📰 vLLM Serves DeepSeek-V4.1-Flash on NVIDIA Vera Rubin NVL72 at 1.7M Tokens/s per GPU with 387 Tokens/s per User, 58x GB300 NVL72 at That Point and 2.7x at Peak…
On November 12, vLLM published the third post in its DeepSeek-V4.1-Flash series, led by Inferact. On one Vera Rubin NVL72 rack running the SemiAnalysis AgentX workload, it measured 1.7M total tokens/s per GPU at a P90 of 387 tokens/s per user, 58x GB300 NVL72 at the same interactivity, and 2.52M…
💬 What's your take? Join the discussion in the comments.
Read the original Chinese version
📰 vLLM 在英伟达 Vera Rubin NVL72 上跑 DeepSeek-V4.1-Flash：每用户 387 token/s 时单卡 170 万 token/s，为 GB300 NVL72 的 58 倍；峰值吞吐则是 2.7 倍
11 月 12 日，vLLM 发布 DeepSeek-V4.1-Flash 系列第三篇博客（Inferact 主导）：在一台 Vera Rubin NVL72 上，用 SemiAnalysis AgentX 负载测得每用户 P90 387 token/s 时单 GPU 总吞吐 170 万 token/s，是…
💬 你怎么看？欢迎在评论区讨论。