From: Diego Devesa <redacted>
Date: Sun, 24 Nov 2024 15:10:26 +0000 (+0100)
Subject: llama : fix op mul check with command-r-plus (#10476)
X-Git-Tag: upstream/0.0.4488~330
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=dc39012cbaf8752fabecaeb60af78ccdd1dfb73b;p=pkg%2Fggml%2Fsources%2Fllama.cpp

llama : fix op mul check with command-r-plus (#10476)
---

diff --git a/src/llama.cpp b/src/llama.cpp
index 00171103..20df09b1 100644
--- a/src/llama.cpp
+++ b/src/llama.cpp
@@ -7181,12 +7181,12 @@ static bool weight_buft_supported(const llama_hparams & hparams, ggml_tensor * w
             } break;
         case GGML_OP_ADD:
             {
-                ggml_tensor * a = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, w->ne[0], 512);
+                ggml_tensor * a = ggml_new_tensor_4d(ctx, GGML_TYPE_F32, w->ne[0], w->ne[1], w->ne[2], w->ne[3]);
                 op_tensor = ggml_add(ctx, a, w);
             } break;
         case GGML_OP_MUL:
             {
-                ggml_tensor * a = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, w->ne[0], 512);
+                ggml_tensor * a = ggml_new_tensor_4d(ctx, GGML_TYPE_F32, w->ne[0], w->ne[1], w->ne[2], w->ne[3]);
                 op_tensor = ggml_mul(ctx, a, w);
             } break;
         case GGML_OP_DIV: