tqchen commented on PR #18293: URL: https://github.com/apache/tvm/pull/18293#issuecomment-3270274484
Thanks @SigureMo , i am thinkning about more scalable ways to add support without doing specific switch case. One idea is to enable functions like `tensor.__ffi_get_current_stream__` for stream getter in current tensor. We can patch to add generic support by detecting hasattr(tensor, "__ffi_get_current_stream__") -- 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]
