miles-rl-training

miles-rl-training is a skill for Claude Code, Codex from synthetic-sciences/openscience. It costs 51 tokens per session (2,568 once invoked), scanned A, original, Apache-2.0.

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.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/synthetic-sciences/openscience/miles
Any agent
npx skills add synthetic-sciences/openscience --skill miles
Clone the repo
git clone --depth 1 https://github.com/synthetic-sciences/openscience

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for miles-rl-training

README.md
[![agentmods](https://agentmods.dev/badge/skills/synthetic-sciences/openscience/miles.svg)](https://agentmods.dev/skills/synthetic-sciences/openscience/miles)
Your own site
<a href="https://agentmods.dev/skills/synthetic-sciences/openscience/miles"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/miles.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,568 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00051 $0.02568
Opus 5 $0.00026 $0.01284
Sonnet 5 $0.00010 $0.00514
Haiku 4.5 $0.00005 $0.00257

Measured today against content hash 7bb694b48fcd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

miles-rl-training scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

backend/cli/skills/ml-inference/miles/SKILL.md · 328 lines

How it starts

The opening of the file, as written. The whole thing — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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

Hardware Requirements

  • Minimum: 4x H100 80GB (320 GB total VRAM) for 7B models
  • Recommended: 8x H100 80GB (640 GB total VRAM) for 70B+ models
  • For 1TB+ MoE models: Multi-node H200 clusters with InfiniBand
  • Storage: NVMe with 10+ TB for checkpoints

Cost Warning: miles workloads are expensive. A single 8x H100 node costs ~$25-50/hr. Multi-node training for large models can cost $500-2000+ per run.

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

Train-Inference Alignment

  • TIS/MIS: Truncated/Masked Importance Sampling for off-policy correction
  • Kernel-level optimization: FlashAttention-3, DeepGEMM integration

Installation

# Recommended: Docker
docker pull radixark/miles:latest
docker run --rm --gpus all --ipc=host --shm-size=16g \
  -it radixark/miles:latest /bin/bash

# From source
git clone https://github.com/radixark/miles.git
cd miles
pip install -r requirements.txt
pip install -e .

Read the full file on GitHub · 328 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. today First seen · 328 lines · 51 tokens per session scan A 7bb694b48fcd

Subscribe to this mod's changes

miles-rl-training is a skill published in the GitHub repository synthetic-sciences/openscience (3,432 stars, last pushed today), licensed Apache-2.0. It adds 51 tokens to every session and 2,568 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

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.

OpenLAIR/dr-claw · 51 tokens

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.

Orchestra-Research/AI-Research-SKILLs · 51 tokens

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.

liortesta/ClawdAgent · 51 tokens

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.

ihatesea69/HieuNghi-AI-Skills · 51 tokens

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.

davila7/claude-code-templates · 51 tokens

slime-rl-training

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

OpenLAIR/dr-claw · 52 tokens