deepseek-v4.1POST
4 台 DGX Spark 跑 V4.1 Flash 1017：吞吐 +26%，长提示快一倍
TP4 四机实测：6 流吞吐 131.9→165.7 tok/s，93K 提示 78s→42s，KV 池扩到 1.52M token。
Tech2Wild
@Tech2Wild11 天前收录原推发布于 2026.10.18
Tech2Wild @Tech2Wild原推发布于 2026.10.18
DeepSeek V4.1 Flash 1017 on 4x DGX Spark (TP4) 🚀 Same 4 Sparks vs the old V4.1 Flash: ⚡ 6 streams: 131.9 → 165.7 tok/s throughput (+26%) 📥 93K token prompt: 78s → 42s 🧠 300K context, KV pool 1.07M → 1.52M tokens Per prompt numbers 👇 https://github.com/tonyd2wild/DeepSeek-V4.1-Flash-vLLM-DGX-Spark/tree/main/runs/2026-10-17-1017
x.com/tech2wild/status/2111497954498334814采集于 2026.10.18 16:30