ggml webgpu: profiling, CI updates, reworking of command submission

.github/workflows/build.yml

@@ -444,8 +444,8 @@ jobs:
           # This is using llvmpipe and runs slower than other backends
           ctest -L main --verbose --timeout 4200
 
-  ubuntu-22-cmake-webgpu:
-    runs-on: ubuntu-22.04
+  ubuntu-24-cmake-webgpu:
+    runs-on: ubuntu-24.04
 
     steps:
       - name: Clone
@@ -455,16 +455,34 @@ jobs:
       - name: ccache
         uses: ggml-org/[email protected]
         with:
-          key: ubuntu-22-cmake-webgpu
+          key: ubuntu-24-cmake-webgpu
           evict-old-files: 1d
 
-      - name: Vulkan SDK Dependencies
-        id: vulkan-depends
+      - name: Dependencies
+        id: depends
         run: |
-          wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | sudo apt-key add -
-          sudo wget -qO /etc/apt/sources.list.d/lunarg-vulkan-jammy.list https://packages.lunarg.com/vulkan/lunarg-vulkan-jammy.list
+          sudo add-apt-repository -y ppa:kisak/kisak-mesa
           sudo apt-get update -y
-          sudo apt-get install -y build-essential mesa-vulkan-drivers vulkan-sdk libcurl4-openssl-dev
+          sudo apt-get install -y build-essential mesa-vulkan-drivers libxcb-xinput0 libxcb-xinerama0 libxcb-cursor-dev libcurl4-openssl-dev
+
+      - name: Get latest Vulkan SDK version
+        id: vulkan_sdk_version
+        run: |
+          echo "VULKAN_SDK_VERSION=$(curl https://vulkan.lunarg.com/sdk/latest/linux.txt)" >> "$GITHUB_ENV"
+
+      - name: Use Vulkan SDK Cache
+        uses: actions/cache@v4
+        id: cache-sdk
+        with:
+          path: ./vulkan_sdk
+          key: vulkan-sdk-${{ env.VULKAN_SDK_VERSION }}-${{ runner.os }}
+
+      - name: Setup Vulkan SDK
+        if: steps.cache-sdk.outputs.cache-hit != 'true'
+        uses: ./.github/actions/linux-setup-vulkan
+        with:
+          path: ./vulkan_sdk
+          version: ${{ env.VULKAN_SDK_VERSION }}
 
       - name: Dawn Dependency
         id: dawn-depends

CODEOWNERS

@@ -74,6 +74,7 @@
 /ggml/src/ggml.c                        @ggerganov @slaren
 /ggml/src/ggml.cpp                      @ggerganov @slaren
 /ggml/src/gguf.cpp                      @JohannesGaessler @Green-Sky
+/ggml/src/ggml-webgpu/                  @reeselevine
 /gguf-py/                               @CISC
 /media/                                 @ggerganov
 /scripts/gen*                           @ggerganov

ggml/CMakeLists.txt

@@ -221,7 +221,11 @@ option(GGML_VULKAN_SHADER_DEBUG_INFO        "ggml: enable Vulkan shader debug in
 option(GGML_VULKAN_VALIDATE                 "ggml: enable Vulkan validation"                  OFF)
 option(GGML_VULKAN_RUN_TESTS                "ggml: run Vulkan tests"                          OFF)
 option(GGML_WEBGPU                          "ggml: use WebGPU"                                OFF)
+option(GGML_WEBGPU_SERIALIZE_SUBMIT         "ggml: enable WebGPU command serialization"       OFF)
 option(GGML_WEBGPU_DEBUG                    "ggml: enable WebGPU debug output"                OFF)
+option(GGML_WEBGPU_CPU_PROFILE              "ggml: enable WebGPU profiling (CPU)"             OFF)
+option(GGML_WEBGPU_GPU_PROFILE              "ggml: enable WebGPU profiling (GPU)"             OFF)
+
 option(GGML_ZDNN                            "ggml: use zDNN"                                  OFF)
 option(GGML_METAL                           "ggml: use Metal"                                 ${GGML_METAL_DEFAULT})
 option(GGML_METAL_NDEBUG                    "ggml: disable Metal debugging"                   OFF)

ggml/src/ggml-webgpu/CMakeLists.txt

@@ -46,9 +46,21 @@ else()
     set(DawnWebGPU_TARGET dawn::webgpu_dawn)
 endif()
 
+if (GGML_WEBGPU_SERIALIZE_SUBMIT)
+    target_compile_definitions(ggml-webgpu PRIVATE GGML_WEBGPU_SERIALIZE_SUBMIT=1)
+endif()
+
 if (GGML_WEBGPU_DEBUG)
     target_compile_definitions(ggml-webgpu PRIVATE GGML_WEBGPU_DEBUG=1)
 endif()
 
+if (GGML_WEBGPU_CPU_PROFILE)
+    target_compile_definitions(ggml-webgpu PRIVATE GGML_WEBGPU_CPU_PROFILE=1)
+endif()
+
+if (GGML_WEBGPU_GPU_PROFILE)
+    target_compile_definitions(ggml-webgpu PRIVATE GGML_WEBGPU_GPU_PROFILE=1)
+endif()
+
 target_include_directories(ggml-webgpu PRIVATE ${SHADER_OUTPUT_DIR})
 target_link_libraries(ggml-webgpu PRIVATE ${DawnWebGPU_TARGET})