ci : fix windows ccaches (ggml-org#23777)

* ci : server windows set build type explicitly

* cont : try windows-2025

* ci : use llvm

* cont : use ninja

* cont : fix shell

* ci : set number of jobs correctly

* ci : fix windows with vulkan ccache by using llvm

* ci : server ccache only on master

* ocd : fix job names

[no release]

Author: ggerganov

.github/workflows/build.yml

@@ -181,16 +181,16 @@ jobs:
     strategy:
       matrix:
         include:
-          - build: 'cpu-x64 (static)'
+          - build: 'x64-cpu-static'
             arch: 'x64'
             defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/x64-windows-llvm.cmake -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DBUILD_SHARED_LIBS=OFF'
-          - build: 'openblas-x64'
+          - build: 'x64-openblas'
             arch: 'x64'
             defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/x64-windows-llvm.cmake -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DGGML_OPENMP=OFF -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"'
-          - build: 'vulkan-x64'
+          - build: 'x64-vulkan'
             arch: 'x64'
-            defines: '-DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DGGML_VULKAN=ON'
-          - build: 'llvm-arm64'
+            defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/x64-windows-llvm.cmake -DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DGGML_VULKAN=ON'
+          - build: 'arm64'
             arch: 'arm64'
             defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/arm64-windows-llvm.cmake -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON'
 
@@ -209,7 +209,7 @@ jobs:
 
       - name: Download OpenBLAS
         id: get_openblas
-        if: ${{ matrix.build == 'openblas-x64' }}
+        if: ${{ matrix.build == 'x64-openblas' }}
         run: |
           curl.exe -o $env:RUNNER_TEMP/openblas.zip -L "https://github.com/xianyi/OpenBLAS/releases/download/v${env:OPENBLAS_VERSION}/OpenBLAS-${env:OPENBLAS_VERSION}-x64.zip"
           curl.exe -o $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt -L "https://github.com/xianyi/OpenBLAS/raw/v${env:OPENBLAS_VERSION}/LICENSE"
@@ -222,7 +222,7 @@ jobs:
 
       - name: Install Vulkan SDK
         id: get_vulkan
-        if: ${{ matrix.build == 'vulkan-x64' }}
+        if: ${{ matrix.build == 'x64-vulkan' }}
         run: |
           curl.exe -o $env:RUNNER_TEMP/VulkanSDK-Installer.exe -L "https://sdk.lunarg.com/sdk/download/${env:VULKAN_VERSION}/windows/vulkansdk-windows-X64-${env:VULKAN_VERSION}.exe"
           & "$env:RUNNER_TEMP\VulkanSDK-Installer.exe" --accept-licenses --default-answer --confirm-command install
@@ -243,7 +243,7 @@ jobs:
 
       - name: Add libopenblas.dll
         id: add_libopenblas_dll
-        if: ${{ matrix.build == 'openblas-x64' }}
+        if: ${{ matrix.build == 'x64-openblas' }}
         run: |
           cp $env:RUNNER_TEMP/openblas/bin/libopenblas.dll ./build/bin/Release/openblas.dll
           cp $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt ./build/bin/Release/OpenBLAS-${env:OPENBLAS_VERSION}.txt

.github/workflows/server.yml

@@ -54,10 +54,10 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
-  server:
+  ubuntu:
     runs-on: ubuntu-latest
 
-    name: server (${{ matrix.wf_name }})
+    name: ubuntu (${{ matrix.wf_name }})
     strategy:
       matrix:
         build_type: [Release]
@@ -130,8 +130,8 @@ jobs:
           export ${{ matrix.extra_args }}
           SLOW_TESTS=1 pytest -v -x
 
-  server-windows:
-    runs-on: windows-2022
+  windows:
+    runs-on: windows-2025
 
     steps:
       - name: Clone
@@ -150,9 +150,15 @@ jobs:
 
       - name: Build
         id: cmake_build
+        shell: cmd
         run: |
-          cmake -B build -DLLAMA_BUILD_BORINGSSL=ON -DGGML_SCHED_NO_REALLOC=ON
-          cmake --build build --config Release -j ${env:NUMBER_OF_PROCESSORS} --target llama-server
+          cmake -B build -G "Ninja Multi-Config" ^
+            -DCMAKE_TOOLCHAIN_FILE=cmake/x64-windows-llvm.cmake ^
+            -DCMAKE_BUILD_TYPE=Release ^
+            -DLLAMA_BUILD_BORINGSSL=ON ^
+            -DGGML_SCHED_NO_REALLOC=ON
+          set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1
+          cmake --build build --config Release -j %NINJA_JOBS% --target llama-server
 
       - name: Python setup
         id: setup_python