vai-flag-configuration
Iteratively improve the VAIML compilation configuration for an ONNX model. Analyzes the model and the flag catalog, proposes a non-default vitisai_config.json, compiles it, validates NPU offload (and board inference time when available), and loops until the user's stop condition is met. Use when the user wants to tune compiler flags, improve NPU offloading, or reduce inference time for a model.
- Version
- 6.3.0
- License
- Apache-2.0 WITH LLVM-exception
- Compatibility
- Requires VitisAI 6.3+
Pinned to revision 2cdc9eef1b6b, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/vai-flag-configuration/SKILL.md
- skills/vai-flag-configuration/README.md
- skills/vai-flag-configuration/scripts/ai_analyzer_timing.py
- skills/vai-flag-configuration/scripts/compile_probe.py
- skills/vai-flag-configuration/scripts/flag_catalog.py
- skills/vai-flag-configuration/scripts/ledger.py
- skills/vai-flag-configuration/scripts/model_ops.py
- skills/vai-flag-configuration/scripts/normalize_timer_json.py
- skills/vai-flag-configuration/scripts/offload_gap.py
- skills/vai-flag-configuration/scripts/run_on_board.py
- skills/vai-flag-configuration/scripts/spill_check.py
- skills/vai-flag-configuration/scripts/ssh_utils.py
- skills/vai-flag-configuration/skill_requirements.txt
Every link opens the file at its source, pinned to the revision this page describes.