ggml : re-enable BLAS for CPU when src0 != F32 + remove redundant full offload checks in llama.cpp (#4240)

* ggml : use blas even if src0 is not F32

* llama : use n_threads_batch only when n_tokens >= 32

ggml-ci

* llama : revert n_threads_batch logic

ggml-ci

1 files changed, 1 insertions, 1 deletions

diff --git a/ggml.c b/ggml.c
index 0c7264a3..c522a101 100644
--- a/ggml.c
+++ b/ggml.c
@@ -9373,7 +9373,7 @@ static bool ggml_compute_forward_mul_mat_use_blas(
     // TODO: find the optimal values for these
     if (ggml_is_contiguous(src0) &&
         ggml_is_contiguous(src1) &&
-        src0->type == GGML_TYPE_F32 &&
+      //src0->type == GGML_TYPE_F32 &&
         src1->type == GGML_TYPE_F32 &&
         (ne0 >= 32 && ne1 >= 32 && ne10 >= 32)) {