junrushao commented on PR #300:
URL: https://github.com/apache/tvm-ffi/pull/300#issuecomment-3741288307
Looks like there's another issue from this PR:
```
[2026-01-12T20:01:26.601Z]
/tmp/build-env-5u_p2hia/lib/python3.12/site-packages/tvm_ffi/include/tvm/ffi/extra/cuda/device_guard.h(52):
error: a value of type "cudaError_t" (aka "cudaError") cannot be used to
initialize an entity of type "tvm::ffi::cuda_api::ResultType" (aka
"cudaError_enum")
[2026-01-12T20:01:26.601Z] do { ::tvm::ffi::cuda_api::ResultType __err
= (cudaGetDevice(&original_device_index_)); if (__err !=
::tvm::ffi::cuda_api::kSuccess) { const char *__err_name, *__err_str;
::tvm::ffi::cuda_api::GetErrorString(__err, &__err_name, &__err_str);
::tvm::ffi::details::ErrorBuilder("RuntimeError",
TVMFFIBacktrace("/tmp/build-env-5u_p2hia/lib/python3.12/site-packages/tvm_ffi/include/tvm/ffi/extra/cuda/device_guard.h",
52, __PRETTY_FUNCTION__, 0), 0) .stream() << "CUDA Error: " << __err_name << "
(" << static_cast<int>(__err) << "): " << __err_str; } } while (0);
```
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
