zuowanbushiwo opened a new issue, #13018:
URL: https://github.com/apache/tvm/issues/13018

   
   
   ### Environment
   
   host:Ubuntu  TVM:v0.10.0(dev)
   
   ### Steps to reproduce
   
   ```
   run_example.sh
   Build the libraries..
   python3 prepare_test_libs.py
   /home/yangjie/tvm/python/tvm/target/target.py:809: UserWarning: 
tvm.target.create() is being deprecated. Please use tvm.target.Target() instead
     warnings.warn("tvm.target.create() is being deprecated. Please use 
tvm.target.Target() instead")
   g++ -c -std=c++17 -O2 -fPIC -I/home/yangjie/tvm/include 
-I/home/yangjie/tvm/3rdparty/dmlc-core/include 
-I/home/yangjie/tvm/3rdparty/dlpack/include 
-DDMLC_USE_LOGGING_LIBRARY=\<tvm/runtime/logging.h\> -o 
lib/libtvm_runtime_pack.o  tvm_runtime_pack.cc
   g++ -std=c++17 -O2 -fPIC -I/home/yangjie/tvm/include 
-I/home/yangjie/tvm/3rdparty/dmlc-core/include 
-I/home/yangjie/tvm/3rdparty/dlpack/include 
-DDMLC_USE_LOGGING_LIBRARY=\<tvm/runtime/logging.h\> -o lib/cpp_deploy_pack  
cpp_deploy.cc lib/test_addone_sys.o lib/libtvm_runtime_pack.o 
-L/home/yangjie/tvm/build -ldl -pthread
   g++ -std=c++17 -O2 -fPIC -I/home/yangjie/tvm/include 
-I/home/yangjie/tvm/3rdparty/dmlc-core/include 
-I/home/yangjie/tvm/3rdparty/dlpack/include 
-DDMLC_USE_LOGGING_LIBRARY=\<tvm/runtime/logging.h\> -o lib/cpp_deploy_normal  
cpp_deploy.cc lib/test_addone_sys.o -ltvm_runtime -L/home/yangjie/tvm/build 
-ldl -pthread
   Run the example
   Run the deployment with all in one packed library...
   [12:29:28] cpp_deploy.cc:77: Verify dynamic loading from test_addone_dll.so
   [12:29:28] cpp_deploy.cc:69: Finish verification...
   [12:29:28] cpp_deploy.cc:81: Verify load function from system lib
   terminate called after throwing an instance of 'tvm::runtime::InternalError'
     what():  [12:29:28] cpp_deploy.cc:34:
   ---------------------------------------------------------------
   An error occurred during the execution of TVM.
   For more information, please see: https://tvm.apache.org/docs/errors.html
   ---------------------------------------------------------------
     Check failed: (f != nullptr) is false:
   Stack trace:
     [bt] (0) lib/cpp_deploy_pack(+0x13407) [0x55c0176b7407]
     [bt] (1) lib/cpp_deploy_pack(+0x1044e) [0x55c0176b444e]
     [bt] (2) lib/cpp_deploy_pack(+0xbd5a) [0x55c0176afd5a]
     [bt] (3) lib/cpp_deploy_pack(+0xda10) [0x55c0176b1a10]
     [bt] (4) lib/cpp_deploy_pack(+0x6649) [0x55c0176aa649]
     [bt] (5) /lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xe7) 
[0x7fb1bd74cc87]
     [bt] (6) lib/cpp_deploy_pack(+0xb3da) [0x55c0176af3da]
   
   
   ./run_example.sh: 行 26: 37729 已放弃               (核心已转储) lib/cpp_deploy_pack
   Run the cpp deployment with all in normal library...
   [12:29:28] cpp_deploy.cc:77: Verify dynamic loading from test_addone_dll.so
   [12:29:28] cpp_deploy.cc:69: Finish verification...
   [12:29:28] cpp_deploy.cc:81: Verify load function from system lib
   terminate called after throwing an instance of 'tvm::runtime::InternalError'
     what():  [12:29:28] cpp_deploy.cc:34:
   ---------------------------------------------------------------
   An error occurred during the execution of TVM.
   For more information, please see: https://tvm.apache.org/docs/errors.html
   ---------------------------------------------------------------
     Check failed: (f != nullptr) is false:
   Stack trace:
     0: Verify(tvm::runtime::Module, std::__cxx11::basic_string<char, 
std::char_traits<char>, std::allocator<char> >)
     1: DeploySingleOp()
     2: main
     3: __libc_start_main
     4: _start
     5: 0xffffffffffffffff
   
   
   ./run_example.sh: 行 29: 37731 已放弃               (核心已转储) lib/cpp_deploy_normal
   Run the python deployment with all in normal library...
   Verify dynamic loading from test_addone_dll.so
   Finish verification...
   
   ```
   
   


-- 
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]

Reply via email to