2025-12-21
Moore Threads launches MTT C256 supernode architecture launched The Quaorvanka computing cluster possesses versatile computing capabilities and absolute precision, enabling efficient and stable AI training and inference at a scale of 10,000 kilowatts. [image]
Bloomberg
Chinese AI chipmaker Moore Threads announces a new generation of chips slated for mass production from 2026, just weeks after its blockbuster IPO in China
Moore Threads Technology Co. introduced a new generation of chips aimed at reducing artificial-intelligence developers' dependence …
2025-01-29
DeepSeek tried to do one thing: transplant its own model to Huawei Ascend 910B chip to run. Through the “dynamic precision adjustment” technology, they only lost 5% of the performance in the same task, but the cost dropped by 70%. [image]
Tom's Hardware
Huawei adds DeepSeek's R1 to its ModelArts Studio platform, saying the free model is “Ascend-adapted”, referencing its data center GPUs, but offers few details
Nvidia has competition in China. … The tech company explicitly said this version is “Ascend-adapted,” as in Huawei's Ascend data center GPUs.