DeepSeek V4.1 Flash reportedly adopts YOCO architecture for order-of-magnitude KV savings
donglixp · x · 2026-09-11
DeepSeek V4.1 Flash has reportedly embraced YOCO (You Only Cache Once) as the soul of its architecture, per a credible unconfirmed leak, inheriting YOCO's order-of-magnitude advantages in prefill and KV caching. The decoder-decoder architecture, from a 2024 paper, caches KV pairs only once while retaining global attention, extends to 1M context with near-perfect needle retrieval, and improves inference memory, prefill latency, and throughput by orders of magnitude.
Related event: DeepSeek V4.1 Flash Confirmed to Center on YOCO Architecture(7 posts)→
More from Models
- DeepSeek cut KV cache per token from 389KB to 890B in two years as open-closed gap debate rages — teortaxesTex · 2026-10-27
- GPT-6 Astra controls dexterous hands zero-shot at just 5.2% success in 500 trials — stingning · 2026-10-27
- Unverified: fable 5.5 speculated at 4-5T parameters to outscale 1-3T Opus — haider1 · 2026-10-27
- Kimi K3 Is 'Open' Until You Succeed: License Caps Free Use at $20M Revenue — alex_verem · 2026-10-27
- Screenshot shows 'GPT-6 Astra Ultra' in ChatGPT model picker — unverified leak or joke — justalexoki · 2026-10-27
- DeepSeek Safety Eval Finds "Over-Attribution": Model Mistakes Ordinary Tasks for Tests — Much_Boysenberry9124 · 2026-10-27