deepseek-v4.1POST
双网线 DGX Spark 本地跑 V4.1 Flash：单用户 93.6 tok/s
接上第二根网线后，TensorFold 上单用户达 93.6 tok/s（vLLM 48.5，1.93 倍），6 用户 213.8 tok/s，长提示读取也变快，代码已开源。
Tech2Wild
@Tech2Wild12 天前收录原推发布于 2026.10.18
Tech2Wild @Tech2Wild原推发布于 2026.10.18
Bruh ! 🔌 Turned on the 2nd network cable between the Sparks and TensorFold got even faster: ⚡️ 93.6 tok/s for 1 user (vLLM: 48.5), 1.93x 👥 213.8 tok/s with 6 users (+29%) 📖 Long prompt reading now even with vLLM https://github.com/tonyd2wild/DeepSeek-V4.1-Flash-vLLM-DGX-Spark
这条是引用着另一条写的：x.com/tech2wild/status/2111658578100809966
x.com/tech2wild/status/2111666374032425064采集于 2026.10.18 16:25