# Nvidia Kyber NVL144 Delayed 12+ Months to 2028

> Source: [https://icharles.com/articles/nvidia-kyber-nvl144-delay-2028](https://icharles.com/articles/nvidia-kyber-nvl144-delay-2028) (canonical)
> Author: iCharles News — iCharles, https://icharles.com
> Published: 2026-07-06

## TL;DR

SemiAnalysis reported on July 6, 2026 that Nvidia's Kyber NVL144 rack architecture is delayed by more than 12 months, pushing its launch to 2028. The cause is manufacturing failures in the midplane PCB — a 78-layer board Nvidia calls the "orthogonal backplane." A backup design, the NVL72x2, was also canceled. The four-compute-die version of Rubin Ultra has been scrapped, and the larger NVL576 system faces its own delays tied to co-packaged optics.

## What did SemiAnalysis report about the Kyber NVL144?

Nvidia's Kyber NVL144 rack architecture is delayed by more than 12 months, pushing its launch to 2028 — just three months after Jensen Huang showcased it at GTC. Semiconductor research firm SemiAnalysis posted six consecutive tweets on X on July 6, 2026, disclosing the delay and a series of related cancellations. The firm stated bluntly: "Major delay: Just three months after Jensen Huang showcased the Kyber NVL144 at GTC, the product has suffered a major setback, with delays exceeding 12 months, pushing its launch to 2028."

## What is the Kyber NVL144 and why does it matter?

The **Kyber NVL144** is Nvidia's rack architecture designed to interconnect 144 GPUs within a single domain, targeting large-scale AI training. It is part of the Rubin Ultra generation of hardware. Using conventional copper cabling for 144 GPUs would require over 20,000 cables, increasing weight by more than 30% and causing severe signal attenuation — which is why the midplane PCB is central to the design.

## Why is the midplane PCB causing the delay?

The **midplane PCB** — which Nvidia officially calls the "orthogonal backplane" — is the board that enables 90-degree vertical interconnects between compute trays and switch trays inside the Kyber rack. Manufacturing it has proven extremely difficult. According to [SemiAnalysis as reported by Futunn](https://news.futunn.com/en/post/75547099/semianalysis-reports-again-nvidia-s-kyber-nvl144-rack-has-been), the board uses a hybrid material of M9-grade copper-clad laminate, quartz fabric, and PTFE. It has 78 layers — formed by laminating three 26-layer boards together — with trace widths and spacings of 25μm or less to meet signal integrity requirements at SerDes rates exceeding 448G. That combination sits at the current limits of PCB manufacturing technology.

This is directly relevant to the broader AI memory chip shortage affecting the supply chain, as SemiAnalysis noted the delays will impact memory, PCB, and ODM supply chains.

## What happened to the NVL72x2 backup plan?

Nvidia had developed an interim solution called the **NVL72x2**, a back-to-back rack design that placed two Oberon racks together and used pure copper NVLink interconnects to scale the domain — bypassing the midplane PCB problem entirely. That plan was canceled. SemiAnalysis said it was dropped "due to strong objections from cloud service providers and hyperscale data center operators over its unconventional design and heavy operational burden."

Here is a summary of what has been delayed or canceled across the Rubin Ultra platform:

| Component | Status | Reason |
|---|---|---|
| Kyber NVL144 rack | Delayed 12+ months → 2028 | Midplane PCB manufacturing failures |
| NVL72x2 back-to-back rack | Canceled | Rejected by cloud and hyperscale operators |
| Rubin Ultra four-die version | Canceled | Not specified beyond product-level change |
| NVL576 (8-rack CPO system) | Likely delayed or limited volume | CPO production readiness uncertain |

## What is the NVL576 and is it also affected?

The **NVL576** is a larger-scale system that connects eight Oberon racks via CPO (Co-Packaged Optics), forming a two-tier fully connected network. [SemiAnalysis, as covered by GuruFocus](https://www.gurufocus.com/news/8944804/nvidia-faces-major-setback-with-kyber-nvl144-architecture-delay-nvda), stated the NVL576 "may also face delays or be limited to low-volume shipments given the current challenges facing CPO." CPO-enabled NVSwitches will not be fully ready until the Feynman generation, according to SemiAnalysis's March 2026 research report.

## What happened to the four-die Rubin Ultra chip?

SemiAnalysis reported that the four-compute-die version of Rubin Ultra has been canceled. Only the two-compute-die version remains, which delivers roughly half the performance of the original four-die configuration. Nvidia's stated response is to offset this by "significantly increasing sales of Oberon Rubin racks and Oberon Rubin Ultra racks."

The cancellation matters for AI chip packaging strategies across the industry, as multi-die configurations are central to scaling compute density.

## Which competitors could benefit from Nvidia's delay?

SemiAnalysis named two potential beneficiaries. The firm stated: "NVIDIA currently lacks a proven solution to scale the Oberon Rubin Ultra's scalability domain, creating an opening for competitors such as the AMD MI500X or Google's TPUv8i Broadfly to surpass Rubin Ultra in scalability capabilities." The window exists specifically in large-scale training scenarios where rack-level scalability is critical.

Here's what we know so far: Nvidia has no confirmed interim solution between the canceled NVL72x2 and the delayed Kyber NVL144, leaving a gap in its scalability roadmap until CPO NVSwitch arrives with the Feynman platform.

## How did markets react?

The SemiAnalysis report moved Asian PCB stocks in pre-market trading on July 6, 2026, according to Bloomberg's coverage. The manufacturing challenges with the Kyber midplane directly reflect technical bottlenecks for high-end PCB suppliers, and SemiAnalysis confirmed the delays will affect the memory, PCB, and ODM supply chains.

The supply chain pressure connects to trends already visible in Micron's HBM expansion and broader custom AI chip development efforts across the industry.

According to Nvidia's current roadmap, CPO NVSwitch will not be introduced until the next-generation Feynman platform — making 2028 the earliest realistic target for the Kyber NVL144.

## Frequently asked questions

**Why is the Nvidia Kyber NVL144 delayed?**

SemiAnalysis says the Kyber NVL144 is delayed because of manufacturing failures in the midplane PCB, which Nvidia calls the "orthogonal backplane." The board has 78 layers, uses hybrid materials including M9-grade copper-clad laminate and PTFE, and requires trace widths of 25μm or less. These specifications sit at the current limits of PCB manufacturing technology, making mass production impossible on the original schedule.

**When will the Nvidia Kyber NVL144 be available?**

According to SemiAnalysis's July 6, 2026 report, the Kyber NVL144 rack architecture has been delayed by more than 12 months, pushing its expected launch to 2028. The delay was disclosed just three months after Jensen Huang showcased the product at GTC. No revised intermediate timeline was provided in the report.

**What is the Nvidia NVL72x2 and why was it canceled?**

The NVL72x2 was a backup rack design that placed two Oberon racks back-to-back, using pure copper NVLink interconnects to scale the GPU domain without needing the problematic midplane PCB. It was canceled because cloud service providers and hyperscale data center operators objected to its unconventional design and the heavy operational burden it would impose on their infrastructure.

**What is the Rubin Ultra four-die cancellation?**

SemiAnalysis reported that the four-compute-die version of Rubin Ultra has been canceled entirely. Only the two-compute-die version remains in production, which delivers roughly half the performance of the original four-die design. Nvidia plans to offset this reduction in per-rack compute by significantly increasing sales of Oberon Rubin and Oberon Rubin Ultra racks.

**Which competitors benefit from Nvidia's Kyber delay?**

SemiAnalysis specifically named AMD and Google as potential beneficiaries. The firm said the lack of a proven scalability solution for Oberon Rubin Ultra "creates an opening for competitors such as the AMD MI500X or Google's TPUv8i Broadfly to surpass Rubin Ultra in scalability capabilities," particularly for large-scale AI training workloads that require high GPU domain counts.