From the NVIDIA edition of September 23, 2026
Vertiv 2.3 MW CoolChip CDU qualifies as first NVIDIA DSX Ready CDU
Vertiv · AI factory liquid cooling / facilities infrastructure · Global (vendor announcement; edge/colo/hyperscale positioning)
- Publisher
- Vertiv News Releases
- Original publication
- September 21, 2026
- Source retrieved
- 2026-09-24
- Event date
- 2026-09-21
What happened
On Sep 21, 2026 Vertiv announced its 2.3 MW CoolChip liquid-to-liquid CDU qualified as an NVIDIA DSX Ready CDU—described as the first CDU to qualify specifically under the program and among initial CDU providers. The unit supports direct-to-chip and rear-door heat-exchanger applications for end-of-row or perimeter install. Vertiv states DSX Ready uses NVIDIA’s CDU self-qualification suite for functional requirements, and explicitly: qualification does not replace site/configuration engineering; customers must still determine facility fit, system configuration, and operating requirements.
Why it matters
Extends yesterday’s BESS-heavy Ready diligence to the cooling side with a named 2.3 MW SKU and an on-the-record site-engineering caveat—useful for SLED BOM screening of liquid-cooled AI rooms without treating Ready as campus certification.
Evidence and measured results
2.3 MW CoolChip CDU; first CDU specifically DSX Ready; liquid-to-liquid; direct-to-chip + rear-door HX; end-of-row/perimeter; CDU self-qualification suite; explicit non-replacement of site engineering / facility-fit determination.
Limitations and uncertainty
Vendor PR; no third-party re-test published here; “first CDU” is Vertiv’s characterization; MW rating is product capacity, not a measured campus deployment.
Put this evidence to work
Lighthouse Advisory interpretation, grounded in this source. Enriched 2026-09-24; this does not change the original publication date. Each role follows the same checklist so takeaways compare across sources.
Sales
Role takeaway
- Customer problem
- Buyers need credible liquid-cooling SKUs matched to NVIDIA AI-factory references without mistaking logos for site readiness.
- Stakeholders
- facilities
- AI platform
- general contractor
- procurement
- Discovery questions
- What rack kW and loop ΔT are designed?
- Is D2C or RDHx primary?
- Who signs site thermal acceptance?
- Value hypothesis
- Ready CDUs can shorten BOM diligence if site engineering remains mandatory.
- Potential engagement
- Cooling design review against DSX CDU requirements for one hall.
- Unsupported claims
- Site certified by Ready
- 2.3 MW equals deployed campus capacity
- Guaranteed Vertiv win
Pre-sales engineering
Role takeaway
- Fit
- Strong for liquid-cooled AI halls; weak for air-only legacy rooms.
- Architecture and integration
- Liquid-to-liquid CDU serving D2C/RDHx at end-of-row or perimeter.
- Prerequisites
- TCS design
- Redundancy plan
- Controls/Modbus path
- Water/chemistry plan
- Constraints
- Vendor self-qual path
- No independent re-bench in PR
- Security
- Harden remote CDU control; source silent on cyber tests.
- Proof of value
- Design-day heat rejection met
- Failover demonstrated
- Facility-fit memo signed
Delivery
Role takeaway
- Work
- Select SKU, commission loop, integrate BMS/controls, witness tests.
- Dependencies
- MEP engineer
- NVIDIA/partner SE
- BMS vendor
- Ownership
- Facilities MEP lead.
- Skills and adoption
- Operators need liquid-cooling runbooks beyond air CRAC literacy.
- Governance checkpoints
- No Ready-only acceptance
- Failover drill before energization
- Change control on firmware
- Acceptance criteria
- Thermal model vs measured
- N+1 failover time
- Remote-control ACL review
- Risks
- Logo shopping
- Loop chemistry issues
- Power/cooling desync
Implementation considerations
Lighthouse Advisory interpretation across the operating dimensions a public-sector buyer must settle before this evidence becomes a design. Each note answers the question under its heading for this specific source.
Architecture and integration
What must connect, and where does the AI sit in the workflow?
High-density AI rooms need CDU selection tied to DSX reference flows, but loop design, redundancy, and operating envelopes remain site engineering.
Governance
Who approves, reviews and stays accountable for outcomes?
BOM shortlists may prefer Ready SKUs; acceptance still requires site thermal/hydraulic sign-off.
Security and privacy
What data, permissions and controls need testing?
No workload security claims; cooling control plane becomes an ops trust boundary if remotely managed.
Accessibility and workforce
Who is affected, and what skills or accommodations follow?
Indirect: stable cooling supports shared research tools; no accessibility features claimed.
Procurement
What should contracts, pricing and exit terms secure?
Allow Ready as evaluation input; require site engineering deliverables in contracts.
Operating model
Which teams own the service once it runs?
Shifts cooling from afterthought to codesigned AI-factory constraint.
Publication history
- 2026-09-23NVIDIA · Issue 188 resources
Stable resource ID: vertiv-coolchip-cdu-dsx-ready-20260921