ClawHub
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…
The catalogue holds this skill’s description, not a full SKILL.md — no upstream address was recorded at ingestion, so the body cannot be fetched.
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…Fetch this skill’s definition over the open API — no key required.
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__tilegym-improve-cutile-kernel-perf