Rackscale AI Accelerators

Rackscale AI Accelerators technology area definition, domain scope, key architectural milestones, and verified ecosystem relationships.

Exponential Industry Ontology

Rackscale AI Accelerators

2023 → 2026
Swipe roadmap
Exponential Industry Backdrop
milestone
May 28, 2023
NVIDIA DGX GH200 AI supercomputer announcement
NVIDIA Corporation
milestone
Mar 18, 2024
NVIDIA Blackwell platform and GB200 NVL72 announcement (GTC 2024)
NVIDIA CorporationJensen Huang
partnership
May 31, 2026
First Dell PowerEdge XE9812 Vera Rubin NVL72 delivery to CoreWeave
Dell TechnologiesCoreWeaveNVIDIA Corporation
partnership
Jun 2, 2026
Intel–SambaNova–Foxconn rackscale AI infrastructure (Computex 2026)
IntelSambaNova SystemsFoxconn
milestone
Jun 2, 2026
Vector Core fully disaggregated inference demonstration
Vector Core ComputeIntelSambaNova Systems
milestone
Jul 23, 2026
AMD Helios rack-scale AI launch
Advanced Micro Devices
milestone
Aug 2026
SpaceX exclusive Nvidia GPU procurement commitment
SpaceXNVIDIA CorporationElon Musk
2026
milestone

SpaceX exclusive Nvidia GPU procurement commitment

Musk stated on SpaceX earnings call and on X that SpaceX will build exclusively on Nvidia / use Nvidia GPUs exclusively, citing Vera Rubin as best architecture. This is an executive procurement commitment; not modeled as a disclosed long-term exclusive supply contract.

Related: SpaceX · organization NVIDIA Corporation · organization Elon Musk · person
milestone

AMD Helios rack-scale AI launch

AMD launches Helios rack-scale AI infrastructure (72× MI455X) at Advancing AI 2026 (AMD blog).

Related: Advanced Micro Devices · organization
milestone

NVIDIA Vera Rubin customer stand-up / full production

Ian Buck (NVIDIA VP/GM) said Vera Rubin systems are in full production and being stood up at major customers; OpenAI planned scale adoption in Q3 2026 (Bloomberg, Jul 21, 2026).

Related: NVIDIA Corporation · organization
partnership

Intel–SambaNova–Foxconn rackscale AI infrastructure (Computex 2026)

Computex 2026: intent and production-ready demos of rackscale AI infrastructure for inference/agentic workloads on Xeon + SambaNova SN-50 RDUs with Foxconn system integration.

Related: Intel · organization SambaNova Systems · organization Foxconn · organization
milestone

Vector Core fully disaggregated inference demonstration

Live disaggregated inference demo: Xeon 6 orchestration, SambaNova SN40 decode, NVIDIA Blackwell prefill from Vector Core LA data center; Together.ai first commercial customer.

Related: Vector Core Compute · organization Intel · organization SambaNova Systems · organization
partnership

First Dell PowerEdge XE9812 Vera Rubin NVL72 delivery to CoreWeave

Michael Dell announced delivery of the world's first working liquid-cooled Dell PowerEdge XE9812 NVIDIA Vera Rubin NVL72 server rack for CoreWeave (X, May 31, 2026).

Related: Dell Technologies · organization CoreWeave · organization NVIDIA Corporation · organization
milestone

NVIDIA Vera Rubin platform announcement

NVIDIA announces Vera Rubin platform and related racks at GTC; seven chips in full production.

Related: NVIDIA Corporation · organization
2024
milestone

NVIDIA Blackwell platform and GB200 NVL72 announcement (GTC 2024)

GTC 2024 (Mar 18) launch of the NVIDIA Blackwell platform: Blackwell GPU architecture, GB200 Grace Blackwell Superchip, liquid-cooled GB200 NVL72 rack-scale system (72 Blackwell GPUs + 36 Grace CPUs on fifth-gen NVLink), HGX B200, and broad cloud/OEM adoption commitments. Foundational rackscale-AI milestone that established the NVL72 rack product line later continued by GB300 and Vera Rubin NVL72.

Related: NVIDIA Corporation · organization Jensen Huang · person
2023
milestone

NVIDIA DGX GH200 AI supercomputer announcement

Computex 2023: DGX GH200 large-memory AI supercomputer class with Grace Hopper Superchips and NVLink Switch System—predecessor NVLink domain architecture before Blackwell NVL72.

Related: NVIDIA Corporation · organization