Miles Rl Training

What it does

When your agent uses it

• Training large MoE models with FP8/INT4
• Needing train-inference alignment
• Requiring speculative RL for maximum throughput

Example prompts

• “Use the miles-rl-training skill to provide guidance for enterprise-grade RL training using miles, a production-ready fork of slime”
• “/miles-rl-training”

Requirements

• Python 3
• Docker

Workflow steps

4 steps, taken from the step headings in SKILL.md.

1. 1Environment Setup
2. 2Configure Training
3. 3Enable Speculative Decoding
4. 4Enable Online MTP Training (Optional)

What it can do on your machine

Read from SKILL.md and the folder at commit 773a529. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • python
  • docker
  • pip
  • git

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • github.com

  Also links to:

  • lmsys.org

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Miles Rl Training loads about 2.2k tokens when it runs, and up to ~4.7k if it reads all its reference files. Until then it costs about 63 tokens; SKILL.md has 697 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~63

When it runs · the whole SKILL.md, loaded when a task matches

~2.2k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~4.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Orchestra-Research/AI-Research-SKILLs at commit 773a529, republished under its MIT licence (© Orchestra-Research). 697 words, ~2,224 tokens.

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

# 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 .

python train.py \
    --advantage-estimator grpo \
    --model-name qwen3-30b-a3b \
    --hf-checkpoint /path/to/qwen3-30b-a3b-hf \
    --rollout-batch-size 512 \
    --n-samples-per-prompt 8

# FP8 block scaling (recommended for stability)
export NVTE_FP8_BLOCK_SCALING_FP32_SCALES=1
export CUDA_DEVICE_MAX_CONNECTIONS=1

python train.py \
    --actor-num-gpus-per-node 8 \
    --rollout-num-gpus 8 \
    --hf-checkpoint /path/to/deepseek-v3 \
    --advantage-estimator grpo \
    --tensor-model-parallel-size 8 \
    --expert-model-parallel-size 4 \
    --prompt-data /path/to/data.jsonl \
    --num-rollout 3000

python train.py \
    --actor-num-gpus-per-node 8 \
    --hf-checkpoint /path/to/target-model \
    --sglang-speculative-algorithm EAGLE \
    --sglang-speculative-num-steps 3 \
    --sglang-speculative-eagle-topk 1 \
    --sglang-speculative-num-draft-tokens 4 \
    --sglang-speculative-draft-model-path /path/to/draft-model \
    --advantage-estimator grpo \
    --prompt-data /path/to/data.jsonl

--mtp-num-layers 1 \
--enable-mtp-training \
--mtp-loss-scaling-factor 0.2

--actor-num-nodes 1
--actor-num-gpus-per-node 8
--rollout-num-gpus 8
--rollout-num-gpus-per-engine 2
--colocate

--tensor-model-parallel-size 8
--pipeline-model-parallel-size 2
--expert-model-parallel-size 4    # MoE expert parallelism

--sglang-speculative-algorithm EAGLE
--sglang-speculative-num-steps 3
--sglang-speculative-eagle-topk 1
--sglang-speculative-num-draft-tokens 4
--sglang-enable-draft-weights-cpu-backup
--sglang-speculative-draft-model-path /your/draft/model/path

--mtp-num-layers 1
--enable-mtp-training
--mtp-loss-scaling-factor 0.2

@dataclass
class Sample:
    prompt: str | list[dict]
    tokens: list[int]
    response: str
    reward: float | dict
    loss_mask: list[int]
    status: Status
    metadata: dict
    rollout_log_probs: list[float]
    rollout_routed_experts: list[list[int]]  # MoE routing for R3

© Orchestra-Research, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in 06-post-training/miles of Orchestra-Research/AI-Research-SKILLs.

• SKILL.md
• references/api-reference.md
• references/troubleshooting.md

Open the folder on GitHubat commit 773a529

Used in 2 other repositories

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in Orchestra-Research/AI-Research-SKILLs, which our catalogue first saw on October 7, 2026.

• davila7/claude-code-templatescli-tool/components/skills/ai-research/post-training-miles
• OpenLAIR/dr-clawskills/post-training/miles