NEWS
 Meta Integrates Network Interface onto Chip with MTIA 300The MTIA 300 stands out as Meta's first training chip that separates the communication load, which creates bottlenecks in the training of recommendation models, from general-purpose processors, delivering communication performance that is 3.9 times faster than GPUs. This is a news summary compiled for the AiPulse newsletter — not the original article. The original article is at engineering.fb.com. Read the original article AI Critique → English (automatic translation) |