llama.cpp
3ef358ff - Revert "cuda : use CUDA memory pool with async memory allocation/deallocation when available (#3903)"

Commit
2 years ago
Revert "cuda : use CUDA memory pool with async memory allocation/deallocation when available (#3903)" This reverts commit d6069051de7165a4e06662c89257f5d2905bb156. ggml-ci
Author
Committer
Parents
Loading