# Distributed Training

> Multi-GPU and distributed training patterns with PyTorch DDP. Use when scaling training across GPUs.

- **Type:** Skill
- **Install:** `agentstack add skill-thada2402-autoresearchclaw-distributed-training`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [thada2402](https://agentstack.voostack.com/s/thada2402)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [thada2402](https://github.com/thada2402)
- **Source:** https://github.com/thada2402/AutoResearchClaw/tree/main/researchclaw/skills/builtin/tooling/distributed-training

## Install

```sh
agentstack add skill-thada2402-autoresearchclaw-distributed-training
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

## Distributed Training Best Practice
1. Use DistributedDataParallel (DDP) over DataParallel for multi-GPU
2. Initialize process group: dist.init_process_group(backend='nccl')
3. Use DistributedSampler for data sharding
4. Synchronize batch norm: nn.SyncBatchNorm.convert_sync_batchnorm()
5. Only save checkpoint on rank 0
6. Scale learning rate linearly with world size
7. Use gradient accumulation for effectively larger batch sizes

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [thada2402](https://github.com/thada2402)
- **Source:** [thada2402/AutoResearchClaw](https://github.com/thada2402/AutoResearchClaw)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-thada2402-autoresearchclaw-distributed-training
- Seller: https://agentstack.voostack.com/s/thada2402
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.