Some initial implementations for DSL frontend

microsoft / nnfusion

A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.

MIT License

955 stars 159 forks source link

Some initial implementations for DSL frontend #524

Closed donglinb closed 1 year ago

donglinb commented 1 year ago

Create json graph from Antares IR expressions, which could be feed to Welder for tuning. Then use both two json graphs before and after tuning to generate device code. Finally, feed device code to Antares CustomOp for run.