1 files changed, 9 insertions, 7 deletions

diff --git a/llama.cpp b/llama.cpp
index e564de7..08c7352 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -1128,8 +1128,8 @@ static bool llama_eval_internal(
         // self-attention
         {
             // compute Q and K and RoPE them
-            struct ggml_tensor * Qcur = ggml_rope(ctx0, ggml_reshape_3d(ctx0, ggml_mul_mat(ctx0, model.layers[il].wq, cur), n_embd/n_head, n_head, N), n_past, n_rot, 0);
-            struct ggml_tensor * Kcur = ggml_rope(ctx0, ggml_reshape_3d(ctx0, ggml_mul_mat(ctx0, model.layers[il].wk, cur), n_embd/n_head, n_head, N), n_past, n_rot, 0);
+            struct ggml_tensor * Qcur = ggml_rope_inplace(ctx0, ggml_reshape_3d(ctx0, ggml_mul_mat(ctx0, model.layers[il].wq, cur), n_embd/n_head, n_head, N), n_past, n_rot, 0);
+            struct ggml_tensor * Kcur = ggml_rope_inplace(ctx0, ggml_reshape_3d(ctx0, ggml_mul_mat(ctx0, model.layers[il].wk, cur), n_embd/n_head, n_head, N), n_past, n_rot, 0);
             ggml_set_name(Qcur, "Qcur");
             ggml_set_name(Kcur, "Kcur");
 
@@ -1170,17 +1170,19 @@ static bool llama_eval_internal(
             struct ggml_tensor * KQ_scale = ggml_new_f32(ctx0, 1.0f/sqrtf(float(n_embd)/n_head));
             ggml_set_name(KQ_scale, "1/sqrt(n_embd/n_head)");
 
-            struct ggml_tensor * KQ_scaled = ggml_scale(ctx0, KQ, KQ_scale);
+            // KQ_scaled shape [n_past + N, N, n_head, 1]
+            struct ggml_tensor * KQ_scaled = ggml_scale_inplace(ctx0, KQ, KQ_scale);
             ggml_set_name(KQ_scaled, "KQ_scaled");
 
             // KQ_masked = mask_past(KQ_scaled)
-            struct ggml_tensor * KQ_masked = ggml_diag_mask_inf(ctx0, KQ_scaled, n_past);
+            struct ggml_tensor * KQ_masked = ggml_diag_mask_inf_inplace(ctx0, KQ_scaled, n_past);
             ggml_set_name(KQ_masked, "KQ_masked");
 
             // KQ = soft_max(KQ_masked)
-            struct ggml_tensor * KQ_soft_max = ggml_soft_max(ctx0, KQ_masked);
+            struct ggml_tensor * KQ_soft_max = ggml_soft_max_inplace(ctx0, KQ_masked);
             ggml_set_name(KQ_soft_max, "KQ_soft_max");
 
+
             // split cached V into n_head heads
             struct ggml_tensor * V =
                 ggml_view_3d(ctx0, kv_self.v,
@@ -1281,7 +1283,7 @@ static bool llama_eval_internal(
     lctx.use_buf(ctx0, -1);
 
     // logits -> probs
-    //inpL = ggml_soft_max(ctx0, inpL);
+    //inpL = ggml_soft_max_inplace(ctx0, inpL);
 
     // run the computation
     ggml_build_forward_expand(&gf, inpL);
@@ -2375,7 +2377,7 @@ int llama_apply_lora_from_file_internal(struct llama_context * ctx, const char *
 
             if (scaling != 1.0f) {
                 ggml_tensor * scale_tensor = ggml_new_f32(lora_ctx, scaling);
-                BA = ggml_scale(lora_ctx, BA, scale_tensor);
+                BA = ggml_scale_inplace(lora_ctx, BA, scale_tensor);
             }
 
             ggml_tensor * r;