domains / families / research / miles

miles

separate

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.

When to use

• 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
• You want the research-grade original → use **slime**
• You need flexible backend swapping → use **verl**
• You want PyTorch-native abstractions → use **torchforge**

When not to use

• Research-grade original slime
• Flexible backend swapping with verl
• PyTorch-native abstractions with torchforge

Skill page

Source