model-builder

name

model-builder

description

QAI ModelBuilder. Tools and workflows for model conversion, inspection, operator patching, quantization, and inference validation of self-converted models on Qualcomm platform. Use this skill when working with custom ONNX/PyTorch models — export to ONNX, convert to QNN/SNPE DLC, FP16/FP32/INT8 quantization, operator patching, context binary generation, and inference validation of self-built models. NOT for AI Hub prebuilt packages — use model-hub skill instead.

Model Builder

How to use this SKILL (it is a thin dispatch layer):

1. Pass the Boundary Decision gate below first — it decides whether this skill even applies.
2. Use the Routing Table to load the ONE reference / sub-SKILL that matches your step or problem — do NOT read everything up front.
3. Follow the Core Workflow spine; open references/core_workflow.md for per-step commands.
4. The Blocking Conditions and Disciplines below are the only rules you must hold in mind the whole time.
5. Trust the docs: never run commands to re-verify facts already in this file or ${APP_ROOT}\data\config\qairt_env.json (torch/Python versions, tool paths). Don't read script source unless a reference doc is missing the detail (then update that doc).
6. x64 host + user wants to run inference locally on this machine? Read ${APP_ROOT}/factory/chat_features/_shared/x64-host-notes.md FIRST (before Step 7). If HOST_OS is ARM64, or if inference will go via ADB, skip that file entirely.

---

🚨 Boundary Decision — pass BEFORE activating (MANDATORY GATE)

Answer three questions; if any veto holds, stop and switch skills.

#	Question	YES ->