Event ·Multi-source

DeepSeek V4.1 Flash 在 GB300 NVL72 上推理速度提升至 1.5 倍

Artificial Analysis 的 AA-AgentPerf 基准显示,DeepSeek V4.1 Flash 在 NVIDIA GB300 NVL72 上过去一个月速度提升明显:单智能体达到 848 tok/s,此前为 596 tok/s(1.42 倍)。单 GPU 吞吐量约为原来的 1.6 倍,每个智能体约 80 tok/s。提升来自新版 vLLM、DeepSeek V4.1 专用内核、FlashInfer 自动调优、更完整的 CUDA graph 覆盖以及调优后的投机解码。NVIDIA 更新的 Dynamo + vLLM 方案还把 prefill 和 decode 放在同一批 GPU 上运行。

Current read

DeepSeek V4.1 Flash 在 GB300 上一个月内单智能体速度从 596 涨到 848 tok/s,文章拆了 vLLM、FlashInfer 等具体优化手段,做部署的可以看看

11 sources56° AI heatLast updated 2026/11/6 20:33:47

Evidence

11 sources
Primary sourceArtificial Analysis
View source
Related source 3arXiv cs.AI
View source
Related source 5techcrunch
View source
Related source 8rohanpaul_ai
View source
Related source 10Gary Marcus
View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.