DeepSeek V4.1 Flash Is an Architecture Reset: KV Cache Cut to 1/4 by Deleting Its Own Ideas

teortaxesTex · x · 2026-09-16

A Zhihu breakdown by Exhalation argues DeepSeek's V4.1 Flash is an architecture reset, not just a cheaper model: despite more total and active parameters than its predecessor, working KV cache drops to one quarter and persistent cache storage to one eighth. The gains come from deleting old modules, sharing KV states, and recomputing local context.

teortaxesTex frames this as DeepSeek pushing the quadratic component into ever rarer operations—accepting the bitter lesson even in its own science, searching for the irreducible part.

Original post →

More from Infra

Infra channel →