tqchen opened a new pull request, #19770: URL: https://github.com/apache/tvm/pull/19770
## Summary The CUDA runtime can rely on the shared tvm-ffi CUDA error helper instead of carrying a TVM-local common header. This keeps CUDA error handling aligned with the FFI CUDA support and removes the remaining reason for src/backend/cuda/runtime/cuda_common.h. Main changes: - Move CUDA workspace thread-local state into cuda_device_api.cc. - Replace CUDA_CALL use sites with TVM_FFI_CHECK_CUDA_ERROR from tvm/ffi/extra/cuda/base.h. - Inline the remaining CUDA driver checks at their call sites and delete cuda_common.h. -- 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]
