#nice-part-usage-npu

#nice-part-usage-npu

Four generations, MTIA 300, 400, 450, and 500, have been produced within less than two years, with several already in production and others scheduled for mass deployment in 2026 and 2027. The quick pace is deliberate. Rather than betting on a single chip generation and waiting years for results, Meta has adopted a roughly six-month cadence per generation, using modular chiplet architecture to enable incremental upgrades without replacing entire rack systems.

For today, I'm going to demonstrate something that's been on my mind in a while - doing summarizing of PDFs completely in the browser, with Chrome's on-device AI. Unlike the Prompt API, summarization has been released since Chrome 138, so most likely those of you on Chrome can run these demos without problem. (You can see more about the AI API statuses if you're curious.)

The company, which is based in San Francisco and has an office in Pune, India, is targeting up to $35 million this year as it builds a royalty-driven on-device AI business. That growth has buoyed the company, which now has post-money valuation of between $270 million and $300 million, up from around $100 million in its 2022 Series B, Kheterpal said.

Intel is making a new push into GPUs, this time with a focus on data center workloads, as the chipmaker looks to reestablish itself in a market increasingly shaped by AI-driven demand and dominated by Nvidia. CEO Lip-Bu Tan said that after hiring a senior GPU architect, the company is working directly with customers to define requirements, signaling a more demand-driven approach as enterprises and cloud providers weigh their options for accelerated computing, according to a Reuters report.

Nvidia is reportedly positioning itself to become the 'Android for robotics'. Arm, meanwhile, has created a fully-fledged business unit for 'Physical AI' alongside its other two divisions for cloud/AI and edge. The priority in both cases is clear: innovation is moving into the physical domain, with new pioneers for the next step in IT systems. The rhetoric, however, is jumping the gun a little.

Scientists are showing that neuromorphic computers, designed to mimic the human brain, are not only useful for AI, but also for complex computational problems that normally run on supercomputers. This is reported by The Register. Neuromorphic computing differs fundamentally from the classic von Neumann architecture. Instead of a strict separation between memory and processing, these functions are closely intertwined. This limits data transport, a major source of energy consumption in modern computers. The human brain illustrates how efficient such an approach can be.

On paper, Positron's next-gen Asimov accelerators, no doubt named for the beloved science fiction author, don't look like much of a match for Nvidia's Rubin GPUs. Yet, the Arm-backed AI startup boasts its inference chip will churn out five times as many tokens per dollar while using one-fifth the power of Nvidia's latest accelerators to do it. Those are certainly some bold claims, which the company contends are possible because the chip was designed to support large-scale inference workloads.