research-miles
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 s...
Source facts
- Repository
- GrayCodeAI/starling
- Last source activity
- July 13, 2026 at 09:28
- Detected SKILL.md language
- English
- Stars
- 2
- Forks
- 0
Install options
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Review the source files
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Showing SKILL.md
SKILL.md
Source instructions · Read-only preview- name
- research-miles
- description
- 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 s...
- license
- MIT
- tags
- ["reinforcement-learning","moe","fp8","int4","enterprise"]
- version
- 1.0.0
- author
- Orchestra Research
- dependencies
- ["sglang-router>=0.2.3","ray","torch>=2.0.0","transformers>=4.40.0"]
## Resources
- **GitHub**: https://github.com/radixark/miles
- **Introduction Blog**: https://lmsys.org/blog/2025-11-19-miles/
- **Slime (upstream)**: https://github.com/THUDM/slime
- **SGLang**: https://github.com/sgl-project/sglang
View on GitHub