debug-distributed-hang

【开发与工程】Debug hanging issues in SGLang distributed inference (TP/PP/DP/EP). Covers identifying hang locations via py-spy/watchdog/cuda coredump, per-rank logging to find state divergence, binary-search methodology for locating the first diverge point, and fix patterns. Use when a multi-GPU SGLang run hangs, freezes, or times out during collective operations.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准