DeepSeek V4.1 Flash Resets Architecture, Shrinking KV Cache to a Quarter

DeepSeek's V4.1 Flash resets its architecture: despite larger total and active parameters, working KV cache shrinks to a quarter and persistent cache to an eighth. Commenters praise the approach as a 'bitter lesson' style scientific exploration.

2026-09-16 ~ 2026-09-16 · 2 related posts

• DeepSeek V4.1 Flash Is an Architecture Reset: KV Cache Cut to 1/4 by Deleting Its Own Ideas — teortaxesTex · 2026-09-16
• DeepSeek keeps moving the quadratic component up, a 'bitter lesson' science play — teortaxesTex · 2026-09-16