miles-rl-training

仓库创建 2025年11月3日最近提交 1 个月前SkillHot 收录 21 天前

▸ 精选理由

对追求高吞吐与训练-推理一致性的工程团队更有价值。

▸ 风险提示

依赖特定硬件与私有分支，部署与复现较为复杂。

这个 Skill 做什么

面向大规模MoE模型与低精度训练（FP8/INT4）的企业级RL训练指南。

提供面向企业级的大规模 RL 训练实践，特别为巨型 MoE 模型和低精度训练（如 FP8/INT4）场景优化。适合训练 TB 级模型、需要训练-推理对齐或用 speculative RL 提升吞吐的团队。基于生产就绪的 slime 分叉 miles，关注稳定性与性能工程。

▸ 展开 SKILL.md 英文原文

Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.

研究检索MoE低精度训练企业级通用

1.1w

Stars

817

Forks

仓库内 Skill

+704

7 日增星

安装 / 使用

给你的 Agent 一句话（通用）

帮我安装这个 skill：https://raw.githubusercontent.com/Orchestra-Research/AI-Research-SKILLs/main/06-post-training/miles/SKILL.md

或 curl 直取 SKILL.md

curl -fsSL "https://raw.githubusercontent.com/Orchestra-Research/AI-Research-SKILLs/main/06-post-training/miles/SKILL.md"

SKILL.MD 节选查看完整文件 ↗

# miles: Enterprise-Grade RL for Large-Scale Model Training

miles is a high-performance, enterprise-ready RL framework optimized for large-scale model post-training. Built as a production fork of slime, it addresses critical challenges in MoE training stability, low-precision training, and train-inference alignment.

## When to Use miles

**Choose miles when you need:**
- Training 1TB+ MoE models (DeepSeek V3, Qwen3-MoE)
- FP8 or INT4 quantization-aware training
- Bit-wise identical train-inference alignment
- Speculative RL for maximum throughput
- Production stability with enterprise support

**Consider alternatives when:**
- You want the research-grade original → use **slime**
- You need

via SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有