coffezhou opened a new issue, #18004:
URL: https://github.com/apache/tvm/issues/18004
### Expected behavior
TVM should run the model correctly.
### Actual behavior
When compiling and running the model, TVM crashes:
```c
!!!!!!! TVM FFI encountered a Segfault !!!!!!!
File "<unknown>", in
__pyx_pw_3tvm_3ffi_4core_8Function_1__call__(_object*, _object* const*, long,
_object*)
File "<unknown>", in tvm::ffi::FunctionObj::SafeCall(void*, TVMFFIAny
const*, int, TVMFFIAny*)
File "<unknown>", in
tvm::runtime::relax_vm::VirtualMachineImpl::GetFunction(tvm::ffi::String
const&, tvm::ffi::ObjectPtr<tvm::ffi::Object>
const&)::{lambda(tvm::ffi::PackedArgs,
tvm::ffi::Any*)#4}::operator()(tvm::ffi::PackedArgs, tvm::ffi::Any*) const
File "<unknown>", in
tvm::runtime::relax_vm::VirtualMachineImpl::_InvokeClosureStateful(std::__cxx11::basic_string<char,
std::char_traits<char>, std::allocator<char> >)
File "<unknown>", in
tvm::runtime::relax_vm::VirtualMachineImpl::InvokeClosureInternal(tvm::ffi::ObjectRef
const&, std::vector<tvm::ffi::Any, std::allocator<tvm::ffi::Any> > const&)
File "<unknown>", in
tvm::runtime::relax_vm::VirtualMachineImpl::GetClosureInternal(tvm::ffi::String
const&, bool)::{lambda(tvm::ffi::PackedArgs,
tvm::ffi::Any*)#1}::operator()(tvm::ffi::PackedArgs, tvm::ffi::Any*) const
[clone .isra.0]
File "<unknown>", in
tvm::runtime::relax_vm::VirtualMachineImpl::InvokeBytecode(long,
std::vector<tvm::ffi::Any, std::allocator<tvm::ffi::Any> > const&)
File "<unknown>", in tvm::runtime::relax_vm::VirtualMachineImpl::RunLoop()
File "<unknown>", in
tvm::runtime::relax_vm::VirtualMachineImpl::RunInstrCall(tvm::runtime::relax_vm::VMFrame*,
tvm::runtime::relax_vm::Instruction)
File "<unknown>", in
tvm::runtime::relax_vm::VirtualMachineImpl::InvokeClosurePacked(tvm::ffi::ObjectRef
const&, tvm::ffi::PackedArgs, tvm::ffi::Any*)
File "<unknown>", in
tvm::ffi::details::FunctionObjImpl<tvm::ffi::Function::FromPacked<tvm::runtime::WrapFFIFunction(int
(*)(void*, TVMFFIAny const*, int, TVMFFIAny*),
tvm::ffi::ObjectPtr<tvm::ffi::Object> const&)::{lambda(tvm::ffi::PackedArgs,
tvm::ffi::Any*)#1}>(tvm::runtime::WrapFFIFunction(int (*)(void*, TVMFFIAny
const*, int, TVMFFIAny*), tvm::ffi::ObjectPtr<tvm::ffi::Object>
const&)::{lambda(tvm::ffi::PackedArgs,
tvm::ffi::Any*)#1})::{lambda(tvm::ffi::AnyView const*, int,
tvm::ffi::Any*)#1}>::Call(tvm::ffi::FunctionObj const*, tvm::ffi::AnyView
const*, int, tvm::ffi::Any*)
File "../sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S", line 262,
in 0x00007f887fd46963
File
"/build/glibc-FcRMwW/glibc-2.31/signal/../sysdeps/unix/sysv/linux/x86_64/sigaction.c",
in 0x00007f887fbfe08f
File "<unknown>", in tvm::ffi::(anonymous
namespace)::backtrace_handler(int)
File "<unknown>", in tvm::ffi::(anonymous namespace)::Traceback()
Segmentation fault (core dumped)
```
### Environment
OS: Ubuntu 20.04
TVM: 0.21.dev0 (3db71bb3a)
onnxruntime: 1.21.0
### Steps to reproduce
This bug can be reproduced by the following code with the model in the
attachment. As shown in the code, the model can be executed by onnxruntime.
However, TVM crashes when calling the invoke_stateful function.
```python
import sys
import numpy as np
import onnx
import onnxruntime
import tvm
from tvm import relax
from tvm.relax.frontend.onnx import from_onnx
import pickle
def main():
onnx_model = onnx.load("a1783.onnx")
shape_onnx_model = onnx.shape_inference.infer_shapes(onnx_model)
onnx.save(shape_onnx_model, '1111.onnx')
with open("inputs.pkl", "rb") as fp:
inputs = pickle.load(fp)
try:
ort_session = onnxruntime.InferenceSession(
onnx_model.SerializeToString(),
providers=["CPUExecutionProvider"]
)
ort_output = ort_session.run([], inputs)
except Exception as e:
print(e)
sys.exit(1)
print("ONNXRuntime:\n", ort_output)
# Convert the onnx model into relax through the onnx importer.
tvm_model = from_onnx(onnx_model, keep_params_in_input=True)
# Convert operators for inference mode.
tvm_model = relax.transform.DecomposeOpsForInference()(tvm_model)
# Legalize any relax ops into tensorir.
tvm_model = relax.transform.LegalizeOps()(tvm_model)
# Separate model from parameters.
tvm_model, params = relax.frontend.detach_params(tvm_model)
# Prepare inputs.
input_list = [
inputs[key.name_hint] for key in tvm_model["main"].params if
key.name_hint in inputs
]
if params:
input_list += params["main"]
# Compile the relax graph into a VM then run.
with tvm.transform.PassContext(opt_level=3):
ex = relax.build(tvm_model, target="llvm")
vm = relax.VirtualMachine(ex, tvm.cpu())
# Run model and check outputs.
vm.set_input("main", *input_list)
vm.invoke_stateful("main")
if __name__ == "__main__":
main()
```
[testcast.zip](https://github.com/user-attachments/files/20359271/testcast.zip)
### Triage
* needs-triage
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
