espdl-operator
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.
Installation and usage
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.
Depois de instalar, você pode usar esta skill executando o seguinte comando no terminal:
skills use espdl-operator