Commit edec462cc for llama.cpp

commit edec462cc00abebc50610b82ac06c6cde266e5d0
Author: Adrien Gallouët <angt@huggingface.co>
Date:   Wed Nov 18 21:10:23 2026 +0100

    ggml, ci : use llvm 22.1.8 (#32548)

    * ggml, ci : use llvm 22.1.8

    Signed-off-by: Adrien Gallouët <angt@huggingface.co>

    * Update build-cpu.yml too

    Signed-off-by: Adrien Gallouët <angt@huggingface.co>

    * Fix clang 22

    Signed-off-by: Adrien Gallouët <angt@huggingface.co>

    * Fix release.yml (arm64 with vulkan)

    Signed-off-by: Adrien Gallouët <angt@huggingface.co>

    * Fix server.yml

    Signed-off-by: Adrien Gallouët <angt@huggingface.co>

    ---------

    Signed-off-by: Adrien Gallouët <angt@huggingface.co>

diff --git a/.github/workflows/build-cpu.yml b/.github/workflows/build-cpu.yml
index 35d610e1e..285a01a7c 100644
--- a/.github/workflows/build-cpu.yml
+++ b/.github/workflows/build-cpu.yml
@@ -187,6 +187,11 @@ jobs:
         run: |
           choco install ninja

+      - name: Install LLVM
+        run: |
+          choco install llvm --version=22.1.8
+          echo "C:\Program Files\LLVM\bin" >> $env:GITHUB_PATH
+
       - name: Build
         id: cmake_build
         run: |
diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml
index 4d78c9985..c918feb06 100644
--- a/.github/workflows/release.yml
+++ b/.github/workflows/release.yml
@@ -900,6 +900,11 @@ jobs:
         run: |
           choco install ninja

+      - name: Install LLVM
+        run: |
+          choco install llvm --version=22.1.8
+          echo "C:\Program Files\LLVM\bin" >> $env:GITHUB_PATH
+
       - name: ccache
         uses: ggml-org/ccache-action@v1.2.24
         with:
@@ -1146,6 +1151,11 @@ jobs:
         run: |
           choco install ninja

+      - name: Install LLVM
+        run: |
+          choco install llvm --version=22.1.8
+          echo "C:\Program Files\LLVM\bin" >> $env:GITHUB_PATH
+
       # TODO: these jobs need to use llvm toolchain in order to utilize the ccache
       #- name: ccache
       #  uses: ggml-org/ccache-action@v1.2.24
diff --git a/.github/workflows/server.yml b/.github/workflows/server.yml
index f3c577ec6..38231317e 100644
--- a/.github/workflows/server.yml
+++ b/.github/workflows/server.yml
@@ -175,6 +175,11 @@ jobs:
           evict-old-files: 1d
           save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}

+      - name: Install LLVM
+        run: |
+          choco install llvm --version=22.1.8
+          echo "C:\Program Files\LLVM\bin" >> $env:GITHUB_PATH
+
       - name: Build
         id: cmake_build
         shell: cmd
diff --git a/ggml/src/CMakeLists.txt b/ggml/src/CMakeLists.txt
index 5ff78f240..eee1a460d 100644
--- a/ggml/src/CMakeLists.txt
+++ b/ggml/src/CMakeLists.txt
@@ -231,7 +231,7 @@ if (GGML_OPENMP_FETCH)
         message(FATAL_ERROR "GGML_OPENMP_FETCH currently requires Clang on Windows")
     endif()

-    set(GGML_OPENMP_LLVM_VERSION "20.1.8")
+    set(GGML_OPENMP_LLVM_VERSION "22.1.8")
     string(REGEX MATCH "^[0-9]+" GGML_OPENMP_LLVM_VERSION_MAJOR "${GGML_OPENMP_LLVM_VERSION}")
     string(REGEX MATCH "^[0-9]+" GGML_OPENMP_COMPILER_VERSION_MAJOR "${CMAKE_C_COMPILER_VERSION}")
     if (NOT GGML_OPENMP_COMPILER_VERSION_MAJOR STREQUAL GGML_OPENMP_LLVM_VERSION_MAJOR)
@@ -242,11 +242,11 @@ if (GGML_OPENMP_FETCH)
     if (GGML_OPENMP_SYSTEM_PROCESSOR MATCHES "^(amd64|x86_64)$")
         set(GGML_OPENMP_ARCH "x64")
         set(GGML_OPENMP_INSTALLER_SUFFIX "win64")
-        set(GGML_OPENMP_INSTALLER_SHA256 "3197846a2b19063687dd56e93e34cd941e3548d907f23a6131571321bdf9fe7b")
+        set(GGML_OPENMP_INSTALLER_SHA256 "16e5709785fef73c854646241c4a92c5cd574318d1b33c63330dd7721903e55c")
     elseif (GGML_OPENMP_SYSTEM_PROCESSOR MATCHES "^(aarch64|arm64)$")
         set(GGML_OPENMP_ARCH "arm64")
         set(GGML_OPENMP_INSTALLER_SUFFIX "woa64")
-        set(GGML_OPENMP_INSTALLER_SHA256 "7c4ac97eb2ae6b960ca5f9caf3ff6124c8d2a18cc07a7840a4d2ea15537bad8e")
+        set(GGML_OPENMP_INSTALLER_SHA256 "76f44ef1ba6eeb5a65904e9500f042f588fade49952778ce48f0374daa934396")
     else()
         message(FATAL_ERROR "GGML_OPENMP_FETCH does not support ${CMAKE_SYSTEM_PROCESSOR}")
     endif()
diff --git a/ggml/src/ggml-cpu/arch/x86/quants.c b/ggml/src/ggml-cpu/arch/x86/quants.c
index 458f05f27..594da2683 100644
--- a/ggml/src/ggml-cpu/arch/x86/quants.c
+++ b/ggml/src/ggml-cpu/arch/x86/quants.c
@@ -861,8 +861,8 @@ void ggml_vec_dot_q4_0_q8_0(int n, float * GGML_RESTRICT s, size_t bs, const voi
     __m128 acc_3 = _mm_setzero_ps();

     for (; ib + 1 < nb; ib += 2) {
-        _mm_prefetch(&x[ib] + sizeof(block_q4_0), _MM_HINT_T0);
-        _mm_prefetch(&y[ib] + sizeof(block_q8_0), _MM_HINT_T0);
+        _mm_prefetch((const char *) (&x[ib] + sizeof(block_q4_0)), _MM_HINT_T0);
+        _mm_prefetch((const char *) (&y[ib] + sizeof(block_q8_0)), _MM_HINT_T0);

         // Compute combined scale for the block 0 and 1
         const __m128 d_0_1 = _mm_set1_ps( GGML_CPU_FP16_TO_FP32(x[ib].d) * GGML_CPU_FP16_TO_FP32(y[ib].d) );
@@ -879,8 +879,8 @@ void ggml_vec_dot_q4_0_q8_0(int n, float * GGML_RESTRICT s, size_t bs, const voi
         bx_1 = _mm_sub_epi8(bx_1, off);
         const __m128i i32_1 = mul_sum_i8_pairs(bx_1, by_1);

-        _mm_prefetch(&x[ib] + 2 * sizeof(block_q4_0), _MM_HINT_T0);
-        _mm_prefetch(&y[ib] + 2 * sizeof(block_q8_0), _MM_HINT_T0);
+        _mm_prefetch((const char *) (&x[ib] + 2 * sizeof(block_q4_0)), _MM_HINT_T0);
+        _mm_prefetch((const char *) (&y[ib] + 2 * sizeof(block_q8_0)), _MM_HINT_T0);

         // Compute combined scale for the block 2 and 3
         const __m128 d_2_3 = _mm_set1_ps( GGML_CPU_FP16_TO_FP32(x[ib + 1].d) * GGML_CPU_FP16_TO_FP32(y[ib + 1].d) );