Part of the day: In-rack busbar & power whips

Assembled by the nightly build from this catalog’s own entry for In-rack busbar & power whips (4.15, Layer 4 — Servers, racks & integration). The tables below are rebuilt every night; published 2026-10-01.

The high-current busbar and cabling that carries power from the rack’s power shelves to each tray, including Nvidia’s specified ±48 V / 1,400 A busbar used in rack-scale liquid-cooled systems.

Busbar and power whips are the last stretch of power distribution inside the rack, carrying current from the power shelves (4.12) to each tray’s own board-level power delivery (4.08). A solid or laminated busbar running vertically through the rack, rather than a bundle of individual cables, is what rack-scale systems use to move very high current at the ±48 V level the taxonomy specifies for NVL72-class racks; a bundle of discrete power whips remains the more conventional approach outside that specific architecture. The shift toward busbar reflects how much current a fully populated GPU rack now needs to distribute internally — a level that individual cables handle poorly at scale. For investors, this is a component defined by its current-carrying and thermal-management engineering rather than by exotic materials, and the suppliers building to the Nvidia-spec busbar are working from a reference design that’s likely to be revised with each rack generation, which keeps requalification a recurring event rather than a one-time qualification.

AI delta: Fully populated GPU racks need to move more current internally than a bundle of discrete cables handles well, which is why rack-scale systems increasingly use a solid busbar rather than conventional power whips.

Who makes it

The full entry — sub-categories, news, videos and sources — lives on the In-rack busbar & power whips page.