deepseek-v4.1IMAGE
vLLM 官方：V4.1 Flash 每美元 13 亿 token
vLLM 官方公布在 SemiAnalysis AgentX 上，DeepSeek-V4.1-Flash 单卡 83 万 tok/s、每美元 TCO 产出 13 亿 token，并称 agent 吞吐较首日提升 5 倍。
vLLM
@vllm_project10 天前收录原推发布于 2026.10.17
vLLM @vllm_project原推发布于 2026.10.17
🎉 Congrats @deepseek_ai on DeepSeek-V4.1-Flash-1017! Better scores and shorter outputs make it a great fit for long agent loops. Making each step fast is the serving side's job. On DeepSeek-V4.1-Flash, vLLM delivers 1.3B tokens per dollar TCO on SemiAnalysis AgentX: 830K tok/s per GPU (cached + input + output) at 100 tok/s per user. 🚀 It's been a fun few weeks building with the community. Chapter one, 5x agentic throughput since day 0: 🔗 https://vllm.ai/blog/2026-10-07-deepseek-v41-flash Next chapter coming soon. 👀
这条是引用着另一条写的：x.com/deepseek_ai/status/2111375640717033777
x.com/vllm_project/status/2111401488392343722采集于 2026.10.18 16:42