What it does
The skill covers training large language models with between 2B and 462B parameters using NVIDIA Megatron-Core. It supports tensor, pipeline, sequence, context and expert parallelism.
The publisher suggests it for training models above 1B parameters where GPU efficiency matters most, and cites 47% MFU on H100 GPUs. The publisher also states that the framework has been used for Nemotron, LLaMA and DeepSeek models.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- AI Templates (aitmpl) first seen 13 Nov 2026 · last seen 18 Nov 2026 · its page on the source · figures reported by the source: aitmpl downloads 96
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.
v1.0.0As shown on www.aitmpl.com when we last read it