How we got microVMs booting in under a second
Depot CI's VM scheduler is just-in-time: no pre-warming, no warm pool of standby VMs. We stacked optimizations to get microVM cold boots from 7 to 9 seconds down to under a second, and this post walks through each one.
How we got microVMs booting in under a second For AI agents: a site index is available at /llms.txt. Append .md to any documentation, blog, changelog, or customer URL on this site to fetch its markdown source. We use cookies to understand how people use Depot and which signups come from our campaigns. Reject cookies Accept cookies 🚀 Just launched: the Depot CI API 🚀 Just launched: the Depot CI API Depot Sign In Get started Menu Blog > engineering How we got microVMs booting in under a second Written by Peter Hasko-Nagy Published on 6 May 2026 Share Share on Twitter Share on LinkedIn Share on
saved by
related reading
- SkyNomad: On Using Multi-Region Spot Instances to Minimize AI Batch Job Costarxiv.org
- How we achieved truly serverless GPUsmodal.com
- How to Rack 30 Petabytes of Storage | blogsi.inc
- Building a hypervisor, 2: Booting Linuxiovec.net
- Look Ma, No Bubbles! Designing a Low-Latency Megakernel for Llama-1B · Hazy Researchhazyresearch.stanford.edu
- From bare metal to a 70B model: infrastructure set-up and scripts - Imbueimbue.com
- LLM Inference Performance Engineering: Best Practices | Databricks Blogdatabricks.com
- firecracker/docs/design.md at main · firecracker-microvm/firecrackergithub.com
- "VMs won't contain cyber-capable agents"blog.trailofbits.com
- PiTorch: ML on Baremetal Raspberry Pis | projectsmasonjwang.com
- Why We Replaced Firecracker with QEMU | Hocus Bloghocus.dev
- Production Twitter on One Machine? 100Gbps NICs and NVMe are fast - Tristan Humethume.ca