llama.cpp
aa8b6210 - Support device-specific host buffer types if all underlying backends expose the same type. This allows using pinned memory instead of pageable memory for CUDA.

Commit

88 days ago

Support device-specific host buffer types if all underlying backends expose the same type. This allows using pinned memory instead of pageable memory for CUDA. Fix compilation errors.

Author

gaugarg-nv

Parents

fd24533e

llama.cpp aa8b6210 - Support device-specific host buffer types if all underlying backends expose the same type. This allows using pinned memory instead of pageable memory for CUDA.

llama.cpp
aa8b6210 - Support device-specific host buffer types if all underlying backends expose the same type. This allows using pinned memory instead of pageable memory for CUDA.