Use BLAS to implement ggml_compute_forward_out_prod_f32 for matrix src0, src1 (finetuning speedup ~5x).#4079

Merged

ggerganov merged 4 commits intoggerganov:masterfrom gwjr:out-prod-using-blas

Nov 17, 2023

+61-8

Commits on Nov 14, 2023

Commits on Nov 15, 2023

Remove ggml_compute_forward_out_prod_use_blas(), fix compiling errors on cmake/zig, remove trailing whitespace
gwjr
committed

Commits on Nov 16, 2023

Add openBLAS support for sgemm() in compute_forward_out_prod()
gwjr
committed