AI Trends

Trending story Continuously updated

NVIDIA Releases Rubin HPC GPU, Q.ANT Showcases Photonic NPU

11 reports3 discussions14 story updatesUpdated Nov 18 17:36

Understand this story

AI overview

On November 17, 2026, NVIDIA officially unveiled the Rubin HPC GPU at the SC26 conference. The chip belongs to the Vera Rubin platform, featuring over 50,000 CUDA cores per GPU, sparse data acceleration capabilities, and seventh-generation NVLink interconnect technology, designed to accelerate agent simulation workloads in science and engineering fields, with an expected market launch in 2028. Ian Buck, Vice President of Supercomputing and High-Performance Computing at NVIDIA, noted that faster simulations help accelerate AI agent testing and subsequent discoveries. Subsequently, on November 18, German company Q.ANT also unveiled its next-generation photonic processor, NPU Gen 2+, based on thin-film lithium niobate, at the SC26 conference. The company demonstrated a hybrid system combining its product with AMD GPUs running large language models, using optical discrete Fourier transforms to replace high-overhead attention layers to alleviate computing bottlenecks, and plans to launch commercial systems integrating dual-generation products in the second half of 2027, along with an open-source SDK.

AI-generated from public reports

Latest development · Report

Q.ANT Releases NPU Gen 2+ Photonic Chip, First Demonstration of Running Large Language Models

Developments

2 confirmed developments

  1. Q.ANT releases photonic processor NPU Gen 2+ and demonstrates running large language models

    Source:English text is being prepared.
  2. NVIDIA releases Rubin HPC GPU

    Source:NVIDIA:Newsroom

Reports and discussion timeline

Browse reports and discussion by time. Their evidence levels remain distinct.

Nov 18

  1. Semiconductor Industry Panorama

    Q.ANT Releases NPU Gen 2+ Photonic Chip, First Demonstration of Running Large Language Models

    German company Q.ANT unveiled its next-generation photonic processor, NPU Gen 2+, based on thin-film lithium niobate at the SC26 conference, and demonstrated on-site a hybrid system combining it with an AMD GPU running a large language model. The processor adds optical discrete Fourier transform capabilities, using optical operations to replace the computationally expensive attention layers in large models, aiming to alleviate computing bottlenecks. The company plans to launch a commercial system integrating both generations of products in the second half of 2027 and has open-sourced an SDK to support developer testing.

  2. SSPAI

    Morning Brief: China Region App Store Makes AIGC Compliance Mandatory for Listing, OpenAI Releases GPT-6.2…

    The SSPAI Morning Brief rounds up several developments: the China region App Store has made AIGC compliance materials mandatory for listing; OpenAI released GPT-6.2 Astra and GPT-6.2 Sol on November 17 local time, with both models launching the same day on ChatGPT Work, Codex, and the API—Astra at $8 input and $40 output per million tokens, and Sol at $2 input and $10 output. Other items include Kuaishou Kling launching Kling Image 4.0, SenseTime open-sourcing the official version of SenseNova Loop-9B, DeepSeek imposing limits on long conversations, and Trajectory Labs publishing the results of Gemini 4 Argon safety testing.

  3. Jiwei.com

    NVIDIA Unveils Rubin HPC GPU at SC26, Expected to Launch in 2028

    At the Supercomputing 2026 conference, NVIDIA unveiled its new GPU chip Rubin HPC, aimed at accelerating science, engineering, and analytics workloads, with an expected launch in 2028. The chip belongs to the Vera Rubin platform, features more than 50,000 CUDA cores, offers sparse data acceleration capabilities, and adopts seventh-generation NVIDIA NVLink interconnect technology. Ian Buck, NVIDIA's vice president of hyperscale and high-performance computing, said that faster simulation means faster discovery, and that Rubin HPC can accelerate AI agents in testing ideas and guide subsequent simulations.

  4. Jiwei.comRelated discussion

    Jiwei.com joined this discussion

    This post contributes to heat; it is not a formal report or confirmed fact.

  5. NVIDIA:NewsroomFirst-party

    NVIDIA Announces Third Quarter Fiscal 2027 Financial Results, Revenue of $115.8 Billion, Up 103% Year-over-Year

    NVIDIA announced its financial results for the third quarter of fiscal 2027, ended October 25, 2026, with revenue of $115.8 billion, up 103% year-over-year and up 20% quarter-over-quarter; data center revenue was $107.6 billion, up 110% year-over-year. Vera Rubin NVL72 has begun shipping and is running at partners including CoreWeave, Google Cloud, Microsoft Azure, Oracle Cloud Infrastructure, and Nebius. The company expects fourth-quarter revenue of $130 billion, plus or minus 3%, and this guidance does not include any data center compute revenue from China.

Nov 17

  1. TechSpotRelated discussion

    TechSpot joined this discussion

    This post contributes to heat; it is not a formal report or confirmed fact.

  2. ServeTheHome

    NVIDIA Announces 2028 Launch of Rubin HPC Server GPU for Scientific Computing

    At SC26, NVIDIA announced that it is developing the Rubin HPC GPU for high-performance computing workloads, with plans to launch it in 2028. It will have more than 50,000 CUDA cores, roughly twice as many as the current Rubin server chip. The chip will support NVLink 7 and may use HBM4e memory, making it NVIDIA's first major HPC-class product since Hopper. NVIDIA also mentioned that it has "sparse data acceleration" capabilities, but did not disclose details about performance or the memory subsystem.

  3. English text is being prepared.

    NVIDIA Releases Rubin HPC GPU: Single Card Exceeds 50,000 CUDA Cores, a Record, Expected to Launch in 2028

    At the SC26 conference, NVIDIA released the Rubin HPC GPU based on the Vera Rubin platform, with more than 50,000 CUDA cores per card, setting a record, while the RTX PRO 6000 Blackwell has 24,064 and the GeForce RTX 5090 has 21,760. The GPU features sparse data acceleration capabilities, supports seventh-generation NVIDIA NVLink interconnect, and targets simulation tasks such as climate modeling, genomic analysis, engineering design, and financial risk computation. The product is expected to launch in 2028, and the official detailed specifications have not yet been announced.

  4. IT Home · AIRelated discussion

    IT Home · AI joined this discussion

    This post contributes to heat; it is not a formal report or confirmed fact.

  5. SiliconANGLE

    Nvidia Releases Rubin HPC Chips and Scientific Computing Software Libraries

    At the SC26 supercomputing conference, Nvidia released the Rubin HPC graphics card for scientific computing, featuring more than 50,000 CUDA cores and equipped with a new version of NVLink and sparse data acceleration capabilities, with plans to ship in 2028. At the same time, it also launched new libraries in the CUDA-X series, among which cuPhoton.xBeam can shorten the data analysis of the Event Horizon Telescope from one month to eight minutes, and open-sourced cuSpa. In addition, Nemotron for Science, based on Nemotron 3.5 Super VL, provides post-training workflows and nearly 50,000 chemistry problems, while CUDA-Q adds quantum software building blocks and qubit error correction algorithms.

  6. Wallstreetcn

    NVIDIA Releases Rubin HPC GPU, Betting on AI Agents to Reshape Supercomputing

    At SC26, NVIDIA unveiled Rubin HPC, a new-generation GPU designed specifically for scientific computing. A single GPU has more than 50,000 CUDA cores and uses seventh-generation NVLink, with launch expected in 2028. The CUDA-X libraries are being expanded in tandem: cuPhoton.xBeam cuts black hole data analysis from one month to 8 minutes, and Daviator delivers up to a 22x speedup for VASP quantum mechanics calculations. Vera CPU racks will be supplied by Dell, HPE, Lenovo and Supermicro in early 2027.

  7. cnBeta

    NVIDIA Releases Rubin HPC GPU to Accelerate Agentic Applications in Science and Engineering

    NVIDIA has released the Rubin HPC GPU for science, engineering, and data analysis, with each GPU equipped with more than 50,000 CUDA cores, setting a record for the number of CUDA cores. The GPU features sparse data acceleration capabilities, adopts seventh-generation NVLink interconnect, and uses a balanced design in which data movement and computation scale in sync to accelerate simulation workloads such as sparse matrix operations, stencil computations, sorting, and reductions. Rubin HPC is expected to be officially launched in 2028, and the CUDA-X software libraries will provide optimized implementations for it.

  8. Unite.AI

    NVIDIA Releases Rubin HPC GPU, Targeting Agent-Driven Science and Engineering

    At SC26, NVIDIA released the Rubin HPC GPU, targeting science, engineering, and analytics scenarios, with more than 50,000 CUDA cores per chip. The chip is aimed at workflows in which agents generate large numbers of candidate materials, molecules, and designs that then require repeated simulation; it performs sparse data acceleration in areas such as sparse matrices, stencil computations, sorting, and reductions, and is paired with CUDA-X libraries and seventh-generation NVLink. Rubin HPC belongs to the Vera Rubin platform and is expected to be available in 2028.

  9. NVIDIA:NewsroomFirst-party

    NVIDIA Releases Rubin HPC GPU: Accelerating Science and Engineering Agent Simulation

    At SC26, NVIDIA released Rubin HPC, a new GPU in the Vera Rubin platform targeting scientific, engineering, and analytics workloads. A single GPU features more than 50,000 CUDA cores and is equipped with sparse data acceleration capabilities and seventh-generation NVLink. The GPU employs a balanced design in which data movement and compute scale in tandem, and is intended to accelerate simulations invoked by agents. It is expected to launch in 2028.

Heat trend for this story

Current
21
Period peak
47 Nov 18 08:00
24-hour change
-53%

Move the pointer or select the chart to inspect hourly heat. Use the left and right arrow keys with a keyboard.

Related stories

  1. Related storiesGoogle launches Gemini 4 Hydrogen on Antigravity
  2. Related storiesMeta releases open-weight model Muse Spark Open
  3. Related storiesMeta launches Muse Wonder and Muse Wonder Full models
  4. Related storiesQwen Releases Qwen4-Max Preview Version