@aakah18151 we don't quite have good enough debugging for this right now for me to be certain, but based on your stack trace and that it's inside
>` [bt] (6) >/tvm_micro_with_debugger/tvm/build/libtvm.so(tvm::runtime::RPCClientSession::AllocDataSpace(DLContext, > unsigned long, unsigned long, DLDataType)+0x2b7) [0x7f7abd9b11b7]` I would suppose that your runtime doesn't define enough memory for that model (or fragmentation issues with the JSON parsing are making the model require much more memory than it should). we are working to address these with AOT runtime and memory planner improvements. in the meantime, see if you can increase the amount of global memory made available in `main.c` or switch to the Zephyr heap allocator as demonstrated [here](https://github.com/areusch/microtvm-blogpost-eval/blob/master/runtimes/zephyr/src/main.c#L196). --- [Visit Topic](https://discuss.tvm.apache.org/t/measuring-utvm-inference-time/9064/6) 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/3f0e9b9d1c80f922e904a27489899a3c49f323f72f421a0aa42121b09f67d6da).
