推理优化方回应跑分质疑：V4.1 Flash 基准用真实输入分布
作者称自家 V4.1-Flash 基准采用真实输入分布、真实专家路由和与 SemiAnalysis AgentX 一致的部署配置，结果 10 月 20 日就已上线，早于 DeepInfer 发布。
It's easy to make inference benchmarks look impressive with random inputs and idealized expert routing. The harder part is making those numbers hold up on real workloads. Our DeepSeek-V4.1-Flash benchmarks use real input distributions, realistic expert routing, and the same serving configurations validated on @SemiAnalysis_ AgentX. Fun fact: our results have been online since Oct. 20, even before DeepInfer's release. And we'll deliver even more speedups! Synthetic benchmarks have their place, but let's be clear about what they actually measure. Check out our blog for the full optimization story and benchmarking methodology!
这条是引用着另一条写的：「vLLM 在 GB300 NVL72 上服务 V4.1 Flash：单 GPU 954K tok/s」