[TVM Discuss] [Development] Zero copy DLManagedTensor for "set_input"

2019-04-05 Thread Bram via TVM Discuss
Those are the expected dimensions, a flat vector of that size 2**25. How can I print out the value stored at int32(arg0.shape[0])? As a debug point the deleters are not being called before the exception is raised, so the corruption might be happening from a misuse of NDArray::FromDLPack

[TVM Discuss] [Development] Zero copy DLManagedTensor for "set_input"

2019-04-04 Thread Bram via TVM Discuss
Any thoughts on the best way to do this? I gave it a shot here: https://gist.github.com/bwasti/a9d3b82d06f0de7df34a04e0c1ae4764 but didn't make much headway -- I hit a hard to decipher error in the Bind logic: ``` RuntimeError: [23:10:17] /home/bwasti/local/pytorch_tvm/tvm/src/runtime/module