llama.cpp
b9b7d94f - CUDA: Fixed 7b q3_K_S with mul_mat_vec_q (#2313)

Commit

2 years ago

CUDA: Fixed 7b q3_K_S with mul_mat_vec_q (#2313)

References

#2313 - CUDA: Fixed 7b q3_K_S with mul_mat_vec_q

Author

JohannesGaessler

JohannesGaessler

Parents

Loading