED

Eliminate overprovisioning

0% safety buffer
04STUCK.SCHEDULE

Rigid infrastructure

cannot adapt
04RESOLVED

Adaptive infrastructure

real-time
Read how we workSee the lifecycle
Live Proof · Console
Cold-Start Race

Same model. Same hardware.
21.7× faster to first token.

GLM-5.2-FP8 · 753B MoE · Multimodal · vLLM v0.19.0 · TP=8 · 8× B200 · 734 GiB ckpt · elapsed 00:00.00s
NATIVE · vLLM v0.19.0 · TP=8
● COLD START
00:00.00
$ vllm serve zai-org/GLM-5.2-FP8 --tp=8
INFO 00:00:03   spawning 8 workers · EP=8
INFO 00:00:40   loading shards 12/94 …
INFO 00:05:00   loading shards 40/94 …
INFO 00:12:00   loading shards 78/94 …
INFO 00:16:20   loading shards 94/94 …
INFO 00:18:40   building cuda graph (×8)
INFO 00:20:30   warming kv cache · vision tower
INFO 00:21:30   jit compile attention
CEDANA · RESTORE
▲ WARM RESUME
00:00.00
$ cedana resume glm-5.2-fp8 --from=snap.az-1
[+] fetch snapshot     :: ok    (734 GiB · memlock)
[+] verify hash        :: ok    (sha256: c4e1…9a)
[+] restore cuda ctx   :: ok    (8× driver attached)
[+] repopulate gpu mem :: ok    (weights + KV)
[+] thaw connections   :: ok    (sockets)
[+] register endpoint  :: ok    (port 8000)
READY 00:01:01   first token
NATIVE
0.0s
CEDANA
0.0s
delta · −1261s savedspeedup · 21.7×verdict · cedana wins
Advanced · Status: SCALING

Built for the hardest workloads.

01 · ADVANCED WORKLOADS

Distributed by default.
Works transparently with MPI & NCCL.

02 · SCALE

From a single node to an AI factory.

The Platform

unlock() your scheduler.

01

Work with what you have

No rip-and-replace. No code changes. No disruption to your teams.

02

Kubernetes & SLURM

Built for AI and HPC. Native support for SLURM and Kubernetes.

03

First migration in <30 min

K8s helm chart or SLURM plug-in. No changes to your config.

~ / cedana / deploy● ready

Command your
compute.

Your compute, liquid — checkpoint, migrate, and resume live GPU jobs across the fleet.

Schedule a demoRead the docs
deployK8s helm chart · SLURM plug-in
first migration<30 min
code changes0
workloadstraining · inference · HPC
01
AWS
02
Google Cloud
03
NVIDIA
04
K8s
05
SLURM
06
Nvidia Dynamo