8 卡实现 V4.1 Flash 单用户 1500+ tok/s

Zhihao Jia @JiaZhihao原推发布于 2026.10.21

在 X 上打开原推

Speed matters. Especially for today's AI agents, which can make thousands of LLM calls to complete a single task. Super excited to enable 1,500+ tokens/second/user for both DeepSeek V4.1 Flash and GLM-5.3-Flash on just 8 standard GPUs! 🚀 We're pushing the boundaries of inference speed to make AI agents faster than ever!

这条是引用着另一条写的：x.com/lithos_ai/status/2112582932900524089