ai-dynamo/aitune

aitune-tune

Use when a user asks to tune, optimize, accelerate, or deploy a PyTorch model or inference pipeline for GPU performance.

Idioma do texto original: inglês

aitune-benchmark

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

Idioma do texto original: inglês

aitune-commit

Use when creating a git commit to ensure the message follows the Conventional Commits specification

Idioma do texto original: inglês

aitune-docs-update

Run full documentation sync (not limited to recent git changes)

Idioma do texto original: inglês

aitune-inspect

Use when inspecting a PyTorch model or pipeline to identify tunable submodules, detect dynamic shapes, and determine the recommended tuning mode before optimization.

Idioma do texto original: inglês

aitune-release

Use when creating a new release tag for the project

Idioma do texto original: inglês

aitune-validate

Use when verifying that a tuned model's outputs match the baseline eager model within numerical tolerance — run after each backend compilation before accepting it as a deployment candidate.

Idioma do texto original: inglês