I have compiled tvm based on ROCm backend
>>> python -c "import tvm; print(tvm.rocm().exist)" True However, when I build llama model using mlc-llm, I encounter the following problem： Traceback (most recent call last): File "/home/xxx/anaconda3/envs/mlc/lib/python3.8/runpy.py", line 194, in _run_module_as_main return _run_code(code, main_globals, None, File "/home/xxx/anaconda3/envs/mlc/lib/python3.8/runpy.py", line 87, in _run_code exec(code, run_globals) File "/home/relay/xxx/workspace/mlc-llm/mlc_llm/build.py", line 13, in main() File "/home/xxx/workspace/mlc-llm/mlc_llm/build.py", line 10, in main core.build_model_from_args(parsed_args) File "/home/xxx/workspace/mlc-llm/mlc_llm/core.py", line 425, in build_model_from_args new_params = utils.convert_weights(param_manager, params, args) File "/home/xxx/workspace/mlc-llm/mlc_llm/utils.py", line 181, in convert_weights vm = relax.vm.VirtualMachine(ex, device) File "/home/xxx/tvm-unity/python/tvm/runtime/relax_vm.py", line 81, in **init** rt_mod = rt_mod.jit() File "/home/xxx/tvm-unity/python/tvm/relax/vm_build.py", line 89, in jit not_runnable_list = self.mod._collect_from_import_tree(_not_runnable) File "/home/xxx/tvm-unity/python/tvm/runtime/module.py", line 431, in _collect_from_import_tree assert ( AssertionError: Module hip should be either dso exportable or binary serializable. can someone help me? best wishes. --- [Visit Topic](https://discuss.tvm.apache.org/t/error-with-relax-while-build-llama-with-mlc-llm-build-py-module-hip-should-be-either-dso-exportable-or-binary-serializable/15443/1) 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/5ae7de81acb80c3bf0bf6ef30fb7f2a69704279fbdbba9624bfe92b189e5cb06).
