Hi @thkim
If you update your from the above [githhub link](https://github.com/i24361/incubator-tvm/blob/0472b1f347976229a29be8a6e60b626a0604c8df/vta/tutorials/autotvm/tune_relay_vta_with_one_board.py) and my change on the `export_library`, then let me check few more. It is not a connection issue, as you see `GFLOPS (always 0.00/ 0.00 GFLOPS)` message. Does it every finish? How many iteration you've set? Are other testing such as [this](https://tvm.apache.org/docs/vta/tutorials/matrix_multiply.html#sphx-glr-vta-tutorials-matrix-multiply-py) that are not using `autotvm` works? Cheers, ISS --- [Visit Topic](https://discuss.tvm.apache.org/t/vta-workaround-for-autotuning-with-one-pynq-z1-board/8091/11) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.apache.org/email/unsubscribe/540d1b583d8bc7152ba1d7c7eb0200fe60dce8f3f77327dc99a7ca1bc787067a).
