# Fastgen inference

> Fastgen inference is an open-source agent skill. Generate and inspect NVIDIA FastGen teacher or distilled-student outputs with the inference scripts or ComfyUI nodes: config, checkpoint, pr. It is available on Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose.

- **Kind:** Skill
- **Pricing:** Open source
- **Platforms:** Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
- **Website:** https://github.com/NVIDIA/skills/tree/main/skills/fastgen-inference
- **Repository:** https://github.com/nvidia/skills
- **GitHub stars:** 4,037
- **License:** Apache-2.0
- **Skill name:** fastgen-inference
- **Collection:** https://github.com/NVIDIA/skills
- **Listing updated:** 2026-11-17

## About

Generate and inspect NVIDIA FastGen teacher or distilled-student outputs with the inference scripts or ComfyUI nodes: config, checkpoint, prompts, conditioning media, seeds and sampling settings. Use it to prepare or execute sampling; use fastgen-validate to assess existing parity or quality evidence.

## When your agent uses it

> Generate and inspect NVIDIA FastGen teacher or distilled-student outputs with the inference scripts or ComfyUI nodes: config, checkpoint, prompts, conditioning media, seeds and sampling settings. Use it to prepare or execute sampling; use fastgen-validate to assess existing parity or quality evidence.

## What it can access

From a static check of the files on GitHub; nothing was run.

- [Runs shell and Python scripts](https://github.com/NVIDIA/skills/tree/HEAD/skills/fastgen-inference)
- [No network calls found in its scripts](https://github.com/NVIDIA/skills/tree/HEAD/skills/fastgen-inference)
- [License: Apache-2.0](https://github.com/NVIDIA/skills/tree/HEAD/skills/fastgen-inference)

## Install

### Claude Code

Copy the skill folder to `~/.claude/skills/fastgen-inference` to use it in all your projects:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/fastgen-inference &&
cp -R "$tmp/skills/fastgen-inference" ~/.claude/skills/fastgen-inference &&
rm -rf "$tmp"
```

For one project only, put the folder in `.claude/skills/fastgen-inference` inside it instead.

### Codex

Copy the skill folder to `~/.agents/skills/fastgen-inference` to use it in every repository:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/fastgen-inference &&
cp -R "$tmp/skills/fastgen-inference" ~/.agents/skills/fastgen-inference &&
rm -rf "$tmp"
```

For one repository only, put the folder in `.agents/skills/fastgen-inference` inside it instead.

### Cursor

Copy the skill folder to `~/.cursor/skills/fastgen-inference` to use it in every project:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/fastgen-inference &&
cp -R "$tmp/skills/fastgen-inference" ~/.cursor/skills/fastgen-inference &&
rm -rf "$tmp"
```

For one project only, put the folder in `.cursor/skills/fastgen-inference` inside it instead.

### Gemini CLI

Run in a terminal (add `--scope workspace` to install it for the current workspace only):

```sh
gemini skills install https://github.com/NVIDIA/skills.git --path skills/fastgen-inference
```

Or copy the folder to `~/.gemini/skills/fastgen-inference` yourself.

### VS Code

For GitHub Copilot in VS Code, copy the skill folder to `~/.copilot/skills/fastgen-inference`:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/fastgen-inference &&
cp -R "$tmp/skills/fastgen-inference" ~/.copilot/skills/fastgen-inference &&
rm -rf "$tmp"
```

For one project only, put the folder in `.github/skills/fastgen-inference` inside it instead.

### Other agents

Get the folder:

```sh
git clone --depth 1 https://github.com/NVIDIA/skills.git
```

Then copy `skills/skills/fastgen-inference` into your agent's skills folder as `fastgen-inference`. Agents that support SKILL.md read one folder per skill.

## FAQ

### How do I install Fastgen inference in Claude Code?

Copy the skill folder from GitHub to ~/.claude/skills/fastgen-inference to use it in all your projects, or to .claude/skills/fastgen-inference in one project.

### Does Fastgen inference run scripts?

Yes. It runs shell and Python scripts. No network calls were found in its scripts. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.

### Which AI agents can use Fastgen inference?

Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.

---
Source: https://ai-powered.com/skills/fastgen-inference
