← BackHacker News front pageankitvguptaNov 21, 2026, 02:15 UTC+8Vibecoding an inference chipankitvgupta 用编码智能体在 AWS F2 FPGA 上运行 LLM,将逐位一致的完整模型基线从 6.43 tok/s 优化至 213.13 tok/s,提升 33.13×。Read the original ↗ShareCopy linkShare imageExport MarkdownSee every follow-up