Video
Animated explainers on AI systems.
-
10:49 Xiao Wang Asks, Da Wang Answers: From KV Cache to YOCO and Shared MemoryAn 11-minute animated explainer. Xiao Wang asks and Da Wang answers as one token's KV cache works through the four questions it must settle before it can become shared memory: identity, reuse, state and reading.
English narration · English subtitles
Watch