{"slug":"nvidia-mcore-run-on-slurm","source_name":"nvidia/mcore-run-on-slurm","name":"Nvidia/Mcore Run On Slurm","description":"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.","version":1,"lift":{"pass_rate_delta_pts":32,"pass_rate_pct":100,"total_cases":25,"passed_cases":25,"tokens_delta_pct":39.4,"turns_delta_pct":0,"verdict":"pass","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-12T21:47:53.383824+00:00"},"skill_score":null,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":32,"with_pass_pct":100,"without_pass_pct":68,"tokens_delta_pct":39.4,"turns_delta_pct":0,"total_cases":25,"cases_aggregated":25,"verdict":"pass","never_hurt":true,"completed_at":"2026-08-12T21:47:53.383824+00:00","run_id":"eae55681-00f4-4388-a13f-ba2ec94a9212","version_number":1,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"Apache-2.0","install_count":0,"manifest_hash":"b2f103737300d865d4488810db7e6f7717f3b93b003faffacf225b248a78c027","raw_url":"https://app.decimal.ai/s/nvidia-mcore-run-on-slurm/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/nvidia-mcore-run-on-slurm"}