Megatron-Bridge

NVIDIA-NeMo/Megatron-Bridge

Training library for Megatron-based models with bidirectional Hugging Face conversion capability

697 stars

348 forks

Python

68 views

View on GitHub Add to Favorites

Installation

Option 1: Use slash command in Claude Code

/install-skill https://github.com/NVIDIA-NeMo/Megatron-Bridge

Option 2: Clone to skills directory

# Global (all projects)

git clone https://github.com/NVIDIA-NeMo/Megatron-Bridge ~/.claude/skills/Megatron-Bridge

# Project-specific

git clone https://github.com/NVIDIA-NeMo/Megatron-Bridge .claude/skills/Megatron-Bridge

Add MCP server to .cursor/mcp.json:

{
  "mcpServers": {
    "skillz": {
      "command": "npx",
      "args": ["-y", "skillz-mcp", "https://github.com/NVIDIA-NeMo/Megatron-Bridge"]
    }
  }
}

Restart Cursor after adding the configuration.

Option 1: Use Gemini CLI command

gemini extensions install https://github.com/NVIDIA-NeMo/Megatron-Bridge

Option 2: Clone to extensions directory

git clone https://github.com/NVIDIA-NeMo/Megatron-Bridge ~/.gemini/extensions/Megatron-Bridge

Topics

Related Skills

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

skill-writer

Tensors and Dynamic neural networks in Python with strong GPU acceleration