Aitune Benchmark

Use when measuring inference performance of a PyTorch model before and after AITune optimization — capturing baseline, compilation time, tuned throughput, and speedup.

ai-dynamo Updated
AITune workflow: inspect, wrap, evaluate backend candidates, validate outputs, measure performance, select the best backend for the configured strategy, and run

File contents

ai-dynamo/aitune commit 4f99ebda41

Frequently asked questions

npx get-skill add ai-dynamo/aitune-benchmark