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)→

Original post →

More from Infra

Infra channel →