llama.cpp
a818f302 - CUDA: use MMQ instead of cuBLAS by default (#8075)

Commit

2 years ago

CUDA: use MMQ instead of cuBLAS by default (#8075)

References

#8075 - CUDA: use MMQ instead of cuBLAS by default

Author

JohannesGaessler

JohannesGaessler

Parents

Loading