Skill · em Dados, IA e pesquisa
miles-rl-training
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.
Procedência
- Origem: davila7/claude-code-templates
- Caminho:
cli-tool/components/skills/ai-research/post-training-miles - Versão fixada:
57f899e5394bb8ca166f38eacae8f0853cbfe033 - Licença: MIT
- Espelhado em 25/09/2026
- 1 download no Claude Code Templates (lido em 25/09/2026)
Antes de instalar
3 arquivos · 18,4 KB · só texto, nenhum script
Instalar na sua CLI
O comando baixa a versão fixada (commit 57f899e) direto da origem, para a pasta que a CLI lê. Precisa de curl (macOS e Linux); no Windows não há comando, porque o Rook Labs é para macOS.
Claude Code
Neste projeto: instala em .claude/skills/miles-rl-training/.
d=".claude/skills/miles-rl-training" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/post-training-miles" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/references/api-reference.md" "$u/references/api-reference.md" \ -o "$d/references/troubleshooting.md" "$u/references/troubleshooting.md"
Global: instala em ~/.claude/skills/miles-rl-training/.
d="$HOME/.claude/skills/miles-rl-training" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/post-training-miles" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/references/api-reference.md" "$u/references/api-reference.md" \ -o "$d/references/troubleshooting.md" "$u/references/troubleshooting.md"
Codex
Neste projeto: instala em .agents/skills/miles-rl-training/.
d=".agents/skills/miles-rl-training" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/post-training-miles" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/references/api-reference.md" "$u/references/api-reference.md" \ -o "$d/references/troubleshooting.md" "$u/references/troubleshooting.md"
Global: instala em ~/.agents/skills/miles-rl-training/.
d="$HOME/.agents/skills/miles-rl-training" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/post-training-miles" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/references/api-reference.md" "$u/references/api-reference.md" \ -o "$d/references/troubleshooting.md" "$u/references/troubleshooting.md"
Antigravity
Neste projeto: instala em .agents/skills/miles-rl-training/.
d=".agents/skills/miles-rl-training" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/post-training-miles" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/references/api-reference.md" "$u/references/api-reference.md" \ -o "$d/references/troubleshooting.md" "$u/references/troubleshooting.md"
Global: instala em ~/.gemini/antigravity-cli/skills/miles-rl-training/.
d="$HOME/.gemini/antigravity-cli/skills/miles-rl-training" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/post-training-miles" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/references/api-reference.md" "$u/references/api-reference.md" \ -o "$d/references/troubleshooting.md" "$u/references/troubleshooting.md"
Peça ao Rook
Já usa o Rook Labs? Cole no chat do Rook: instale a skill https://rooklabs.sh/marketplace/cct.miles-rl-training
Prévia do SKILL.md
---
name: miles-rl-training
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 speculative RL for maximum throughput.
version: 1.0.0
author: Orchestra Research
license: MIT
tags: [Reinforcement Learning, MoE, FP8, INT4, Enterprise, SGLang, Megatron-LM]
dependencies: [sglang-router>=0.2.3, ray, torch>=2.0.0, transformers>=4.40.0]
---
# miles: Enterprise-Grade RL for Large-Scale Model Training
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.
## When to Use miles
**Choose miles when you need:**
- 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
**Consider alternatives when:**
- You want the research-grade original → use **slime**
- You need flexible backend swapping → use **verl**
- You want PyTorch-native abstractions → use **torchforge**
## Key Features
### Low-Precision Training
- **Unified FP8**: End-to-end FP8 for both inference and training
- **INT4 QAT**: 1TB models on single-machine VRAM (H200)
- **Rollout Routing Replay (R3)**: Bit-wise expert alignment for MoE
### Performance Optimizations
- **Speculative RL**: 25%+ rollout speedup with online SFT draft models
- **Zero-Copy Weight Sync**: CUDA IPC zero-copy mapping
- **Partial Rollout**: Recycle half-finished trajectories
…