Liquid Cooling for Edge Deployments
Deliver AI performance wherever it’s needed
Edge deployments require compact, efficient, and reliable cooling solutions that can operate in constrained or remote environments.
Key Challenges
Constrained physical environments
Edge sites — whether in industrial facilities, remote locations, or distributed micro-data centers — offer limited floor space and power capacity, requiring cooling solutions with a compact footprint and low ancillary power draw.
Reliability without on-site support
Edge deployments often operate in locations where regular maintenance visits are impractical — cooling systems must be reliable, low-maintenance, and capable of remote monitoring to minimize operational risk.
Speed to deployment at distributed sites
Bringing AI compute to the edge requires cooling infrastructure that can be deployed quickly across multiple locations — without the lead times associated with custom-engineered or facility-level cooling systems.
How LiquidStack Helps
Compact CDU design for constrained sites
The CDU-1MW’s space-efficient form factor is well-suited to edge environments where floor space is limited — delivering direct-to-chip liquid cooling without the infrastructure overhead of facility-scale systems.
Rapid deployment across distributed locations
With quick-ship availability and straightforward installation, the CDU-1MW can be deployed consistently across multiple edge sites — reducing lead times and enabling AI compute to reach the edge at speed.
Extending AI infrastructure beyond the core
As edge deployments grow in density and scale, LiquidStack’s expertise in high-density direct-to-chip cooling enables customers to bring the same cooling performance available in hyperscale environments to distributed and remote AI infrastructure.
Recommended Solutions
CDU-1MW
Rapid deployment for high-density data center AI workloads
- Quick-ship availability with minimal integration complexity — live in days, not months
- Supports rack densities up to 1MW per row, compatible with next-generation GPU platforms
- In-row and perimeter configurations for new builds and retrofit environments
- Backed by third-party validated performance and global service through Trane Technologies
Gigamodular CDU
Centralized liquid cooling for large-scale AI workloads
- Scales from initial deployment to multi-megawatt capacity without infrastructure redesign
- Centralized control architecture with dual-redundant communications and N+1/N+2 redundancy
- Supports 45°C return water for chillerless operation — optimised for hyperscale efficiency
- Designed for AI factory and hyperscale environments, including NVIDIA Vera Rubin platforms
