Merge branch 'master' into sdxs

Author: leejet

.dockerignore

@@ -1,4 +1,5 @@
 build*/
+docs/
 test/
 
 .cache/

.github/workflows/build.yml

@@ -38,6 +38,10 @@ on:
 env:
   BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
+  cancel-in-progress: true
+
 jobs:
   ubuntu-latest-cmake:
     runs-on: ubuntu-latest
@@ -92,6 +96,123 @@ jobs:
           path: |
             sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-${{ steps.system-info.outputs.OS_TYPE }}-${{ steps.system-info.outputs.OS_NAME }}-${{ steps.system-info.outputs.OS_VERSION }}-${{ steps.system-info.outputs.CPU_ARCH }}.zip
 
+  ubuntu-latest-cmake-vulkan:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Clone
+        id: checkout
+        uses: actions/checkout@v3
+        with:
+          submodules: recursive
+
+      - name: Dependencies
+        id: depends
+        run: |
+          sudo apt-get update
+          sudo apt-get install build-essential libvulkan-dev glslc
+
+      - name: Build
+        id: cmake_build
+        run: |
+          mkdir build
+          cd build
+          cmake .. -DSD_BUILD_SHARED_LIBS=ON -DSD_VULKAN=ON
+          cmake --build . --config Release
+
+      - name: Get commit hash
+        id: commit
+        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+        uses: pr-mpt/actions-commit-hash@v2
+
+      - name: Fetch system info
+        id: system-info
+        run: |
+          echo "CPU_ARCH=`uname -m`" >> "$GITHUB_OUTPUT"
+          echo "OS_NAME=`lsb_release -s -i`" >> "$GITHUB_OUTPUT"
+          echo "OS_VERSION=`lsb_release -s -r`" >> "$GITHUB_OUTPUT"
+          echo "OS_TYPE=`uname -s`" >> "$GITHUB_OUTPUT"
+
+      - name: Pack artifacts
+        id: pack_artifacts
+        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+        run: |
+          cp ggml/LICENSE ./build/bin/ggml.txt
+          cp LICENSE ./build/bin/stable-diffusion.cpp.txt
+          zip -j sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-${{ steps.system-info.outputs.OS_TYPE }}-${{ steps.system-info.outputs.OS_NAME }}-${{ steps.system-info.outputs.OS_VERSION }}-${{ steps.system-info.outputs.CPU_ARCH }}-vulkan.zip ./build/bin/*
+
+      - name: Upload artifacts
+        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+        uses: actions/upload-artifact@v4
+        with:
+          name: sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-${{ steps.system-info.outputs.OS_TYPE }}-${{ steps.system-info.outputs.OS_NAME }}-${{ steps.system-info.outputs.OS_VERSION }}-${{ steps.system-info.outputs.CPU_ARCH }}-vulkan.zip
+          path: |
+            sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-${{ steps.system-info.outputs.OS_TYPE }}-${{ steps.system-info.outputs.OS_NAME }}-${{ steps.system-info.outputs.OS_VERSION }}-${{ steps.system-info.outputs.CPU_ARCH }}-vulkan.zip
+
+  build-and-push-docker-images:
+    name: Build and push container images
+    runs-on: ubuntu-latest
+
+    permissions:
+      contents: read
+      packages: write
+      id-token: write
+      attestations: write
+      artifact-metadata: write
+
+    strategy:
+      matrix:
+        variant: [musa, sycl, vulkan]
+
+    env:
+      REGISTRY: ghcr.io
+      IMAGE_NAME: ${{ github.repository }}
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+        with:
+          submodules: recursive
+
+      - name: Get commit hash
+        id: commit
+        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+        uses: pr-mpt/actions-commit-hash@v2
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to the container registry
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata for Docker
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+
+      - name: Free Disk Space (Ubuntu)
+        uses: jlumbroso/[email protected]
+        with:
+          # this might remove tools that are actually needed,
+          # if set to "true" but frees about 6 GB
+          tool-cache: false
+
+      - name: Build and push Docker image
+        id: build-push
+        uses: docker/build-push-action@v6
+        with:
+          platforms: linux/amd64
+          push: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+          file: Dockerfile.${{ matrix.variant }}
+          tags: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:${{ env.BRANCH_NAME }}-${{ matrix.variant }}
+          labels: ${{ steps.meta.outputs.labels }}
+          annotations: ${{ steps.meta.outputs.annotations }}
+
   macOS-latest-cmake:
     runs-on: macos-latest
 
@@ -146,7 +267,7 @@ jobs:
             sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-${{ steps.system-info.outputs.OS_TYPE }}-${{ steps.system-info.outputs.OS_NAME }}-${{ steps.system-info.outputs.OS_VERSION }}-${{ steps.system-info.outputs.CPU_ARCH }}.zip
 
   windows-latest-cmake:
-    runs-on: windows-2025
+    runs-on: windows-2022
 
     env:
       VULKAN_VERSION: 1.4.328.1
@@ -164,7 +285,7 @@ jobs:
             defines: "-DGGML_NATIVE=OFF -DGGML_AVX512=ON -DGGML_AVX=ON -DGGML_AVX2=ON -DSD_BUILD_SHARED_LIBS=ON"
           - build: "cuda12"
             defines: "-DSD_CUDA=ON -DSD_BUILD_SHARED_LIBS=ON -DCMAKE_CUDA_ARCHITECTURES='61;70;75;80;86;89;90;100;120' -DCMAKE_CUDA_FLAGS='-Xcudafe \"--diag_suppress=177\" -Xcudafe \"--diag_suppress=550\"'"
-          - build: 'vulkan'
+          - build: "vulkan"
             defines: "-DSD_VULKAN=ON -DSD_BUILD_SHARED_LIBS=ON"
     steps:
       - name: Clone
@@ -200,7 +321,7 @@ jobs:
         run: |
           mkdir build
           cd build
-          cmake .. -DCMAKE_CXX_FLAGS='/bigobj' -G Ninja -DCMAKE_C_COMPILER=cl.exe -DCMAKE_CXX_COMPILER=cl.exe ${{ matrix.defines }}
+          cmake .. -DCMAKE_CXX_FLAGS='/bigobj' -G Ninja -DCMAKE_C_COMPILER=cl.exe -DCMAKE_CXX_COMPILER=cl.exe -DCMAKE_BUILD_TYPE=Release ${{ matrix.defines }}
           cmake --build .
 
       - name: Check AVX512F support
@@ -371,6 +492,8 @@ jobs:
 
     needs:
       - ubuntu-latest-cmake
+      - ubuntu-latest-cmake-vulkan
+      - build-and-push-docker-images
       - macOS-latest-cmake
       - windows-latest-cmake
       - windows-latest-cmake-hip

CMakeLists.txt

@@ -8,6 +8,11 @@ if (NOT XCODE AND NOT MSVC AND NOT CMAKE_BUILD_TYPE)
     set_property(CACHE CMAKE_BUILD_TYPE PROPERTY STRINGS "Debug" "Release" "MinSizeRel" "RelWithDebInfo")
 endif()
 
+if (MSVC)
+    add_compile_definitions(_CRT_SECURE_NO_WARNINGS)
+    add_compile_definitions(_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING)
+endif()
+
 set(CMAKE_LIBRARY_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR}/bin)
 set(CMAKE_RUNTIME_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR}/bin)
 

Dockerfile

@@ -1,4 +1,4 @@
-ARG UBUNTU_VERSION=22.04
+ARG UBUNTU_VERSION=24.04
 
 FROM ubuntu:$UBUNTU_VERSION AS build
 
@@ -18,5 +18,6 @@ RUN apt-get update && \
     apt-get clean
 
 COPY --from=build /sd.cpp/build/bin/sd-cli /sd-cli
+COPY --from=build /sd.cpp/build/bin/sd-server /sd-server
 
 ENTRYPOINT [ "/sd-cli" ]

Dockerfile.musa

@@ -19,5 +19,6 @@ RUN mkdir build && cd build && \
 FROM mthreads/musa:${MUSA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}-amd64 as runtime
 
 COPY --from=build /sd.cpp/build/bin/sd-cli /sd-cli
+COPY --from=build /sd.cpp/build/bin/sd-server /sd-server
 
 ENTRYPOINT [ "/sd-cli" ]

Dockerfile.sycl

@@ -15,5 +15,6 @@ RUN mkdir build && cd build && \
 FROM intel/oneapi-basekit:${SYCL_VERSION}-devel-ubuntu24.04 AS runtime
 
 COPY --from=build /sd.cpp/build/bin/sd-cli /sd-cli
+COPY --from=build /sd.cpp/build/bin/sd-server /sd-server
 
 ENTRYPOINT [ "/sd-cli" ]

Dockerfile.vulkan

@@ -0,0 +1,23 @@
+ARG UBUNTU_VERSION=24.04
+
+FROM ubuntu:$UBUNTU_VERSION AS build
+
+RUN apt-get update && apt-get install -y --no-install-recommends build-essential git cmake libvulkan-dev glslc
+
+WORKDIR /sd.cpp
+
+COPY . .
+
+RUN cmake . -B ./build -DSD_VULKAN=ON
+RUN cmake --build ./build --config Release --parallel
+
+FROM ubuntu:$UBUNTU_VERSION AS runtime
+
+RUN apt-get update && \
+    apt-get install --yes --no-install-recommends libgomp1 libvulkan1 mesa-vulkan-drivers && \
+    apt-get clean
+
+COPY --from=build /sd.cpp/build/bin/sd-cli /sd-cli
+COPY --from=build /sd.cpp/build/bin/sd-server /sd-server
+
+ENTRYPOINT [ "/sd-cli" ]

README.md

@@ -70,7 +70,7 @@ API and command-line option may change frequently.***
   - SYCL
 - Supported weight formats
   - Pytorch checkpoint (`.ckpt` or `.pth`)
-  - Safetensors (`./safetensors`)
+  - Safetensors (`.safetensors`)
   - GGUF (`.gguf`)
 - Supported platforms
     - Linux

cache_dit.hpp

@@ -117,7 +117,7 @@ struct TaylorSeerState {
                 continue;
             if (o > 0)
                 factorial *= static_cast<float>(o);
-            float coeff = std::pow(static_cast<float>(elapsed), o) / factorial;
+            float coeff = ::powf(static_cast<float>(elapsed), static_cast<float>(o)) / factorial;
             for (size_t i = 0; i < size; i++) {
                 output[i] += coeff * dY_prev[o][i];
             }

clip.hpp

@@ -296,7 +296,7 @@ class CLIPTokenizer {
                     size_t max_length = 0,
                     bool padding      = false) {
         if (max_length > 0 && padding) {
-            size_t n = std::ceil(tokens.size() * 1.0 / (max_length - 2));
+            size_t n = static_cast<size_t>(std::ceil(tokens.size() * 1.0 / (max_length - 2)));
             if (n == 0) {
                 n = 1;
             }
@@ -525,10 +525,10 @@ struct CLIPLayer : public GGMLBlock {
 
 struct CLIPEncoder : public GGMLBlock {
 protected:
-    int64_t n_layer;
+    int n_layer;
 
 public:
-    CLIPEncoder(int64_t n_layer,
+    CLIPEncoder(int n_layer,
                 int64_t d_model,
                 int64_t n_head,
                 int64_t intermediate_size,
@@ -623,10 +623,10 @@ class CLIPEmbeddings : public GGMLBlock {
 class CLIPVisionEmbeddings : public GGMLBlock {
 protected:
     int64_t embed_dim;
-    int64_t num_channels;
-    int64_t patch_size;
-    int64_t image_size;
-    int64_t num_patches;
+    int num_channels;
+    int patch_size;
+    int image_size;
+    int num_patches;
     int64_t num_positions;
 
     void init_params(struct ggml_context* ctx, const String2TensorStorage& tensor_storage_map = {}, const std::string prefix = "") override {
@@ -641,9 +641,9 @@ class CLIPVisionEmbeddings : public GGMLBlock {
 
 public:
     CLIPVisionEmbeddings(int64_t embed_dim,
-                         int64_t num_channels = 3,
-                         int64_t patch_size   = 14,
-                         int64_t image_size   = 224)
+                         int num_channels = 3,
+                         int patch_size   = 14,
+                         int image_size   = 224)
         : embed_dim(embed_dim),
           num_channels(num_channels),
           patch_size(patch_size),