llama.cpp
89e89599 - CUDA: fix mul_mat_q not used for output tensor (#3127)

Commit

2 years ago

CUDA: fix mul_mat_q not used for output tensor (#3127)

References

#3127 - CUDA: fix mul_mat_q not used for output tensor

Author

JohannesGaessler

JohannesGaessler

Parents

Loading