llama.cpp
defe2158 - CUDA: mul_mat_v support for batch sizes > 1 (#14262)

Commit

92 days ago

CUDA: mul_mat_v support for batch sizes > 1 (#14262) * CUDA: mul_mat_v support for batch sizes > 1 * use 64 bit math for initial offset calculation

References

Author

JohannesGaessler

Parents