miles-rl-training

Name: miles-rl-training
Availability: InStock
Author: KappTech88

Guide RL training of large MoE models with Miles using FP8/INT4 optimization.

Updated Mar 30, 2026

Search Tags:#fp8 #rl-training #sglang #megatron #moe #int4 #miles

Ready to run

npx skills add https://github.com/KappTech88/AI-RESEARCH-SKILLS-MCP --skill miles-rl-training-kapptech88

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: miles-rl-training
Source: https://github.com/KappTech88/AI-RESEARCH-SKILLS-MCP/tree/main/skills/miles
Command: npx skills add https://github.com/KappTech88/AI-RESEARCH-SKILLS-MCP --skill miles-rl-training-kapptech88

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires sglang-router>=0.2.3, ray, torch>=2.0.0, transformers>=4.40.0, and includes references (resource) components.

What problem does it solve?

Provides enterprise-grade guidance for RL training of large MoE models using miles, addressing complexity and scale challenges in production environments.

Core Features & Use Cases

Enterprise-grade RL workflow guidance for miles-based setups
Supports FP8/INT4 training, train-inference alignment, and speculative RL workflows
Real-world use case: orchestrating MoE model training at scale with robust routing and optimization

Quick Start

Run the production-ready Miles RL training workflow for large MoE models.

Frequently Asked Questions about miles-rl-training

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I set up RL training for large MoE models with FP8 and INT4 optimization?▼

You can execute RL training for large MoE models using a Miles-based workflow that applies FP8 and INT4 optimization alongside Megatron-style parallelism. This setup provides enterprise-grade guidance for production-scale training and rollout routing replay.

What is train-inference alignment in speculative RL workflows?▼

Train-inference alignment in speculative RL workflows ensures consistency between training and inference states during MoE model optimization. The Miles workflow provides guidance to maintain this alignment, which is critical for robust rollout routing replay in production environments.

Can I use SGLang with Megatron-style parallelism for MoE model training?▼

Yes, you can use SGLang with Megatron-style parallelism for MoE model training within the Miles workflow. This combination satisfies production requirements for integrating rollout routing replay and executing robust, large-scale RL training.

Do I need Ray and specific PyTorch versions for Miles MoE training?▼

Yes, you need Ray and PyTorch version 2.0.0 or higher, along with Transformers 4.40.0 or higher and SGLang-router 0.2.3 or higher. These dependencies are required to support the production-ready Miles RL training workflow for large MoE models.

What's the best way to handle rollout routing replay during RL training?▼

The best way to handle rollout routing replay is through the Miles workflow, which integrates SGLang to manage routing replay robustly. This approach ensures train-inference alignment and supports speculative RL workflows for large MoE models.

Why does MoE model training require specialized RL workflows?▼

MoE model training requires specialized RL workflows to address the complexity and scale challenges of production environments. The Miles workflow provides enterprise-grade guidance for applying FP8 and INT4 optimization, train-inference alignment, and routing replay to manage these challenges robustly.