Rackscale AI Accelerators
- Exponential Industry
- Technology Area
- 12 Milestones
Fully co-designed rack- and POD-scale AI systems that combine accelerators, host CPUs, scale-up fabric (NVLink-class domains), and scale-out networking in one thermal/mechanical package. Lineage runs from multi-GPU HGX/DGX boxes through Grace Hopper NVL32 domains to liquid-cooled 72-GPU racks (GB200, GB300, Vera Rubin) and competing racks such as AMD Helios. NVIDIA, AMD, and OEM rack builders (Dell, Supermicro) ship the current generation for AI-factory halls.
Hidden Factory
Rackscale AI Accelerators
NVIDIA Groq 3 LPX Enters Full Production; Nebius Deploys in Token Factory
NVIDIA announced full production of the rack-scale Groq 3 LPX system (256 LPUs, 128GB SRAM, 640TB/s bandwidth), with Nebius deploying clusters into the Nebius Token Factory for low-latency agentic decoding achieving 3,400 tok/s on Gemma 4 31B /NVIDIA Newsroom/ /Nebius/.
SpaceXAI adopts NVIDIA Vera CPU and Vera Rubin for Agentic AI
SpaceXAI announced deployment of NVIDIA Vera CPUs featuring 88 Olympus cores and 1.2TB/s memory bandwidth to accelerate orchestration and code execution for Grok agentic AI workloads /NVIDIA Newsroom/ /X (formerly Twitter)/.
First production NVIDIA Vera Rubin systems arrive at Microsoft datacenters
Satya Nadella (Aug 21, 2026) posted that it was delivery day at Microsoft datacenters as the first production Vera Rubins arrived, thanking NVIDIA and Azure hardware and datacenter teams /X/.
SK hynix publishes CPO roadmap in Nature Electronics
SK hynix newsroom Aug 20, 2026: paper "Co-packaged optics for high-performance computing and artificial intelligence" in Nature Electronics (s41928-026-01681-6), corresponding authors Seunghoon Hong (SK hynix) and Kyusang Lee (UVA). Targets >100 Tb/s per node, <1 pJ/bit, <10 ns latency; optics-centric photonic interposer between XPU and memory pools to break the rack/pod bandwidth wall /SK hynix/ /Nature Electronics/.
Etched delivers first inference rack to Jane Street
Etched PR Aug 18, 2026: first rack shipped last month; Jane Street said it tested the chip, is pleased with early results, and has its own rack running in its data center. Treated as the announcement day; ship month is July 2026 without a calendar day /GlobeNewswire/.
NVIDIA and six institutions launch AI-factory financing platforms (>$500B)
NVIDIA announced MOUs with Apollo, BlackRock, Blackstone, Brookfield, Goldman Sachs, and KKR to set up independent compute-financing platforms designed to mobilize over $500 billion of third-party capital for AI-factory buildout. NVIDIA said the figure is not NVIDIA revenue, a single fund, or one customer commitment; partners independently underwrite each deal. Jensen Huang said NVIDIA may offer residual-value support on up to 25% of an opportunity. Final agreements were still outstanding /NVIDIA/ /Jensen Huang / X/.
AMD Helios rack-scale AI launch
AMD launches Helios rack-scale AI infrastructure (72× MI455X) at Advancing AI 2026 (AMD blog).
CoreWeave measures Vera Rubin NVL72 10x tokens per megawatt vs GB200
CoreWeave published first measured silicon performance on Vera Rubin NVL72. At a matched interactivity target, the rack generated 10x tokens-per-second per megawatt versus NVIDIA GB200 NVL72 on the same DeepSeek R1 workload, using TensorRT-LLM and Dynamo with NVFP4, expert parallelism, multi-token prediction, and disaggregated prefill/decode /CoreWeave/.
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).
NVIDIA Vera Rubin platform announcement
NVIDIA announces Vera Rubin platform and related racks at GTC; seven chips in full production.
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, sixth-generation air-cooled DGX B200 (8 Blackwell GPUs, two 5th Gen Intel Xeon; up to 144 PFLOPS FP4), 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; DGX B200 is the traditional air-cooled 8-GPU SuperPOD/BasePOD building block, not NVL72 /NVIDIA Newsroom/.
NVIDIA DGX GH200 AI supercomputer announcement
DGX GH200 large-memory AI supercomputer class with Grace Hopper Superchips and NVLink Switch System—predecessor NVLink domain architecture before Blackwell NVL72.