masahi commented on PR #13532:
URL: https://github.com/apache/tvm/pull/13532#issuecomment-1352409775
Also getting the error
```
2:
tvm::runtime::CUDAModuleNode::GetFunction(std::__cxx11::basic_string<char,
std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::Ob
jectPtr<tvm::runtime::Object> const&)
1: tvm::runtime::PackedFunc
tvm::runtime::PackFuncVoidAddr<tvm::runtime::CUDAWrappedFunc>(tvm::runtime::CUDAWrappedFunc,
std::vector<DLDataType, std:
:allocator<DLDataType> > const&)
0: tvm::runtime::detail::GetArgConvertCode(DLDataType)
File "/home/masa/projects/dev/tvm/src/runtime/cuda/../pack_args.h", line
146
File "/home/masa/projects/dev/tvm/src/runtime/library_module.cc", line 80
TVMError:
---------------------------------------------------------------
An error occurred during the execution of TVM.
For more information, please see: https://tvm.apache.org/docs/errors.html
---------------------------------------------------------------
Check failed: ret == 0 (-1 vs. 0) : TVMError: Cannot handle float16 as
device function argument
```
when tuning winograd fp16 tasks from stable diffusion UNet. Normal
convolution works.
--
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]
