Commit 1af6c65de for llama.cpp

commit 1af6c65de09e88af221f5dbc127fa13fba96f145
Author: Aaron Teo <aaron.teo1@ibm.com>
Date:   Tue Sep 15 17:23:16 2026 +0800

    ci: bump kleidiai runners from 22.04 to 24.04 (#28885)

    * ci: bump kleidiai runners from 22.04 to 24.04

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

    * ci: promote warnings to hard errors for ci

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

    ---------

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

diff --git a/.github/workflows/build-self-hosted.yml b/.github/workflows/build-self-hosted.yml
index 2e05988bf..1337a0ed5 100644
--- a/.github/workflows/build-self-hosted.yml
+++ b/.github/workflows/build-self-hosted.yml
@@ -361,7 +361,7 @@ jobs:
           LLAMA_ARG_THREADS=$(nproc) GG_BUILD_HIGH_PERF=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp

   cpu-arm64-high-perf-graviton4:
-    runs-on: ah-ubuntu_22_04-c8g_8x
+    runs-on: ah-ubuntu_24_04-c8g_8x

     steps:
       - name: Clone
@@ -404,7 +404,7 @@ jobs:
           bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp

   cpu-arm64-graviton4-kleidiai:
-    runs-on: ah-ubuntu_22_04-c8g_8x
+    runs-on: ah-ubuntu_24_04-c8g_8x

     steps:
       - name: Clone
diff --git a/.github/workflows/server-self-hosted.yml b/.github/workflows/server-self-hosted.yml
index de30d1a74..8dc4637c4 100644
--- a/.github/workflows/server-self-hosted.yml
+++ b/.github/workflows/server-self-hosted.yml
@@ -192,7 +192,7 @@ jobs:
           PYTEST_WORKERS=1 ./tests.sh

   server-kleidiai:
-    runs-on: ah-ubuntu_22_04-c8g_8x
+    runs-on: ah-ubuntu_24_04-c8g_8x

     steps:
       - name: Clone
@@ -232,7 +232,7 @@ jobs:
       - name: Build
         id: cmake_build
         run: |
-          cmake -B build -DGGML_SCHED_NO_REALLOC=ON -DGGML_CPU_KLEIDIAI=ON
+          cmake -B build -DGGML_SCHED_NO_REALLOC=ON -DGGML_CPU_KLEIDIAI=ON -DLLAMA_FATAL_WARNINGS=ON
           cmake --build build --config Release -j $(nproc) --target llama-server

       - name: Python setup