Huawei moves its Ascend 960DT chip launch up to early 2027

Huawei says its next-generation Ascend 960DT AI chip will now be ready in the first quarter of 2027, two quarters ahead of the earlier plan.

Paylaş
Huawei moves its Ascend 960DT chip launch up to early 2027

Huawei has pulled forward the launch of its next-generation Ascend 960DT AI chip. Speaking at the Huawei Connect conference on Thursday, the company said the chip is now expected to be ready in the first quarter of 2027. A Huawei spokesperson told TechCrunch the earlier plan had been the third quarter of 2027.

"Ascend 960 chips are launching ahead of schedule, doubling performance and advancing year by year," the spokesperson said. David Wang, Huawei's rotating and acting chairman, announced the revised timeline at the conference.

Peerium architecture and Atlas 950

Huawei wants to turn hundreds of thousands, and eventually millions, of AI chips into a single large computer. It calls the approach its Peerium Computing Architecture, built on UnifiedBus, the company's technology for linking processors with memory, storage and networking hardware. Rotating chairman Eric Xu said the architecture is being used to build larger AI computing systems for both training and inference.

The first systems based on it are the Atlas 950 SuperPoD and SuperCluster. Huawei says an Atlas 950 SuperCluster can connect up to 256,000 accelerator cards.

A question about scale

China tech analyst Rui Ma pointed out a gap on X. Huawei had previously said its Atlas 960 SuperPoD would scale to 15,488 Ascend 960 chips, while this week's announcement described a system with 4,096 chips. "The chip itself is coming WAY earlier, but the SuperPoD they announced is much smaller than what they originally laid out," she wrote.

Huawei continues to push its chip plans despite U.S. restrictions on China's access to advanced semiconductor technology. Ma said those restrictions are unlikely to stop China from developing its own semiconductor technology.

More detail is in the TechCrunch report.

Second source: RTTNews.

Devamını oku

Liquid AI تطلق أكبر نماذج LFM2.5 المفتوحة لتشغيل الوكلاء على الأجهزة

Liquid AI تطلق أكبر نماذج LFM2.5 المفتوحة لتشغيل الوكلاء على الأجهزة

أطلقت Liquid AI نموذج LFM2.5-24B-A2B كنموذج مفتوح، ويضم 24 مليار معامل إجمالا لكنه يشغل نحو 2.5 مليار منها في كل خطوة. وبحسب النتائج التي نشرتها الشركة، يولد النموذج المدرب للوكلاء الذين يستخدمون الأدوات 184 رمزا في الثانية على Apple M5 Max.

GlobalFeed Editor tarafından