MiniMax M3.1 Flash接入SGLang与Miles
MiniMax表示，MiniMax M3.1 Flash可通过SGLang进行推理，并通过Miles开展强化学习。公司声称，该模型使用SGLang进行批大小为1的解码时速度超过每秒1,000个token，并从第一天起即可用于生产。MiniMax称这项集成由其与NVIDIA、AMD及RadixArk共同完成，但报告未提供独立的吞吐性能测量。
这项集成同时覆盖SGLang推理和通过Miles进行的强化学习，直接关系到使用MiniMax M3.1 Flash开展相关工作流的从业者。
From inference to RL, ready from day one. 🐰 Thanks to the teams behind SGLang, and Miles @sgl_project alongside @NVIDIAAI and @AMD, for supporting MiniMax M3.1 Flash. Great building together!
SGLang: Space Bunny is here! 🐰 MiniMax M3.1 Flash hits >1K tok/s, bs1 decode with SGLang, production-ready from Day 0. This integration is a joint effort by @MiniMax_AI, @NVIDIAAI, @AMD, and @radixark, and you can also run RL with Miles! -Broad hardware support: NVIDIA Blackwell and
#MiniMax M3.1 Flash#SGLang#Miles#MiniMax#NVIDIA#AMD#RadixArk