{"type":"link","version":"1.0","title":"Online softmax lets a key-value cache be split across machines while shipping only two scalars per partition, not the cache itself","author_name":"AI Archs","author_url":"https://ai-arch.pages.dev","provider_name":"AI Archs","provider_url":"https://ai-arch.pages.dev","url":"https://ai-arch.pages.dev/n/online-softmax-makes-distributed-attention-communication-cheap","thumbnail_url":"https://ai-arch.pages.dev/android-chrome-512x512.png","thumbnail_width":512,"thumbnail_height":512}