The Latest News in AI

We publish news articles on Forbes, which are copied here for your convenience.  

The Graphcore Data Center Architecture

The Graphcore disaggregated accelerator could be a game changer. I have recently finished a research paper looking into the data center architecture for deploying the Graphcore IPU-Machine, which is a network-attached accelerator for highly-parallel workloads. Lets...

Micron Looks To Be First To Market With HBM3 Update For Generative AI And HPC

According to the company, the new Gen-2 of HBM increases memory capacity by 50%, with another bump in the works for 2024. As you may have heard, in addition to NVIDIA GPUs, generative AI eats memory for lunch. And dinner. In fact, running ChatGPT takes 8 or 16 GPUs...

Cerebras Publishes 7 Trained Generative AI Models To Open Source

The AI company is the first to use Non-GPU tech to train GPT-based Large Language Models and make available to the AI community. The early days of an open AI community, sharing work and building on each other’s success, is over. As there is now much more money at...

Cerebras Partners With Qualcomm, Launches 3rd-Gen Wafer-Scale AI

The newest system from Cerebras can handle multi-trillion parameter generative AI problems at twice the performance of its predecessor, while partnering with Qualcomm will help them cut inference processing costs by 10X. Cerebras Systems, the innovative startup who’s...

IBM Advances Quantum Dev With More Performance And Qiskit Functions

IBM Qiskit, used to develop quantum circuits, is being augmented with a Quantum Function Catalog, is also being updated to deliver faster performance to speed application development. When Qiskit launched in 2017, the Quantum development tool helped learners and...

Arm Adds More AI Firepower

As I covered in a recent article on the status of startups building chips for AI, the AI accelerator market will become quite crowded over the next 12-18 months. Not to be outdone, Arm is now extending its neural network processor family, adding logic designs for...

IBM And Rapidus Will Collaborate To Build 2nm Chips In Japan.

IBM, who invented the tech everyone will use to create 2nm silicon, is partnering with Rapidus to bring it to market The world now realizes that major economies need to have reliable and secure access to semiconductors, the heart of the digital economy, not to mention...

The 2024 AI HW Summit: Here’s What Caught My Attention

The Summit drew over 1000 attendees this year, with scores of presentations and hundreds of AI leaders from large companies as well as many startups. Every September since 2019, the AI HW Summit in the Bay Area has been the focal point for new technologies around AI....

Tenstorrent Opens Office In Japan To Capitalize On RISC-V + AI

Is the company setting up the first RISC-V HPC win? Tenstorrent, the Toronto-based semiconductor company, now led by the super-star chip designer Jim Keller, has just opened a new office in Japan. So, as many other AI startups are struggling, Tenstorrent is doubling...

With MLPerf, NVIDIA Wins, AGAIN!

While the new H100 GPU shows off its Transformer Engine in MLPerf, Intel advances with Gaudi-2 accelerator, and MosaicML shows A100 results nearly as good as H100 with their software. Every six months, MLCommons orchestrates and publishes on mlcommons.org over one...