DeepSeek-V4.1-Flash on vLLM: 5x Agentic Throughput Since Day 0
DeepSeek-V4.1-Flash on vLLM: 5x Agentic Throughput Since Day 0
摘要
Within three weeks of release, vLLM made DeepSeek-V4.1-Flash 1.9x faster at low concurrency and lifted its throughput 5x on SemiAnalysis AgentX, with SWA bounded replay, CUDA graphs, DeepSeek's new kernels, and vLLM kernel fusions.
Within three weeks of release, vLLM made DeepSeek-V4.1-Flash 1.9x faster at low concurrency and lifted its throughput 5x on SemiAnalysis AgentX, with SWA bounded replay, CUDA graphs, DeepSeek's new kernels, and vLLM kernel fusions.
译自 vLLM · 官方博客 · 录于 二〇二六年十月七日