DeepSeek-V4.1-Flash cuts KV cache 4x with split encoder-decoder architecture
bendee983 · x · 2026-09-17
- DeepSeek's V4.1-Flash is called "a masterpiece in AI engineering and research". The model is nearly twice as large as its predecessor, yet KV storage dropped from 3,514 bytes per token to 890, making long agent sessions far cheaper to hold.
- The headline feature is a split encoder-decoder architecture: prefill runs through half the layers while decode uses the full stack, separating reading from writing.
- Key numbers: 8B active params on input, 16B on output; cache hits at $0.006 per million tokens; benchmark score of 40 vs Gemini's 41; a million-token session fits under 1GB of global KV (predecessor needed 3.5GB); local window state is no longer persisted to disk and persistent SSD cache falls to about one-eighth.
- Verdict: expect V4.1-Flash, like prior DeepSeek releases, to set a new precedent for open AI architectures.
Related event: DeepSeek V4.1 Flash resets architecture, shrinking KV cache to a quarter(5 posts)→
More from Infra
- South Korea's chip-led exports accelerate, bringing $1 trillion annual target closer — WSJ — pstAsiatech · 2026-11-02
- Amazon's $215B capex exceeds $168B operating cash flow, FCF turns -$42B — thealexbanks · 2026-11-02
- BofA: B200 and H100 GPU rental prices hit new highs, up 47% and 31% YTD — TheZachMueller · 2026-11-02
- vikhyat predicts alternating compute oversupply and undersupply on the road to AGI — TheZachMueller · 2026-11-02
- PyTorch Mac downloads hit 3.29M in October, up 20.5% MoM — LysandreJik · 2026-11-02
- CVSS 9.8 ingress-nginx flaw lets unauthenticated attackers get RCE and steal cluster Secrets — evilsocket · 2026-11-02