# MiniMax 祝贺 SGLang/RadixArk 发布开源强化学习框架 Miles v0.1

- 来源：MiniMax (official) (@MiniMax_AI)
- 发布时间：2026-08-19 03:11
- AIHOT 分数：26
- AIHOT 链接：https://aihot.virxact.com/items/cmsz1x1bz002iro3fzopllf7l
- 原文链接：https://x.com/MiniMax_AI/status/2089792270879142353

## AI 摘要

MiniMax 祝贺长期合作伙伴 SGLang/RadixArk 发布开源强化学习框架 Miles v0.1，用于 LLM 和多模态模型训练。过去 9 个月，72 位贡献者提交 1,326 次 commit，并在 Kimi K3、DeepSeek V4、Qwen 3.8、GLM 5.2、MiniMax H3 等前沿开源模型上完成测试。

## 正文

Congrats to our long-term partner SGLang/RadixArk on the launch of Miles v0.1! 🎉

From M-Series to H3 and Music 3, we’ve been closely building and pushing the OSS ecosystem forward together.

Nothing beats the feeling of seeing things we built together keep growing
@radixark 🤝 @MiniMax_AI

### 引用推文

> RadixArk：Today we're launching Miles v0.1, an open-source RL framework for LLMs and multimodal models. RL training is easy to start and hard to debug. Miles helps you en...