ayeganov commented on issue #9939:
URL: https://github.com/apache/tvm/issues/9939#issuecomment-1013593029
When I changed the version of tvm to 0.8.0 and tried compiling my own model
I got the following error:
```
[21:39:35]
/Users/ayeganov/code/cisco/tvm_exploration/tvm/src/target/target_kind.cc:164:
Warning: Unable to detect CUDA version, default to "-mcpu=sm_20" instead
[21:39:35]
/Users/ayeganov/code/cisco/tvm_exploration/tvm/src/target/target_kind.cc:190:
Warning: Unable to detect ROCm compute arch, default to "-mcpu=gfx900" instead
[21:39:35]
/Users/ayeganov/code/cisco/tvm_exploration/tvm/src/target/target_kind.cc:204:
Warning: Unable to detect ROCm version, assuming >= 3.5
[21:39:35]
/Users/ayeganov/code/cisco/tvm_exploration/tvm/src/target/target_kind.cc:164:
Warning: Unable to detect CUDA version, default to "-mcpu=sm_20" instead
[21:39:35]
/Users/ayeganov/code/cisco/tvm_exploration/tvm/src/target/target_kind.cc:190:
Warning: Unable to detect ROCm compute arch, default to "-mcpu=gfx900" instead
[21:39:35]
/Users/ayeganov/code/cisco/tvm_exploration/tvm/src/target/target_kind.cc:204:
Warning: Unable to detect ROCm version, assuming >= 3.5
/Users/ayeganov/.pyenv/versions/3.8.6/envs/tvm_for_ladon/lib/python3.8/site-packages/tvm-0.8.0-py3.8-macosx-10.15-x86_64.egg/tvm/relay/frontend/onnx.py:4478:
UserWarning: Input encoder_output_1280x9x16 has unknown dimension shapes:
['batch_size', 1280, 9, 16]. Specifying static values may improve performance
warnings.warn(warning_msg)
[21:39:35]
/Users/ayeganov/code/cisco/tvm_exploration/tvm/src/target/target_kind.cc:164:
Warning: Unable to detect CUDA version, default to "-mcpu=sm_20" instead
[21:39:35]
/Users/ayeganov/code/cisco/tvm_exploration/tvm/src/target/target_kind.cc:190:
Warning: Unable to detect ROCm compute arch, default to "-mcpu=gfx900" instead
[21:39:35]
/Users/ayeganov/code/cisco/tvm_exploration/tvm/src/target/target_kind.cc:204:
Warning: Unable to detect ROCm version, assuming >= 3.5
Traceback (most recent call last):
File
"/Users/ayeganov/.pyenv/versions/3.8.6/Python.framework/Versions/3.8/lib/python3.8/runpy.py",
line 194, in _run_module_as_main
return _run_code(code, main_globals, None,
File
"/Users/ayeganov/.pyenv/versions/3.8.6/Python.framework/Versions/3.8/lib/python3.8/runpy.py",
line 87, in _run_code
exec(code, run_globals)
File
"/Users/ayeganov/.pyenv/versions/3.8.6/envs/tvm_for_ladon/lib/python3.8/site-packages/tvm-0.8.0-py3.8-macosx-10.15-x86_64.egg/tvm/driver/tvmc/__main__.py",
line 24, in <module>
tvmc.main.main()
File
"/Users/ayeganov/.pyenv/versions/3.8.6/envs/tvm_for_ladon/lib/python3.8/site-packages/tvm-0.8.0-py3.8-macosx-10.15-x86_64.egg/tvm/driver/tvmc/main.py",
line 94, in main
sys.exit(_main(sys.argv[1:]))
File
"/Users/ayeganov/.pyenv/versions/3.8.6/envs/tvm_for_ladon/lib/python3.8/site-packages/tvm-0.8.0-py3.8-macosx-10.15-x86_64.egg/tvm/driver/tvmc/main.py",
line 87, in _main
return args.func(args)
File
"/Users/ayeganov/.pyenv/versions/3.8.6/envs/tvm_for_ladon/lib/python3.8/site-packages/tvm-0.8.0-py3.8-macosx-10.15-x86_64.egg/tvm/driver/tvmc/compiler.py",
line 141, in drive_compile
compile_model(
File
"/Users/ayeganov/.pyenv/versions/3.8.6/envs/tvm_for_ladon/lib/python3.8/site-packages/tvm-0.8.0-py3.8-macosx-10.15-x86_64.egg/tvm/driver/tvmc/compiler.py",
line 271, in compile_model
graph_module = relay.build(mod, target=tvm_target, params=params)
File
"/Users/ayeganov/.pyenv/versions/3.8.6/envs/tvm_for_ladon/lib/python3.8/site-packages/tvm-0.8.0-py3.8-macosx-10.15-x86_64.egg/tvm/relay/build_module.py",
line 369, in build
executor_config, runtime_mod, params = bld_mod.build(
File
"/Users/ayeganov/.pyenv/versions/3.8.6/envs/tvm_for_ladon/lib/python3.8/site-packages/tvm-0.8.0-py3.8-macosx-10.15-x86_64.egg/tvm/relay/build_module.py",
line 177, in build
self._build(mod, target, target_host, executor, mod_name)
File
"/Users/ayeganov/.pyenv/versions/3.8.6/envs/tvm_for_ladon/lib/python3.8/site-packages/tvm-0.8.0-py3.8-macosx-10.15-x86_64.egg/tvm/_ffi/_ctypes/packed_func.py",
line 237, in __call__
raise get_last_ffi_error()
tvm._ffi.base.TVMError: Traceback (most recent call last):
[bt] (8) 9 libtvm.dylib 0x000000010aa456d6
tvm::relay::ExprFunctor<void (tvm::RelayExpr const&)>::VisitExpr(tvm::RelayExpr
const&) + 214
[bt] (7) 8 libtvm.dylib 0x000000010aa459df
tvm::NodeFunctor<void (tvm::runtime::ObjectRef const&,
tvm::relay::ExprFunctor<void (tvm::RelayExpr
const&)>*)>::operator()(tvm::runtime::ObjectRef const&,
tvm::relay::ExprFunctor<void (tvm::RelayExpr const&)>*) const + 303
[bt] (6) 7 libtvm.dylib 0x000000010aa5e1d3
tvm::relay::transform::DeviceAwareExprVisitor::VisitExpr_(tvm::relay::FunctionNode
const*) + 291
[bt] (5) 6 libtvm.dylib 0x000000010ac023db
tvm::relay::StorageAllocaBaseVisitor::DeviceAwareVisitExpr_(tvm::relay::FunctionNode
const*) + 171
[bt] (4) 5 libtvm.dylib 0x000000010ac0360c
tvm::relay::StorageAllocaBaseVisitor::CreateToken(tvm::RelayExprNode const*,
bool) + 156
[bt] (3) 4 libtvm.dylib 0x000000010ac0329b
tvm::relay::StorageAllocator::CreateTokenOnDevice(tvm::RelayExprNode const*,
DLDeviceType, bool) + 1755
[bt] (2) 3 libtvm.dylib 0x000000010ac06527
tvm::relay::StorageAllocator::GetMemorySize(tvm::relay::StorageToken*) + 487
[bt] (1) 2 libtvm.dylib 0x0000000109975479
tvm::runtime::detail::LogFatal::Entry::Finalize() + 89
[bt] (0) 1 libtvm.dylib 0x000000010ae2a068
tvm::runtime::Backtrace() + 24
File
"/Users/ayeganov/code/cisco/tvm_exploration/tvm/src/relay/backend/graph_plan_memory.cc",
line 408
TVMError:
---------------------------------------------------------------
An error occurred during the execution of TVM.
For more information, please see: https://tvm.apache.org/docs/errors.html
---------------------------------------------------------------
Check failed: (pval != nullptr) is false: Cannot allocate memory symbolic
tensor shape [?, 1280, 9, 16]
```
--
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]
