We have the debug graph executor, which has the method `debug_get_output` (https://tvm.apache.org/docs/api/python/graph_executor.html#tvm.contrib.graph_executor.GraphModule.debug_get_output). This will dump all tensors from all the ops. Note that it is currently broken, but https://github.com/apache/tvm/pull/7903 should fix it.
--- [Visit Topic](https://discuss.tvm.apache.org/t/relay-dump-all-ops-outputs-vm-or-graph-runtime/9828/2) 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/5ba68fd75dae5393b2864d64a060a9b87361bc012912ab22b2f8fdb9b31e0f8c).
