SGLang 支持 M3.1 Flash（Space Bunny）：单请求解码超 1K tok/s
SGLang 宣布 Day 0 支持开源权重，bs1 解码 >1K tok/s，AgentX 轨迹下每 GPU 约 100K tok/s、96 并发，覆盖 Blackwell/Hopper 与 AMD MI350X。
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 Hopper (GB300/B300/B200/H200), plus AMD Instinct MI350X and MI355X. -Agentic serving at scale: ~100K total tok/s per GPU on the AgentX coding-agent trace with 96 concurrent sessions. -Speculative decoding: Supports MiniMax's DSpark draft and a DFlash2 draft trained by @radixark; supports HiCache and multimodal input. -Ultra-low-latency inference: MegaKernels deliver 2.15× faster single-request decode.
这条是引用着另一条写的：「MiniMax M3.1 Flash 开源权重：428B 总参、23B 激活」