AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
The AI Model Efficiency Toolkit
The AI model efficiency toolkit is kind of at the center of this right. We have tools that plug into PyTorch and plug into TensorFlow, add a little bit of extra to your training pipeline and then condition the model during training to be quantization aware. So you would run it through post training quantization. This produces a representation of the model in this Qualcomm AI engine direct format. Think about it like an intermediate representation. Once we have it in that common representation, you can then write wherever you want.