-
Notifications
You must be signed in to change notification settings - Fork 1.6k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Bug] Binary was created using {relax.Executable} but a loader of that name is not registered. #3055
Comments
Hi @LLIo6oH thanks for bringing this up. Just want to confirm first, are you following the instructions in our documentation https://llm.mlc.ai/docs/deploy/ios.html? And I am curious about at which step you encounter this issue. Thanks. |
Yes, sure, I'm following the instruction
And here I have a crash that I provided above I have the lates: conda, CMake, python, XCode, swift, ios |
I just removed everything to the ground. I Built it over again step-by-step according to instruction and still have the same error |
I see. The error didn't occur the last time we build the app. We will try to see if we can reproduce it. |
We tried on our side but unfortunately we are not able to reproduce this issue. Did you make sure that the MLC codebase is the latest? |
🐛 Bug
I run an iOS application. And have this error log:
libc++abi: terminating due to uncaught exception of type tvm::runtime::InternalError: [19:32:52] /Users/dmitrykuklin/Documents/Projects/Samsung/mlc-llm/3rdparty/tvm/src/runtime/library_module.cc:122: Binary was created using {relax.Executable} but a loader of that name is not registered. Available loaders are . Perhaps you need to recompile with this runtime enabled. Stack trace: [bt] (0) 1 HealthWise.debug.dylib 0x0000000108a38c60 tvm::runtime::detail::LogFatal::Entry::Finalize() + 100 [bt] (1) 2 HealthWise.debug.dylib 0x0000000108a38bfc tvm::runtime::detail::LogFatal::Entry::Finalize() + 0 [bt] (2) 3 HealthWise.debug.dylib 0x0000000108a3879c std::__1::basic_ostream<char, std::__1::char_traits<char>>& std::__1::__put_character_sequence[abi:ne180100]<char, std::__1::char_traits<char>>(std::__1::basic_ostream<char, std::__1::char_traits<char>>&, char const*, unsigned long) + 0 [bt] (3) 4 HealthWise.debug.dylib 0x0000000108c296e4 tvm::runtime::LoadModuleFromBinary(std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&, dmlc::Stream*) + 1308 [bt] (4) 5 HealthWise.debug.dylib 0x0000000108c29e30 tvm::runtime::ProcessModuleBlob(char const*, tvm::runtime::ObjectPtr<tvm::runtime::Library>, std::__1::function<tvm::runtime::PackedFunc (int (*)(TVMValue*, int*, int, TVMValue*, int*, void*), tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)>, tvm::runtime::Module*, tvm::runtime::ModuleNode**) + 864 [bt] (5) 6 HealthWise.debug.dylib 0x0000000108c2abb8 tvm::runtime::CreateModuleFromLibrary(tvm::runtime::ObjectPtr<tvm::runtime::Library>, std::__1::function<tvm::runtime::PackedFunc (int (*)(TVMValue*, int*, int, TVMValue*, int*, void*), tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)>) + 624 [bt] (6) 7 HealthWise.debug.dylib 0x0000000108c584c8 tvm::runtime::SystemLibModuleRegistry::GetOrCreateModule(std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>) + 236 [bt] (7) 8 HealthWise.debug.dylib 0x0000000108c581a0 tvm::runtime::PackedFuncObj::Extractor<tvm::runtime::PackedFuncSubObj<tvm::runtime::$_0>>::Call(tvm::runtime::PackedFuncObj const*, tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) + 228 [bt] (8) 9 HealthWise.debug.dylib 0x0000000108b19440 mlc::llm::serve::FunctionTable::Init(tvm::runtime::String, DLDevice, picojson::object_with_ordered_keys, tvm::runtime::Optional<tvm::runtime::Session>, int, int) + 3096
I know there was the similar issue
But I didn't find a way to solve it
Environment
conda
):pip
):The text was updated successfully, but these errors were encountered: