quark-onnx-result-validator
SkillFiles & storageValidate Quark ONNX quantization output using four lightweight checks: auxiliary file copy alignment, expected non-quantized initializer MD5 byte-identity (inline `raw_data` + external-data byte ranges), model metadata equality after stripping quantization-only opset entries / Quark domains, and fuzzy node-pattern + op-type + dtype summaries with QDQ / `com.amd.quark` custom-op presence. Intended for post-quantization inspection of `model.onnx` (with or without `model.onnx_data`). Trigger for "validate ONNX quantization result", "check quantized .onnx output", "verify ONNX initializers", "did QDQ insertion happen", "are the non-quantized weights byte-identical".
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the quark-onnx-result-validator skill
What this skill tells your AI
The instructions your AI receives, as published by amd/quark in .claude/skills/quark-onnx-result-validator/SKILL.md and read by ahel’s review.
Read and follow the instructions in .claude/skills-impl/l1-atomic/onnx/quark-onnx-result-validator/SKILL.md.
Signals
- GitHub stars
- 166
- Forks
- 33
- Last commit
- Aug 2026
Advanced
- Catalog kind
- skill
- Gateway key
quark-onnx-result-validator- Source
- github.com/amd/quark