omgskills Get the Mac app
Skill

aoti-debug

@pytorch 102k stars Updated 2026-07-28 Author match: High

Debug AOTInductor (AOTI) errors and crashes. Use when encountering AOTI segfaults, device mismatch errors, constant loading failures, or runtime errors from aot_compile, aot_load, aoti_compile_and_package, or aoti_load_package.

autograddeep-learninggpumachine-learningneural-networknumpypythontensor

Install

Install this Claude and Codex skill with the command below. The command stays visible even when copy support is unavailable.

Install command
git clone https://github.com/pytorch/pytorch /tmp/pytorch && ln -s /tmp/pytorch/.claude/skills/aoti-debug ~/.claude/skills/aoti-debug

View on GitHub

From README

AOTI Debugging Guide This skill helps diagnose and fix common AOTInductor issues. Error Pattern Routing Check the error message and route to the appropriate sub-guide: Triton Index Out of Bounds If the error matches this pattern: → Follow the guide in triton-index-out-of-bounds.md All Other Errors Continue with the sections below. --- First Step: Always Check Device and Shape Matching For ANY AOTI error (segfault, exception, crash, wrong output), ALWAYS check these first: Compile device == Load device: The model must be loaded on the same device type it was compiled on Input devices match: Runtime inputs must be on the same device as the compiled model Input shapes match: Runtime input shapes must match the shapes used during compilation (or satisfy dynamic shape constraints) If any of these don't match, you will get errors ranging from segfaults to exceptions to wrong outputs. Key Constraint: Device Type Matching AOTI requires compile and load to use the same device type.

More from this repo