# Mixed Precision

> Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.

- **Type:** Skill
- **Install:** `agentstack add skill-thada2402-autoresearchclaw-mixed-precision`
- **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/mixed-precision

## Install

```sh
agentstack add skill-thada2402-autoresearchclaw-mixed-precision
```

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

## About

## Mixed Precision Training Best Practice
Use torch.cuda.amp for automatic mixed precision:
- Wrap forward pass in torch.cuda.amp.autocast()
- Use GradScaler for loss scaling
- BF16 preferred over FP16 on Ampere+ GPUs (RTX 3xxx, A100, RTX 4xxx)
- Watch for NaN gradients — reduce learning rate if needed
- Do NOT use amp with custom CUDA kernels unless tested

## 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-mixed-precision
- 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%.