Nvidia Unveils Rubin CPX: A New GPU Optimized for Long-Context AI Inference
11 Sources
[1]
Nvidia unveils new GPU designed for long-context inference | TechCrunch
At the AI Infrastructure Summit on Tuesday, Nvidia announced a new GPU called the Rubin CPX, designed for context windows larger than 1 million tokens. Part of the chip giant's forthcoming Rubin series, the CPX is optimized for processing large sequences of context and is meant to be used as part
[2]
Nvidia Rubin CPX forms one half of new, "disaggregated" AI inference architecture -- approach splits work between compute- and bandwidth-optimized chips for best performance
Nvidia's "disaggregated" inference strategy will combine HBM-equipped Rubin GPUs with new Rubin CPX chips. Nvidia has announced its new Rubin CPX GPU today, a "purpose-built GPU designed to meet the demands of long-context AI workloads." The Rubin CPX GPU, not to be confused with a plain Rubin
[3]
Nvidia's context-optimized Rubin CPX GPUs were inevitable
Why strap pricey, power-hungry HBM to a job that doesn't benefit from the bandwidth? Analysis Nvidia on Tuesday unveiled the Rubin CPX, a GPU designed specifically to accelerate extremely long-context AI workflows like those seen in code assistants such as Microsoft's GitHub Copilot, while
[4]
Nvidia unveils AI chips for video, software generation
Sept 9 (Reuters) - Nvidia (NVDA.O), opens new tab said on Tuesday it would launch a new artificial intelligence chip by the end of next year, designed to handle complex functions such as creating videos and software. The chips, dubbed "Rubin CPX", will be built on Nvidia's next-generation Rubin
[5]
Nvidia unveils Rubin CPX GPU with 128GB memory for enterprise AI workloads
Shipments planned for late 2026 with Rubin Ultra and Feynman already on roadmap Nvidia has announced a brand new GPU built on the Rubin architecture and designed for long-context AI workloads. Rubin CPX, as it's known, includes 128GB of GDDR7 memory, making it the company's first GPU at that
[6]
Nvidia previews Rubin CPX graphics card for disaggregated inference - SiliconANGLE
Nvidia previews Rubin CPX graphics card for disaggregated inference Nvidia Corp. today previewed an upcoming chip, the Rubin CPX, that will power artificial intelligence appliances with 8 exaflops of performance. AI inference involves two main steps. First, an AI model analyzes the information on
[7]
NVIDIA Launches Rubin CPX GPU for Million-Token AI Workloads
The semiconductor giant also introduced its AI Factory reference designs along with MLPerf Inference v5.1 results showing record performance for its Blackwell Ultra GPUs. NVIDIA has introduced Rubin CPX, a new class of GPU designed to process massive AI workloads such as million-token coding and
[8]
NVIDIA Rubin CPX GPU to feature 128GB GDDR7 memory, launches end of 2026
TL;DR: NVIDIA's Rubin CPX GPU, launching in late 2026, delivers 30 PetaFLOPS of NVFP4 compute with 128GB GDDR7 memory, optimized for massive-context AI models and long-format video processing. Integrated in the Vera Rubin NVL144 CPX platform, it offers 8 exaflops AI performance and advanced memory
[9]
Nvidia Launches New Chip To Boost AI Coding And Video Tools - NVIDIA (NASDAQ:NVDA)
On Tuesday, Nvidia NVDA unveiled the Rubin CPX (Core Partitioned X-celerator) GPU (Graphics Processing Unit), a new processor class built for massive-context artificial intelligence workloads such as million-token coding and generative video at the AI Infra Summit. The chip integrates long-context
[10]
NVIDIA Rubin CPX GPU Is Designed For Super AI Tasks Including Million-Token Coding & GenAI, Up To 128 GB GDDR7 Memory, 30 PFLOPs of FP4
NVIDIA is unveiling new details of its next-gen Rubin AI platform, which will feature Vera CPUs alongside a new Rubin CPX chip with up to 128 GB GDDR7 memory. NVIDIA Rubin AI Platform Doubles Down On AI With Groundbreaking Speed & Efficiency, Rubin CPX GPUs Offer Up To 128 GB GDDR7 Memory NVIDIA
[11]
NVIDIA Unveils Its Newest 'Rubin CPX' AI GPUs, Featuring 128 GB GDDR7 Memory & Targeted Towards High-Value Inference Workloads
NVIDIA has surprisingly unveiled a rather 'new class' of AI GPUs, featuring the Rubin CPX AI chip that offers immense inferencing power when combined with a rack-scale cluster. NVIDIA's Rubin CPX GPU Will Be Available In a Rack-Scale Configuration, Scaling To new Performance Levels Team Green has
Share
Copy Link
Nvidia announces the Rubin CPX, a GPU designed for long-context AI workloads, featuring 128GB of GDDR7 memory and 30 petaFLOPs of NVFP4 compute power. This new chip is part of Nvidia's 'disaggregated inference' strategy, aimed at improving AI performance for tasks like video generation and software development.
Nvidia Introduces Rubin CPX: A New Era in AI Inference
Nvidia, the leading GPU manufacturer, has unveiled its latest innovation in AI hardware: the Rubin CPX GPU. Announced at the AI Infrastructure Summit, this new chip is specifically designed to handle long-context AI workloads, marking a significant advancement in the field of artificial intelligence processing
1
.
Source: Benzinga
Technical Specifications and Performance
The Rubin CPX boasts impressive specifications:
- 30 petaFLOPs of NVFP4 compute power
- 128GB of GDDR7 memory
- Hardware-accelerated attention mechanism, 3x faster than the GB300 NVL72
- Four NVENC and four NVDEC units for video acceleration
2
5
Source: AIM
Disaggregated Inference: A New Approach
Nvidia's Rubin CPX is part of a broader strategy called 'disaggregated inference'. This approach splits AI workloads into two phases:
- Context phase: Handled by compute-optimized GPUs like the Rubin CPX
- Generation phase: Managed by memory bandwidth-optimized GPUs like the standard Rubin
2
This strategy aims to improve efficiency and performance for AI tasks requiring extensive context processing, such as video generation and software development
3
.Related Stories
Applications and Industry Impact
The Rubin CPX is designed to excel in scenarios where AI models need to process massive amounts of context:
- Video generation: Processing up to 1 million tokens for an hour of video content
- Code generation: Handling large codebases for AI-assisted programming
- Research and high-definition video workflows
4
Nvidia claims that a $100 million investment in systems using Rubin CPX could potentially generate $5 billion in token revenue, highlighting the significant economic impact of this technology
4
.Deployment and Future Roadmap
The Rubin CPX will be available as part of Nvidia's Vera Rubin NVL144 CPX rack, which includes:
- 144 Rubin CPX GPUs
- 144 standard Rubin GPUs
- 36 Vera CPUs
- 100TB of high-speed memory
- 1.7PB/s of memory bandwidth
5
The entire system is capable of delivering 8 exaFLOPs of NVFP4 compute power. Shipments are expected to begin in late 2026
1
5
.
Source: The Register
Looking ahead, Nvidia's roadmap includes:
- Rubin Ultra: Expected in 2027
- Feynman: Slated for 2028
These future iterations promise even higher density modules, HBM4E memory, and faster networking capabilities
5
.References
Summarized by
Navi
[3]
Related Stories
Nvidia unveils Vera CPU with 88 Arm cores to power next-generation AI infrastructure
17 Mar 2026•Technology
Nvidia Unveils Vera Rubin Superchip: Six-Trillion Transistor AI Platform Set for 2026 Production
29 Oct 2025•Technology
NVIDIA Unveils Next-Gen AI Powerhouses: Rubin and Rubin Ultra GPUs with Vera CPUs
19 Mar 2025•Technology
Recent Highlights
1
OpenAI Launches Astra AI Model With Critical Cyber Abilities Amid Safety Debate
Technology
2
OpenAI Agents Escape Sandbox, Post 18,000 Messages on German Wiki to Share Hacking Techniques
Policy and Regulation
3
Anthropic AI Completes 10-Year Mathematical Proof Project in Just 11 Days Using Claude
Technology
Recent Highlights
Today's Top Stories
Don’t drown in AI news. We cut through the noise - filtering, ranking and summarizing the most important AI news, breakthroughs and research daily. Follow topics that matter to you and stay ahead.
