vendor: attempt to ignore warnings from vendored files

Signed-off-by: Aaron Teo <[email protected]>

.github/workflows/build-ibm.yml

@@ -100,6 +100,46 @@ jobs:
           wget https://huggingface.co/ggml-org/models/resolve/main/tinyllamas/stories260K-be.gguf
           ./bin/llama-completion -m stories260K-be.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256
 
+  ubuntu-26-zdnn-s390x:
+    name: ubuntu-26-zdnn-s390x
+    runs-on: ubuntu-24.04-s390x
+    container: ubuntu:26.04  # required to get GCC 15.1 and binutils 2.44
+    defaults:
+      run:
+        shell: bash
+
+    steps:
+      - name: Build Dependencies
+        id: build_depends
+        run: |
+          apt-get update
+          apt-get install -y --no-install-recommends \
+            build-essential cmake git ca-certificates \
+            libssl-dev libzdnn-dev
+
+      - name: Clone
+        id: checkout
+        uses: actions/checkout@v6
+
+      - name: Toolchain workaround (GCC 15)
+        run: |
+          apt-get install -y gcc-15 g++-15
+          echo "CC=gcc-15" >> "$GITHUB_ENV"
+          echo "CXX=g++-15" >> "$GITHUB_ENV"
+
+      - name: Build with zDNN Backend
+        id: cmake_build
+        run: |
+          cmake -B build \
+            -DLLAMA_FATAL_WARNINGS=ON \
+            -DGGML_NATIVE=OFF \
+            -DGGML_VXE=ON \
+            -DGGML_ZDNN=ON \
+            -DGGML_RPC=ON \
+            -DCMAKE_C_FLAGS="-march=arch15" \
+            -DCMAKE_CXX_FLAGS="-march=arch15"
+          time cmake --build build --config Release -j $(nproc)
+
   ubuntu-24-ppc64le:
     runs-on: ubuntu-24.04-ppc64le
 

common/arg.cpp

@@ -2673,16 +2673,17 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
             params.video_ffmpeg_bin_dir = value;
         }
     ).set_examples(mmproj_examples).set_env("LLAMA_ARG_VIDEO_FFMPEG_DIR"));
-    if (params.is_gen_docs || llama_supports_rpc()) {
-        add_opt(common_arg(
-            {"--rpc"}, "SERVERS",
-            "comma-separated list of RPC servers (host:port)",
-            [](common_params & params, const std::string & value) {
-                add_rpc_devices(value);
-                GGML_UNUSED(params);
+    add_opt(common_arg(
+        {"--rpc"}, "SERVERS",
+        "comma-separated list of RPC servers (host:port)",
+        [](common_params & params, const std::string & value) {
+            if (!llama_supports_rpc()) {
+                throw std::invalid_argument("RPC not supported in this build");
             }
-        ).set_env("LLAMA_ARG_RPC"));
-    }
+            add_rpc_devices(value);
+            GGML_UNUSED(params);
+        }
+    ).set_env("LLAMA_ARG_RPC"));
     add_opt(common_arg(
         {"-lm", "--load-mode"}, "MODE",
         "model loading mode (default: auto)\n"

ggml/include/ggml-zdnn.h

@@ -10,6 +10,8 @@ extern "C" {
 // device buffer
 GGML_BACKEND_API ggml_backend_buffer_type_t ggml_backend_zdnn_buffer_type(void);
 
+GGML_BACKEND_API bool ggml_backend_is_zdnn(ggml_backend_t backend);
+
 GGML_BACKEND_API ggml_backend_reg_t ggml_backend_zdnn_reg(void);
 
 #ifdef __cplusplus

ggml/src/ggml-zdnn/ggml-zdnn.cpp

@@ -438,15 +438,13 @@ static ggml_backend_i ggml_backend_zdnn_i = {
 };
 
 static ggml_guid_t ggml_backend_zdnn_guid(void) {
-    static const char * guid_str = "IBM-ZDNN-ACCELER";
-    return reinterpret_cast<ggml_guid_t>((void *)guid_str);
+    static char guid_str[] = "IBM-ZDNN-ACCELER";
+    return reinterpret_cast<ggml_guid_t>(guid_str);
 }
 
 bool ggml_backend_is_zdnn(ggml_backend_t backend) {
     return backend != NULL &&
            ggml_guid_matches(backend->guid, ggml_backend_zdnn_guid());
-
-    GGML_UNUSED(backend);
 }
 
 //
@@ -483,7 +481,7 @@ static void ggml_backend_zdnn_device_get_props(ggml_backend_dev_t dev, ggml_back
     props->description = ggml_backend_zdnn_device_get_description(dev);
     props->type        = ggml_backend_zdnn_device_get_type(dev);
     ggml_backend_zdnn_device_get_memory(dev, &props->memory_free, &props->memory_total);
-    props->caps = (ggml_backend_dev_caps) {
+    props->caps = {
         /* .async                = */ false,
         /* .host_buffer          = */ false,
         /* .buffer_from_host_ptr = */ false,
@@ -500,7 +498,7 @@ static ggml_backend_t ggml_backend_zdnn_device_init(ggml_backend_dev_t dev, cons
     }
 
     ggml_backend_t backend = (ggml_backend *)malloc(sizeof(ggml_backend));
-    *backend = (ggml_backend) {
+    *backend = {
         /* .guid       = */ ggml_backend_zdnn_guid(),
         /* .iface      = */ ggml_backend_zdnn_i,
         /* .device     = */ dev,
@@ -619,13 +617,13 @@ ggml_backend_reg_t ggml_backend_zdnn_reg(void) {
     atexit(ggml_zdnn_cleanup);
 
     {
-        g_ggml_backend_zdnn_reg = (ggml_backend_reg) {
+        g_ggml_backend_zdnn_reg = {
             /* .api_version = */ GGML_ZDNN_VERSION,
             /* .iface       = */ ggml_backend_zdnn_reg_i,
             /* .context     = */ NULL
         };
 
-        g_ggml_backend_zdnn_device = (ggml_backend_device) {
+        g_ggml_backend_zdnn_device = {
             /* .iface       = */ ggml_backend_zdnn_device_i,
             /* .reg         = */ &g_ggml_backend_zdnn_reg,
             /* .context     = */ &g_ggml_ctx_dev_main

tools/server/server.cpp

@@ -102,12 +102,12 @@ int llama_server(int argc, char ** argv) {
     // touch it. lifecycle is symmetric, stop_gc() runs in clean_up() before backend free
     server_stream_session_manager_start();
 
-    SRV_INF("%s", "initializing ...\n");
-
     if (!common_params_parse(argc, argv, params, LLAMA_EXAMPLE_SERVER)) {
         return 1;
     }
 
+    SRV_INF("%s", "initializing ...\n");
+
     llama_backend_init();
     llama_numa_init(params.numa);
 

vendor/stb/CMakeLists.txt

@@ -4,3 +4,7 @@ add_library(stb INTERFACE)
 add_library(vendor::stb ALIAS stb)
 
 target_include_directories(stb INTERFACE ..)
+
+if (CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
+    target_compile_options(stb INTERFACE -Wno-maybe-uninitialized)
+endif()