AITechNode6 months ago
Moore Threads unveils Huagang GPU architecture
1 min read
Moore Threads unveiled its next-generation Huagang GPU architecture at its inaugural MUSA developer conference. The architecture supports full-precision computing from FP4 to FP64, delivers a 50% increase in compute density, and improves energy efficiency tenfold. It scales to clusters of up to 100,000 GPUs via MTLink interconnect.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyMeta