Skip to content

[Bugfix] fix hipMemcpyKind enum #35

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
takeshi-yoshimura merged 1 commit into from
Nov 11, 2025
Merged

[Bugfix] fix hipMemcpyKind enum #35

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions fastsafetensors/cpp/ext.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,7 +39,12 @@ typedef struct CUfileError { CUfileOpError err; } CUfileError_t;
// Define minimal CUDA/HIP types for both platforms to avoid compile-time dependencies
// We load all GPU functions dynamically at runtime via dlopen()
typedef enum cudaError { cudaSuccess = 0, cudaErrorMemoryAllocation = 2 } cudaError_t;
// Platform-specific enum values - CUDA and HIP have different values for HostToDevice
#ifdef USE_ROCM
enum cudaMemcpyKind { cudaMemcpyHostToDevice=1, cudaMemcpyDefault = 4 };
#else
enum cudaMemcpyKind { cudaMemcpyHostToDevice=2, cudaMemcpyDefault = 4 };
#endif


typedef enum CUfileFeatureFlags {
Expand Down