Skip to content
Back to pull request #4079

Use BLAS to implement ggml_compute_forward_out_prod_f32 for matrix src0, src1 (finetuning speedup ~5x). #4102

Sign in to view logs

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

Use BLAS to implement ggml_compute_forward_out_prod_f32 for matrix src0, src1 (finetuning speedup ~5x). #4102

The logs for this run have expired and are no longer available.