Product update

Write the June 2026 product update email that Lumenrack sends to everyone with a Lumenrack Functions account.

Lumenrack Functions is the Lumenrack serverless container platform for CPU and GPU workloads. June is the culmination of many months of work: it shipped four features that take Functions real-time workloads to a global footprint. The three headline numbers are: cold starts 80% lower with checkpointing, routing decisions in 9 ms with global routing, and protected capacity billed at 2x the interruptible rate. The email presents those three numbers as metric callouts before the feature detail.

The four features, in this order:

1. CPU and GPU checkpointing. Functions can snapshot a fully warmed CPU and GPU container after model weights and kernels are loaded, then restore new replicas from that snapshot instead of starting from scratch. For vLLM, SGLang, and other GPU-heavy workloads this turns multi-minute cold starts into seconds and cuts wasted GPU time during scale-up. Docs: https://lumenrack-email.s3.amazonaws.com/docs/checkpointing Reference artwork: assets.illustrations.checkpointingBanner

2. Global routing. Deploy to a single URL and Lumenrack routes every request to the closest healthy cluster across multiple regions and providers. If a cluster degrades, traffic fails over automatically. Docs: https://lumenrack-email.s3.amazonaws.com/docs/global-routing Action needed: from August 1 the legacy single-cluster URLs are no longer supported. They keep working through a proxy, which can add latency; switching to the global URL is a host-only swap that takes about five minutes. Migration guide: https://lumenrack-email.s3.amazonaws.com/docs/migrate-global-url

3. Global storage. One persistent storage layer shared across all apps and regions, so model weights and shared files are stored once and read everywhere instead of being duplicated per app or per region. Docs: https://lumenrack-email.s3.amazonaws.com/docs/global-storage Reference artwork: assets.illustrations.globalStorageBanner

4. Protected compute tiers. Each deployment chooses a tier. Interruptible is the default: cheaper preemptible capacity, and nothing changes for existing deployments. Protected is on-demand capacity that Lumenrack does not reclaim while it is serving a request, for real-time and latency-sensitive workloads. From July 1, protected is billed at 2x the interruptible rate; interruptible pricing is unchanged, and enterprise customers with negotiated pricing are not affected. Present the two tiers as an icon list using assets.icons.zap for interruptible and assets.icons.shieldCheck for protected. Docs: https://lumenrack-email.s3.amazonaws.com/docs/compute-tiers

Three posts from the Lumenrack blog close the email, as a compact list after the features:

• SOC 2 Type II: Lumenrack has completed its SOC 2 Type II audit and supports GDPR, HIPAA, and ISO 27001 programmes. https://lumenrack-email.s3.amazonaws.com/blog/soc-2-type-ii
• Beacon, the Lumenrack global router: how Beacon picks a healthy, cheaper, lower-latency cluster for every request in single-digit milliseconds, with automatic failover. https://lumenrack-email.s3.amazonaws.com/blog/beacon-router
• Restoring GPU workloads from memory snapshots: how Lumenrack snapshots warmed CPU and GPU memory inside its sandbox runtime and restores workloads like vLLM in seconds. https://lumenrack-email.s3.amazonaws.com/blog/gpu-memory-snapshots

The Lumenrack team welcomes feedback on the platform by reply.

The recipient receives this because they have a Lumenrack Functions account. Email preferences are at https://lumenrack-email.s3.amazonaws.com/preferences and they can unsubscribe at https://lumenrack-email.s3.amazonaws.com/unsubscribe

Use /world/lumenrack-email for brand chrome and CSS; the marketing family fits this email. Use the absolute HTTPS URLs from tokens.json; do not use /world/ paths as image src.

Dark mode should be supported.

Leave the HTML in output/email.html, a plain-text version in output/email.txt, and the subject in output/meta.json as {"subject": "..."}. Don't include From, To, or Date headers.