[TVM Discuss] [Questions] Schedule not registered for 'mytarget'

This is where the problem lies. You need to give the target context by relay.build with the target argument. But there is no requirement to do this in TVM for flexibility. In some tutorials, compute graph is not build by using op strategy but directly using the wrap function(cfunc&sfunc). For

[TVM Discuss] [Questions] Schedule not registered for 'mytarget'

It seems right. Maybe your target is error. Use this to see your current target. ``` print(tvm.target.Target.current(allow_none=False) ``` --- [Visit Topic](https://discuss.tvm.ai/t/schedule-not-registered-for-mytarget/6675/2) to respond. You are receiving this because you enabled mailing

[TVM Discuss] [Questions] Meet an error when deploy nms on target

I think I solved this problem on vta target. It is a simple pass bug causing extern function ‘sort’ error. https://discuss.tvm.ai/t/vta-a-workaround-for-deploying-faster-r-cnn-on-target-ext-dev-vta-and-arm-cpu/6516 --- [Visit Topic](https://discuss.tvm.ai/t/meet-an-error-when-deploy-nms-on

[TVM Discuss] [Questions] Execution order of operators at Runtime in TVM

It seems that annotate_target tutorial has not been uploaded. I am wondering how one runtime communicates with another runtime. Something like a host runtime and a kernel runtime？Host runtime uses jit to generate kernel's code? Or they use other synchronization mechanisms? ![微信截图_2020050619291

[TVM Discuss] [Questions] Execution order of operators at Runtime in TVM

I guess external_mods is the mods needed external codegen tools. The official document shows the codegen sequence. https://docs.tvm.ai/dev/codebase_walkthrough.html ``` /*! * \brief Lower the external function using external codegen tools. * \return The runtime moduels for each needed ex