vulkan: fix assertion when qy_needs_dequant (#12068)

Looks like a copy/paste bug from qx_needs_dequant.

diff --git a/ggml/src/ggml-vulkan/ggml-vulkan.cpp b/ggml/src/ggml-vulkan/ggml-vulkan.cpp
index 5864e9819d9c6a68c6228c886a7ed9c943f4135e..abe3e7908cb97815fae89f1e85e945951c311eb9 100644 (file)
--- a/ggml/src/ggml-vulkan/ggml-vulkan.cpp
+++ b/ggml/src/ggml-vulkan/ggml-vulkan.cpp
@@ -4192,7 +4192,7 @@ static void ggml_vk_mul_mat_q_f16(ggml_backend_vk_context * ctx, vk_context& sub
     }
     if (qy_needs_dequant) {
         d_Y = ctx->prealloc_y;
-        GGML_ASSERT(d_Y->size >= y_sz * ne02 * ne03);
+        GGML_ASSERT(d_Y->size >= y_sz * ne12 * ne13);
     } else {
         d_Y = d_Qy;
         y_buf_offset = qy_buf_offset;
@@ -4769,7 +4769,7 @@ static void ggml_vk_mul_mat_id_q_f16(ggml_backend_vk_context * ctx, vk_context&
     }
     if (qy_needs_dequant) {
         d_Y = ctx->prealloc_y;
-        GGML_ASSERT(d_Y->size >= y_sz * ne02 * ne03);
+        GGML_ASSERT(d_Y->size >= y_sz * ne12 * ne13);
     } else {
         d_Y = d_Qy;
         y_buf_offset = qy_buf_offset;