**What one vLLM replica on an L40 can carry and how it fails**

> The experiment Percentes runs takes one of two serving replicas away under sustained load and measures what the survivor does. Each replica is vLLM, an engin... What one vLLM replica on an L40 can carry and how it fails Varun Mahadkar · 25 September 2026 The experiment Percentes runs takes one of two serving replicas away under sustained load and measures what the survivor does. Each replica is vLLM, an engine that l...

**来源信息**
- **来源**：Hacker News：AI 热帖
- **分类**：ai-products
- **发布时间**：2026-09-26 04:48（北京时间）
- **原文**：[打开原文](https://percentes.ai/writing/2026/calibrating-one-l40-configuration)