Commit be2c6d7d1 for llama.cpp

commit be2c6d7d1ff08b3059d8bf755623c77768f8482b
Author: Aaron Teo <aaron.teo1@ibm.com>
Date:   Mon Sep 14 19:04:58 2026 +0800

    tests(s390x): add non-vxe build to tests (#28776)

    * tests: add non-vxe build to tests

    Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

    ggml-cpu: add unused macro to fix ci

    Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

    Revert "ggml-cpu: temporarily add #28775 patch until its merged"

    This reverts commit d4645257b6b7e65c47b1b46baec3eb46a3f40968.

    Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

    * ggml-cpu: revert back to upstream/master

    Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

    ---------

    Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

diff --git a/.github/workflows/build-ibm.yml b/.github/workflows/build-ibm.yml
index d2e4f3cda..355487e97 100644
--- a/.github/workflows/build-ibm.yml
+++ b/.github/workflows/build-ibm.yml
@@ -34,10 +34,15 @@ env:
   LLAMA_ARG_LOG_TIMESTAMPS: 1

 jobs:
-
   ubuntu-24-s390x:
+    name: ubuntu-24-s390x (VXE ${{ matrix.vxe }})
     runs-on: ubuntu-24.04-s390x

+    strategy:
+      fail-fast: false
+      matrix:
+        vxe: ["ON", "OFF"]  # `-DGGML_VXE=ON/OFF`
+
     steps:
       - name: Clone
         id: checkout
@@ -77,7 +82,8 @@ jobs:
         run: |
           cmake -B build \
             -DLLAMA_FATAL_WARNINGS=ON \
-            -DGGML_RPC=ON
+            -DGGML_RPC=ON \
+            -DGGML_VXE=${{ matrix.vxe }}
           time cmake --build build --config Release -j $(nproc)

       - name: Test
diff --git a/ggml/src/ggml-cpu/arch/s390/quants.c b/ggml/src/ggml-cpu/arch/s390/quants.c
index 70f2882d8..52344828e 100644
--- a/ggml/src/ggml-cpu/arch/s390/quants.c
+++ b/ggml/src/ggml-cpu/arch/s390/quants.c
@@ -417,6 +417,7 @@ void ggml_vec_dot_mxfp4_q8_0(int n, float * GGML_RESTRICT s, size_t bs, const vo
     sumf = vec_hsum_f32x4(v_acc);
     *s = sumf;
 #else
+    UNUSED(nb);
     UNUSED(x);
     UNUSED(y);
     UNUSED(ib);