界面已本地化;技能介绍与说明文档按所选语言由 AI 自动翻译,代码、命令、路径和专业术语保留原文,以原作者文档为准。
探索技能
数据与研究 · SKILL.md

tilegym-improve-cutile-kernel-perf

tilegym-improve-cutile-kernel-perf

【数据与研究】Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning. Covers tile sizes, occupancy, autotune configs, TMA, latency hints, persistent scheduling, num_ctas, flush_to_zero, and IR-level debugging. Use when asked to "optimize cutile kernel", "improve kernel perf", "tune cutil…

独立 GitHub 快照 · 自动分类 · 以原作者文档为准

NNVIDIA / skillsNOASSERTION

技能说明

GitHub
正在从源仓库读取说明…
我的收藏