miles-rl-training

SKILL.md

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.

Use this workflow for training large MoE models like DeepSeek V3 or Qwen3-MoE.

Use this workflow for maximum rollout throughput with EAGLE speculative decoding.

為使用 Miles（一種可立即投入生產的 Slime 分支）進行企業級 RL 訓練提供指導。當使用 FP8/INT4 訓練大型 MoE 模型、需要訓練推理對齊或需要推測 RL 以獲得最大吞吐量時使用。 來源：orchestra-research/ai-research-skills。

查看原文