feat(runtime): publish Windows Vulkan binary (#3398)

* feat(runtime): add Windows Vulkan release asset

* fix(ci): install SPIR-V headers for Windows Vulkan

* fix(runtime): make Windows Vulkan package standalone

.github/workflows/build-llamacpp-binaries.yml

@@ -100,6 +100,27 @@ jobs:
               -DGGML_FMA=ON
               -DGGML_F16C=ON
               -DGGML_BMI2=ON
+          - os: windows-latest
+            name: windows-x64-vulkan
+            vulkan: true
+            windows_vulkan: true
+            build_target: llama-funasr-sensevoice
+            timeout_minutes: 90
+            cmake_flags: >-
+              -DGGML_NATIVE=OFF
+              -DCMAKE_MSVC_RUNTIME_LIBRARY=MultiThreaded
+              -DGGML_VULKAN=ON
+              -DGGML_OPENMP=OFF
+              -DGGML_AVX=OFF
+              -DGGML_AVX2=OFF
+              -DGGML_AVX_VNNI=OFF
+              -DGGML_AVX512=OFF
+              -DGGML_AVX512_VBMI=OFF
+              -DGGML_AVX512_VNNI=OFF
+              -DGGML_AVX512_BF16=OFF
+              -DGGML_FMA=OFF
+              -DGGML_F16C=OFF
+              -DGGML_BMI2=OFF
           - os: windows-latest
             name: windows-x64-cuda
             cuda: true
@@ -143,11 +164,38 @@ jobs:
         if: matrix.cuda
         run: nvcc --version
       - name: Install Vulkan SDK packages
-        if: matrix.vulkan
+        if: matrix.vulkan && runner.os == 'Linux'
         run: |
           sudo apt-get update
           sudo apt-get install -y libvulkan-dev glslc spirv-headers vulkan-tools
           vulkaninfo --summary || true
+      - name: Install Vulkan SDK
+        if: matrix.windows_vulkan
+        uses: humbletim/install-vulkan-sdk@30ba978f977e81b72d091fc8888feb1fb26f9aff
+        with:
+          version: '1.4.309.0'
+          cache: true
+      - name: Show Vulkan shader compiler
+        if: matrix.windows_vulkan
+        run: glslc --version
+      - name: Install SPIR-V Headers CMake package
+        if: matrix.windows_vulkan
+        run: |
+          runner_temp="$(cygpath -u "$RUNNER_TEMP")"
+          headers_src="$runner_temp/SPIRV-Headers"
+          headers_build="$runner_temp/SPIRV-Headers-build"
+          headers_prefix="$runner_temp/SPIRV-Headers-install"
+          git init -q "$headers_src"
+          git -C "$headers_src" remote add origin https://github.com/KhronosGroup/SPIRV-Headers.git
+          git -C "$headers_src" fetch --depth 1 origin 09913f088a1197aba4aefd300a876b2ebbaa3391
+          git -C "$headers_src" checkout --detach FETCH_HEAD
+          cmake -S "$headers_src" -B "$headers_build" \
+            -DSPIRV_HEADERS_ENABLE_INSTALL=ON \
+            -DSPIRV_HEADERS_ENABLE_TESTS=OFF \
+            -DCMAKE_INSTALL_PREFIX="$headers_prefix"
+          cmake --install "$headers_build" --config Release
+          cmake_prefix_path="$(cygpath -m "$headers_prefix")"
+          echo "CMAKE_PREFIX_PATH=$cmake_prefix_path" >> "$GITHUB_ENV"
       - name: Configure and build
         run: |
           # Release binaries must be portable across user machines, not tuned to
@@ -209,4 +257,4 @@ jobs:
           gh release create "$tag" dist/* \
             --repo "${{ github.repository }}" \
             --title "FunASR llama.cpp runtime $version" \
-            --notes "Prebuilt self-contained binaries for the FunASR llama.cpp / GGUF runtime: SenseVoice, Paraformer and Fun-ASR-Nano with built-in FSMN-VAD. Download the default quantized model with \`bash download-funasr-model.sh <sensevoice|paraformer|nano>\` (the helper requires the Hugging Face CLI: \`pip install -U huggingface_hub\`), then run \`llama-funasr-cli\` / \`llama-funasr-sensevoice\` / \`llama-funasr-paraformer\`. Use the default x64 asset for maximum CPU compatibility; use the x64-avx2 asset on CPUs with AVX2/FMA/F16C/BMI2 for higher throughput. The Linux Vulkan asset is \`linux-x64-vulkan\`; it requires a working Vulkan driver/ICD and enables SenseVoiceSmall graph execution with \`llama-funasr-sensevoice ... --backend vulkan\`. Build from source with \`-DGGML_VULKAN=ON\` to validate distro-specific GPU stacks. The Windows CUDA asset is \`windows-x64-cuda\`; it requires an NVIDIA driver compatible with the CUDA Toolkit version configured by the release workflow, targets CUDA architecture 86, and enables SenseVoiceSmall graph execution with \`llama-funasr-sensevoice ... --backend cuda\`. Build from source for other GPU architectures. No Python ASR runtime or local build is required. Docs: $docs"
+            --notes "Prebuilt self-contained binaries for the FunASR llama.cpp / GGUF runtime: SenseVoice, Paraformer and Fun-ASR-Nano with built-in FSMN-VAD. Download the default quantized model with \`bash download-funasr-model.sh <sensevoice|paraformer|nano>\` (the helper requires the Hugging Face CLI: \`pip install -U huggingface_hub\`), then run \`llama-funasr-cli\` / \`llama-funasr-sensevoice\` / \`llama-funasr-paraformer\`. Use the default x64 asset for maximum CPU compatibility; use the x64-avx2 asset on CPUs with AVX2/FMA/F16C/BMI2 for higher throughput. The Vulkan assets are \`linux-x64-vulkan\` and \`windows-x64-vulkan\`; they require a working Vulkan driver/ICD and enable SenseVoiceSmall graph execution with \`llama-funasr-sensevoice ... --backend vulkan\`. Build from source with \`-DGGML_VULKAN=ON\` to validate platform-specific GPU stacks. The Windows CUDA asset is \`windows-x64-cuda\`; it requires an NVIDIA driver compatible with the CUDA Toolkit version configured by the release workflow, targets CUDA architecture 86, and enables SenseVoiceSmall graph execution with \`llama-funasr-sensevoice ... --backend cuda\`. Build from source for other GPU architectures. No Python ASR runtime or local build is required. Docs: $docs"