uv-miles-rl-training

Community

Enterprise RL for large-scale MoE training

Authoruv-xiao
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides a robust framework for training large-scale Mixture-of-Experts (MoE) models, addressing challenges like training stability, low-precision quantization, and train-inference alignment in enterprise environments.

Core Features & Use Cases

  • Large MoE Training: Optimized for training models over 1TB, supporting DeepSeek V3 and Qwen3-MoE.
  • Low-Precision Training: Enables FP8 and INT4 quantization-aware training for reduced memory footprint and increased throughput.
  • Train-Inference Alignment: Ensures bit-wise identical alignment between training and inference using techniques like Rollout Routing Replay (R3).
  • Speculative RL: Achieves up to 25%+ rollout speedup through speculative decoding.
  • Use Case: Train a 1TB MoE model using FP8 quantization on H100 GPUs, ensuring bit-wise alignment with inference and maximizing throughput via speculative RL.

Quick Start

Use the uv-miles-rl-training skill to train a Qwen3-30B model with FP8 quantization and speculative RL enabled.

Dependency Matrix

Required Modules

sglang-router>=0.2.3raytorch>=2.0.0transformers>=4.40.0

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: uv-miles-rl-training
Download link: https://github.com/uv-xiao/pkbllm/archive/main.zip#uv-miles-rl-training

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.