SemiAnalysis
@SemiAnalysis_
๊ฐ์
January 2024
29 ํ๋ก์ ์ค 150K ํฌ
Similar to the panic over DeepSeek R1, some uneducated people think Kimi K3โs use of linear attention (KDA) is bad for NVIDIA, HBM, DRAM, and networking because it has relatively lower KV-cache requirements. The opposite is true, and we explain why below. ๐๏ธ 1/8๐งต
๋ ๋ณด๊ธฐ
