llama.cpp
d4156690 - cuda : add ROCm / hipBLAS cublasGemmBatchedEx define

Commit

1 year ago

cuda : add ROCm / hipBLAS cublasGemmBatchedEx define

References

#3749 - cuda : add batched cuBLAS GEMM for faster attention

Author

ggerganov

ggerganov

Parents

Loading