From: AidanBeltonS <redacted>
Date: Mon, 27 May 2024 16:34:51 +0000 (+0100)
Subject: Fix q_xxs using mul_mat_q (llama/7459)
X-Git-Tag: upstream/0.0.1642~643
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=2a791109462855f1c793219b4301706d6039c552;p=pkg%2Fggml%2Fsources%2Fggml

Fix q_xxs using mul_mat_q (llama/7459)
---

diff --git a/src/ggml-sycl.cpp b/src/ggml-sycl.cpp
index f329bc27..8839f775 100644
--- a/src/ggml-sycl.cpp
+++ b/src/ggml-sycl.cpp
@@ -15263,6 +15263,7 @@ static void ggml_sycl_mul_mat(const ggml_tensor * src0, const ggml_tensor * src1
             }
         } else {
             bool use_mul_mat_q = min_compute_capability >= VER_4VEC && ggml_is_quantized(src0->type);
+            use_mul_mat_q = use_mul_mat_q && (src0->type != GGML_TYPE_IQ2_XXS);
 
             if (use_xmx && min_compute_capability >= VER_GEN9 && src1->ne[1] > XMX_MAX_BATCH_SIZE) {
                 use_mul_mat_q = false;