MiniMax (official)· @MiniMax_AI · X·· 3 小时前AI 评分56
AI 导读
MiniMax 转发并致谢 SGLang 团队：SGLang-TorchTPU 由 SGLang 与 Google TPU 团队、Meta PyTorch 团队共建，可将 MiniMax H3、GLM-5.3 Flash、Kimi K3 等开源模型部署在 TPU 上，并已支撑 Meta 生产环境推理。Muse Spark Open 在 InferenceX 8K/1K、bs=1 下解码达 770 tok/s，项目已在 GitHub 开源。MiniMax 表示期待高效视频推理方向更多开源工作。
正文 · 原文
Thank you for bringing H3 to TPUs! Excited to see more open-source work on efficient video inference and what it could enable: faster creative iteration, new interactive experiences, and more ways for developers to build with H3.
Today we launch SGLang-TorchTPU, built with @Google TPU team and Meta @PyTorch team. We’re excited to see it powering production inference at Meta! SGLang-TorchTPU is a TPU plugin for SGLang that brings: - Top open models on TPU: Muse Spark Open, GLM-5.3 Flash, Kimi K3, Ling 3.1 Flash, MiniMax H3 - SGLang’s production features for large agentic workloads - Custom MegaKernel: Muse Spark Open hits 770 tok/s decode at bs=1 on InferenceX 8K/1K SGLang-TorchTPU is available now: http://github.com/sgl-project/sglang-torchtpu在 X 查看被引用的帖子
来源：MiniMax (official) · x.com