search
stacked AI chip
Trends
- 1Huawei Open-Sources openPangu-2.0 Training Code for Ascend▼Huawei Open-Sources openPangu-2.0 Pretrain, SFT and RL Training Code on Ascend
Huawei has released openPangu-2.0, open-sourcing the pretraining, supervised fine-tuning and reinforcement learning training code for its Pangu AI models, built to run on its own Ascend chips. The move gives developers full access to the training pipeline and is being read as an effort to build an open ecosystem around Huawei's domestic AI hardware amid competition with Nvidia-based stacks.
- 2AMD to buy Fei-Fei Li's World Labs for $8.2 billion▼AMD (AMD) to acquire Fei-Fei Li's World Labs AI startup for USD 8.2bln
AMD has agreed to acquire World Labs, the spatial-intelligence AI startup founded by Stanford professor Fei-Fei Li, in a deal reported at $8.2 billion. The move would put one of the most prominent figures in AI research behind AMD's technology stack as the company pushes to challenge Nvidia in artificial intelligence computing.
- 3Stacked AI chip tracks motion changes with fast and slow layers▼Stacked AI chip uses fast and slow layers to recognize changes in motion over time
Researchers have developed a stacked AI chip that pairs fast and slow processing layers to recognize changes in motion over time. The design is aimed at improving how artificial intelligence systems interpret dynamic visual scenes, a task that has been difficult for conventional chips. Coverage of the work is so far limited, and details about the team behind it and its practical applications have not been widely reported.