Iteratively tune esp-ppq QuantizationSetting to recover post-quantization accuracy on ESP-DL targets. Drives a closed loop of "baseline -> calibration × TQT(default) cartesian product -> distribution-aware residual fixes -> agent-driven open exploration -> re-evaluate" in the current Python environment, using a minimal user contract (calib dataloader + evaluate function). Generic across architectures (ResNet / EfficientNet / ViT / DETR / YOLO / LSTM and any esp-ppq-supported graph) — the search procedure is distribution-driven and does not depend on a specific network family. Method ordering is accuracy-first with a soft penalty for passes that slow down on-device inference; once the prescribed Phase-1/2/3 sequence exhausts, the skill hands control to the agent (Phase 5) with a structured history of improving levers + the per-iteration error artifacts to read, so the agent can compose multi-knob iterations (lever stacking, calibration cross-pollination, ablation, cost-trim) without a rigid template. LSQ on PO
End-to-end guide for implementing, testing, and optimizing neural network operators in the ESP-DL framework. Covers C++ module implementation, C reference kernels, SIMD assembly optimization, esp-ppq quantization strategy integration, Docker-based build/test, and inference result alignment between esp-dl and esp-ppq. Use this skill whenever the user wants to add a new operator, implement an operator, optimize an existing operator with SIMD, add quantization support for an operator, or test/validate operator correctness. Also triggers for "算子实现", "添加算子", "SIMD优化", "量化支持", "算子对齐" and similar phrases.