nvidia logo
Observability

Real file from a public repo · synced Sep 3, 2026

mcore-run-on-slurm

How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules across hardware and parallelism modes, container conventions, monitoring, and per-rank failure diagnosis.

nvidia/skills1.7k installsApache-2.0

Works with

Claude CodeCursorCodex CLIGitHub CopilotGemini CLI

Install in three steps

  1. 1

    Download the ZIP

    One file per agent, plus INSTALL.md with the exact paths below.

  2. 2

    Claude Code: copy SKILL.md into your skills folder

    .claude/skills/mcore-run-on-slurm/SKILL.md    # this project
    ~/.claude/skills/mcore-run-on-slurm/SKILL.md   # every project
  3. 3

    Other agents: use the matching file

    skill.mdc goes in Cursor’s .cursor/rules/. AGENTS.md works as GitHub Copilot instructions, a legacy .cursorrules, or a Codex / Gemini CLI instructions file.

More Observability skills

All Observability skills

Check your AI visibility

One URL in, a 0–100 score and the exact fixes out.

RUN THE CHECK

Browse all the tools

15 tools across six categories
13 of them never send your data anywhere

Free · No signup · No trial clock

SEE THE DIRECTORY