vLLM 支持 NVIDIA Vera Rubin 芯片
精选理由
vLLM 支持 NVIDIA 新款 Vera Rubin 芯片，性能提升近8倍，适合关注推理优化的开发者。
vLLM 项目宣布支持 NVIDIA Vera Rubin 芯片。测试显示其在 MiniMax M3 on AgentX 基准上性能超过 GB200 7.8倍。该项目由 @inferact、@NVIDIAAI、@RedHat_AI 和 vLLM 社区合作推进。
原文 · vLLM
vLLM now supports NVIDIA Vera Rubin. The early results show more than 7.8x the throughput of GB200 on MiniMax M3 on AgentX.
@inferact, @NVIDIAAI, @RedHat_AI, and the vLLM community have been bringing vLLM up on Rubin since it was announced. Here is where things stand.
🧵 1/5 https://t.co/iN239Tytko
