DeepSeek Hits 96% Cache Ratio, Sparking User Data Retention Concerns
airesearch12 · x · 2026-08-13
A developer reported that DeepSeek's API achieved a 96.56% cache ratio under heavy traffic, significantly higher than the second-best provider at 91.60%, effectively halving GPU time usage.
However, this high cache ratio has sparked data privacy concerns. Critics point out that such a high hit rate implies the provider is likely storing all user input data to reuse computation results in subsequent requests.
More from Infra
- Dev publicly asks neoclouds for discounts on a $30k GPU compute purchase — Sauers_ · 2026-10-16
- New hardware day: local LLM deployment the moment it arrives — lxfater · 2026-10-16
- Together AI's score centering fixes RL training collapse under quantized inference — nrehiew_ · 2026-10-16
- Inference is splitting prefill and decode across specialized chips, not just H100s — AccBalanced · 2026-10-16
- Rebasely launches in beta: Git hosting built for humans and coding agents — handotdev · 2026-10-16
- Drama3 TTS lands in audio.cpp: up to 5x real-time on RTX 5090, <8GB VRAM mode too — Acceptable-Cycle4645 · 2026-10-16