From 60c9495c2f344ac512f9389a497ddd167e61c6fa Mon Sep 17 00:00:00 2001
From: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Date: Wed, 19 Mar 2025 16:44:34 +0200
Subject: [PATCH] Fix ggml_compute_forward_dup_q

I broke it with PR #265. I was testing with a model where
the wk_b and wk_v tensors were present, so didn't need to be computed,
so didn't notice that the change I made to ggml_compute_forward_dup_q
breaks that computation.
---
 ggml/src/ggml.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/ggml/src/ggml.c b/ggml/src/ggml.c
index 1552d91b..faf1902d 100644
--- a/ggml/src/ggml.c
+++ b/ggml/src/ggml.c
@@ -10576,6 +10576,11 @@ static void ggml_compute_forward_dup_q(
     if (dst->type == GGML_TYPE_Q8_0 && dst->src[0]->type == GGML_TYPE_Q8_0 &&
             ggml_are_same_shape(dst, dst->src[0])) {
 
+        if (dst->src[0]->nb[0] == sizeof(block_q8_0) && dst->nb[0] == sizeof(block_q8_0)) {
+            ggml_compute_forward_dup_bytes(params, dst);
+            return;
+        }
+
         // we assume src is transposed and that's why we are here
 
         GGML_ASSERT(dst->ne[0] % QK8_0 == 0);