From the NVIDIA edition of September 18, 2026
DSX MaxLPS technical deep dive: DPS Developer Preview and up-to-40% Rubin projection
NVIDIA · AI factory software / facilities engineering · Global (vendor technical blog)
- Publisher
- NVIDIA Technical Blog
- Original publication
- August 24, 2026
- Source retrieved
- 2026-09-19
- Event date
- 2026-08-24
What happened
Aug 24, 2026 NVIDIA technical blog defines MaxLPS as Maximum Land Power Shell—dynamic power allocation via Dynamic Power Software (Developer Preview), workload-profile power solutions/APPM, and 45°C liquid-cooling inlet design. An illustrative 100 MW waterfall leaves ~60 MW for AI load after facility/rack/ops deductions. Vendor examples reclaim 170 kW stranded in a 540 kW static plan and show GB200/GB300 rack power cuts enabling roughly 35–39% more racks at preserved throughput; the post projects up to 40% more Rubin GPUs in a 100 MW factory. DPS does not change the site power envelope.
Why it matters
Newly relevant alongside today’s Lambda PoC: explains control-loop prerequisites and that Rubin “+40%” is a planning projection requiring early facilities design for 45°C and rack-position optionality—not a drop-in software toggle for SLED halls.
Evidence and measured results
DPS Developer Preview continuous control loop; DSX Exchange optional IT/OT bus also Developer Preview; Figure 4 GB200 125→90 kW and GB300-class 136→101 kW examples; Table 1 100 MW factory projections; guidance to validate before infrastructure is fixed; scoped NVL72 inference power pilot recommended.
Limitations and uncertainty
Vendor-authored; DPS/Exchange in Developer Preview; Rubin capacity gains are projections; illustrative waterfalls are not a specific customer site audit.
Put this evidence to work
Lighthouse Advisory interpretation, grounded in this source. Enriched 2026-09-19; this does not change the original publication date. Each role follows the same checklist so takeaways compare across sources.
Sales
Role takeaway
- Customer problem
- Utility interconnect and shell limits block AI expansion more than chip supply.
- Stakeholders
- facilities
- CIO/CTO
- procurement
- utility
- Discovery questions
- Is the site designed for 45°C DLC inlet?
- Can you leave rack positions dark for later fill?
- Is DPS on the software roadmap?
- Value hypothesis
- Early MaxLPS-ready design can raise lifecycle GPU count inside a fixed MW without promising immediate +40%.
- Potential engagement
- Site MaxLPS readiness review plus scoped software pilot.
- Unsupported claims
- 40% more Rubin GPUs guaranteed
- DPS GA everywhere
- Cooling power always reclaimed
Pre-sales engineering
Role takeaway
- Fit
- Fits greenfield AI factories and major retrofits; poor fit for unmanaged racks without telemetry.
- Architecture and integration
- DPS groups plus WPPS/APPM profiles; size network for MaxLPS GPU count; optional DSX Exchange to BMS.
- Prerequisites
- power telemetry
- policy engine
- thermal design validation
- space for optional racks
- Constraints
- Developer Preview DPS/Exchange
- workload-mix dependent Day-1 fill
- climate-specific free cooling
- Security
- Harden any IT/OT bus; least-privilege power policy changes.
- Proof of value
- static vs managed pilot metrics
- policy compliance logs
- thermal inlet targets met
Delivery
Role takeaway
- Work
- Parallel facilities design gate and software pilot; do not wait for full Day-1 population.
- Dependencies
- mechanical/electrical engineer
- NVIDIA DSX SE
- platform SRE
- Ownership
- Facilities program lead with platform co-owner.
- Skills and adoption
- Train ops on power policies and TCS loop behavior.
- Governance checkpoints
- Design freeze only after MaxLPS optionality review
- No +40% in budget without pilot
- Preview software risk accepted
- Acceptance criteria
- Site design checklist signed
- Pilot metrics filed
- Rollback power policy documented
- Risks
- Retrofit cost exceeds reclaim
- Preview software delays
- Training mix prevents densification
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?
Site must be designed for MaxLPS rack-position optionality, east-west network sized to MaxLPS GPU count, and warm-water cooling; Day-1 population can be lower than the lifecycle target.
Governance
Who approves, reviews and stays accountable for outcomes?
Treat 40% Rubin capacity and zettaflop tables as planning estimates pending measured site pilots; separate software validation from irreversible facilities decisions.
Security and privacy
What data, permissions and controls need testing?
IT/OT event bus (DSX Exchange) expands attack surface to building systems if adopted; still in Developer Preview.
Accessibility and workforce
Who is affected, and what skills or accommodations follow?
None stated; denser factories may intensify facilities staffing needs.
Procurement
What should contracts, pricing and exit terms secure?
Separate facilities-readiness BOM from GPU purchase; require Developer Preview risk language.
Operating model
Which teams own the service once it runs?
Capacity becomes a lifecycle fill strategy tied to workload-mix evolution.
Publication history
- 2026-09-18NVIDIA · Issue 138 resources
Stable resource ID: nvidia-dsx-maxlps-technical-20260824