Fix nasty bug in ggml_compute_forward_mul_mat_f32() and reenable BLAS

1 files changed, 2 insertions, 3 deletions

diff --git a/llama.cpp b/llama.cpp
index 14de611a..bb7bdead 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -917,8 +917,7 @@ static bool llama_eval_internal(
             struct ggml_tensor * KQ_scaled =
                 ggml_scale(ctx0,
                         KQ,
-                        ggml_new_f32(ctx0, 1.0f/sqrt(float(n_embd)/n_head))
-                        );
+                        ggml_new_f32(ctx0, 1.0f/sqrt(float(n_embd)/n_head)));
 
             // KQ_masked = mask_past(KQ_scaled)
             struct ggml_tensor * KQ_masked = ggml_diag_mask_inf(ctx0, KQ_scaled, n_past);
@@ -934,7 +933,7 @@ static bool llama_eval_internal(
                                 ggml_view_1d(ctx0, kv_self.v, (n_past + N)*n_embd, il*n_ctx*ggml_element_size(kv_self.v)*n_embd),
                                 n_embd/n_head, n_head, n_past + N),
                             1, 2, 0, 3),
-                    ggml_new_tensor_3d(ctx0, GGML_TYPE_F32, n_past + N, n_embd/n_head, n_head));
+                    ggml_new_tensor_3d(ctx0, kv_self.v->type, n_past + N, n_embd/n_head, n_head));
 
             // KQV = transpose(V) * KQ_soft_max
             struct ggml_tensor * KQV = ggml_mul_mat(ctx0, V_trans, KQ_soft_max);