Fix missing memory_v

Author: ocrickard

llama.cpp

@@ -862,7 +862,7 @@ static bool llama_eval_internal(
             struct ggml_tensor * V_trans =
                 ggml_permute(ctx0,
                         ggml_reshape_3d(ctx0,
-                            ggml_view_1d(ctx0, model.memory_v, (n_past + N)*n_embd, il*n_ctx*ggml_element_size(model.memory_v)*n_embd),
+                            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);