Agent Skills: spark-training-gotchas

Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.

UncategorizedID: wshobson/agents/spark-training-gotchas

Author

wshobson

https://github.com/wshobson View all skills

Repository

wshobson/agents

wshobsonLicense: MIT

39,5404,213

Install this agent skill to your local

pnpm dlx add-skill https://github.com/wshobson/agents/spark-training-gotchas

Skill Files

Browse the full folder contents for spark-training-gotchas.

Download Skill

Loading file tree…

Select a file to preview its contents.