junrushao commented on issue #338: URL: https://github.com/apache/tvm-ffi/issues/338#issuecomment-3649934339
I'd love to learn more details about the usecases before deciding what the best approach is. > For computation-related data types such as cv::Mat (or CV-CUDA), we can implement a sequence of computation and type-conversion backends (e.g., DecodeMat, ResizeMat, Mat2TVMTensor), which inherently introduces backend boundaries Would you like to elaborate what TVM-FFI is used for in this case? For example, as an ABI convention so that it makes linking easier, or exchange tensors with other frameworks (e.g. PyTorch, cuteDSL), or anything else? Will the types you like (cv::Mat, Event, Status) be opaque to TVM-FFI? If you are primarily interested in opaqueness, TVM-FFI has a mechanism to handle all Python opaque types, where all unknown Python objects are translated to: https://github.com/apache/tvm-ffi/blob/main/src/ffi/object.cc#L464-L478 -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
