NVIDIA/nvidia-resiliency-ext

fault-injection-loop

Closed-loop fault injection and attribution accuracy benchmark. Draws from a prioritized pool of (fault_type, rank, iter, nodes) experiments and submits them 2 at a time via sbatch — waiting for each pair to finish before submitting the next — to bound…

لغة النص الأصلي: الإنجليزية

log-analysis

Analyze a SLURM job log file for failure root-cause attribution and restart decisions using NVRxLogAnalyzer. Use when you have a SLURM training job log and need to determine why the job failed and whether it should be restarted. Performs per-cycle chunking,…

لغة النص الأصلي: الإنجليزية

nvrx-attr

Orchestration layer over nvidia_resiliency_ext attribution modules. Provides log-analysis, fr-analysis, and a Megatron-LM-oriented fault-injection feedback loop for benchmarking attribution quality on SLURM workloads.

لغة النص الأصلي: الإنجليزية

fr-analysis

Analyze PyTorch NCCL flight-recorder (FR) dumps to identify collective operation hangs and isolate the responsible ranks using CollectiveAnalyzer. Use when a distributed training job hangs due to an NCCL collective timeout and FR dump files are available.…

لغة النص الأصلي: الإنجليزية