DeepSeek report praised: absurdly tiny KV cache, dense infra design
stochasticchasm · x · 2026-09-23
stochasticchasm's read of DeepSeek's latest report: it packs impressive infra design into a few sentences, with the standout being an "absurdly" small KV cache. He notes far more moving parts than before make nailing every detail very hard, and calls it a report worth re-reading.
More from Infra
- Cloudflare Bets on Microtransactions to Save the Web, but Agents Want Answers, Not Fragments — Ronangmi · 2026-09-23
- Google Colab joins Google AI plans with faster GPUs and background execution — DynamicWebPaige · 2026-09-23
- NEAR AI confidential inference goes live on Bittensor via SayGm's TDX-enclave routing — markjeffrey · 2026-09-23
- 6 serving-side techniques that make LLM inference faster - from prefix caching to PD disaggregation — techNmak · 2026-09-23
- SanDisk shares surge 7.56% as Wall Street turns bullish on AI memory demand — Polymarket · 2026-09-23
- SGLang v0.5.20 ships: Intel XPU support, up to 52% faster decode — hsu_byron · 2026-09-23