NVIDIA AI
@NVIDIAAI
Teaching your AI new tricks.
加入 June 2016
898 正在關注 343.9K 粉絲
How can a 30B-parameter model activate just 3B parameters per token and still draw on the full model’s capacity?
Learn how dense and MoE models use parameters differently, and what that means for throughput, memory and serving complexity.
Check out our new technical explainer:
顯示更多
