Skip to content

feat(cuda): add CUDA backend initialization and device info test#478

Merged
chenghuaWang merged 2 commits intoUbiquitousLearning:v2from
chenghuaWang:v2
Oct 14, 2025
Merged

feat(cuda): add CUDA backend initialization and device info test#478
chenghuaWang merged 2 commits intoUbiquitousLearning:v2from
chenghuaWang:v2

Conversation

@chenghuaWang
Copy link
Copy Markdown
Collaborator

  • Add compile definition MLLM_CUDA_BACKEND when building CUDA backend
  • Implement initCudaBackend function to register CUDA backend and allocator
  • Update namespace usage in CudaBackend.cpp to support global init function
  • Add memory cleanup before backend shutdown in mllm.cpp
  • Declare initCudaBackend in mllm.hpp for external linkage
  • Add new test for CUDA device info with proper linking and includes

chenghuaWang and others added 2 commits October 14, 2025 14:09
- Add compile definition MLLM_CUDA_BACKEND when building CUDA backend
- Implement initCudaBackend function to register CUDA backend and allocator
- Update namespace usage in CudaBackend.cpp to support global init function
- Add memory cleanup before backend shutdown in mllm.cpp
- Declare initCudaBackend in mllm.hpp for external linkage
- Add new test for CUDA device info with proper linking and includes
@chenghuaWang chenghuaWang merged commit e19bf81 into UbiquitousLearning:v2 Oct 14, 2025
2 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant