DeepSeek cut KV cache per token 54x in 9 months, called the third frontier lab
max_paperclips · x · 2026-09-11
Investor 0xdoug argues DeepSeek is firmly the third frontier lab after OpenAI and Anthropic — with a different strategy: OAI and Anth push the frontier of intelligence at acceptable efficiency, while DeepSeek pushes the frontier of efficiency at acceptable intelligence. The cited datapoint: DeepSeek has compressed KV cache size per token by 54x over the last 9 months.
Related event: DeepSeek Compresses KV Cache 54x in Nine Months to Sub-KB Per Token(6 posts)→
More from Infra
- Web Demo Approximates V4.1 Flash-Style Fast KV Prefill on Qwen3 — T_rex2700 · 2026-09-11
- OpenAI CFO: Compute I bought a year ago could sell for 3-5x today — and we're still short — rwang07 · 2026-09-11
- REVA Mines LLM Attention into Reusable Evidence Views, Cutting RAG Compression Overhead up to 15.6x — _reachsumit · 2026-09-11
- Edge0-35B-A3B preview MoE model for edge inference trends on Hugging Face — Edge0 · 2026-09-11
- Reflect Orbital wants to sell sunlight via volleyball-court mirrors on satellites — kyliebytes · 2026-09-11
- Data centers are for startups, not frontier labs: more compute is the anti-monopoly move — arthurcolle · 2026-09-11