SKILL

distributed-training-megatron-core

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.

Target: Learning & research. Automatically collected · unverified.

Use with Cursor

A guide for this combination is not available yet, and compatibility has not been verified.

Requirements

Only the author’s Skill metadata is included. Read the full instructions to check dependencies, licensing and conditions of use.

Choose an AI tool with documented instructions, or save the resource and request a guide after the page loads.

Read the author’s documentation ↗