Merge llama into beellama 2

.devops/cann.Dockerfile

@@ -13,6 +13,20 @@ ARG APP_REVISION=N/A
 # BUILD STAGE
 # Compile all binary files and libraries
 # ==============================================================================
+ARG NODE_VERSION=24
+
+FROM docker.io/node:$NODE_VERSION AS web
+
+ARG APP_VERSION
+
+WORKDIR /app/tools/ui
+
+COPY tools/ui/package.json tools/ui/package-lock.json ./
+RUN npm ci
+
+COPY tools/ui/ ./
+RUN LLAMA_BUILD_NUMBER="$APP_VERSION" npm run build
+
 FROM ${CANN_BASE_IMAGE} AS build
 
 # -- Install build dependencies --
@@ -26,6 +40,8 @@ WORKDIR /app
 # -- Copy project files --
 COPY . .
 
+COPY --from=web /app/tools/ui/dist tools/ui/dist
+
 # -- Set CANN environment variables (required for compilation) --
 # Using ENV instead of `source` allows environment variables to persist across the entire image layer
 ENV ASCEND_TOOLKIT_HOME=/usr/local/Ascend/ascend-toolkit/latest
@@ -129,7 +145,7 @@ ENTRYPOINT ["/app/tools.sh"]
 # ==============================================================================
 FROM base AS light
 
-COPY --from=build /app/full/llama-cli /app/full/llama-completion /app
+COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app
 
 ENTRYPOINT [ "/app/llama-cli" ]
 
@@ -140,7 +156,7 @@ FROM base AS server
 
 ENV LLAMA_ARG_HOST=0.0.0.0
 
-COPY --from=build /app/full/llama-server /app
+COPY --from=build /app/full/llama /app/full/llama-server /app
 
 HEALTHCHECK --interval=5m CMD [ "curl", "-f", "http://localhost:8080/health" ]
 

.devops/cpu.Dockerfile

@@ -2,7 +2,21 @@
 
 ARG UBUNTU_VERSION=24.04
 
-FROM ubuntu:$UBUNTU_VERSION AS build
+ARG NODE_VERSION=24
+
+FROM docker.io/node:$NODE_VERSION AS web
+
+ARG APP_VERSION
+
+WORKDIR /app/tools/ui
+
+COPY tools/ui/package.json tools/ui/package-lock.json ./
+RUN npm ci
+
+COPY tools/ui/ ./
+RUN LLAMA_BUILD_NUMBER="$APP_VERSION" npm run build
+
+FROM docker.io/ubuntu:$UBUNTU_VERSION AS build
 
 ARG TARGETARCH
 
@@ -20,6 +34,11 @@ COPY . .
 RUN --mount=type=cache,target=/root/.ccache \
     if [ "$TARGETARCH" = "amd64" ] || [ "$TARGETARCH" = "arm64" ]; then \
         cmake -S . -B build -DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=OFF -DLLAMA_BUILD_TESTS=OFF -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DCMAKE_C_COMPILER_LAUNCHER=ccache -DCMAKE_CXX_COMPILER_LAUNCHER=ccache; \
+
+COPY --from=web /app/tools/ui/dist tools/ui/dist
+
+RUN if [ "$TARGETARCH" = "amd64" ] || [ "$TARGETARCH" = "arm64" ]; then \
+        cmake -S . -B build -DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=OFF -DLLAMA_BUILD_TESTS=OFF -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON; \
     else \
         echo "Unsupported architecture"; \
         exit 1; \
@@ -40,7 +59,7 @@ RUN mkdir -p /app/full \
     && cp .devops/tools.sh /app/full/tools.sh
 
 ## Base image
-FROM ubuntu:$UBUNTU_VERSION AS base
+FROM docker.io/ubuntu:$UBUNTU_VERSION AS base
 
 RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
     --mount=type=cache,target=/var/lib/apt/lists,sharing=locked \
@@ -63,6 +82,17 @@ LABEL org.opencontainers.image.created=$BUILD_DATE \
       org.opencontainers.image.url=$IMAGE_URL \
       org.opencontainers.image.source=$IMAGE_SOURCE
 
+
+RUN apt-get update \
+    && apt-get install -y libgomp1 curl ffmpeg \
+    && apt autoremove -y \
+    && apt clean -y \
+    && rm -rf /tmp/* /var/tmp/* \
+    && find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
+    && find /var/cache -type f -delete
+
+COPY --from=build /app/lib/ /app
+
 ### Full
 FROM base AS full
 
@@ -89,7 +119,7 @@ ENTRYPOINT ["/app/tools.sh"]
 ### Light, CLI only
 FROM base AS light
 
-COPY --from=build /app/full/llama-cli /app/full/llama-completion /app
+COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app
 
 WORKDIR /app
 
@@ -100,7 +130,7 @@ FROM base AS server
 
 ENV LLAMA_ARG_HOST=0.0.0.0
 
-COPY --from=build /app/full/llama-server /app
+COPY --from=build /app/full/llama /app/full/llama-server /app
 
 WORKDIR /app
 

.devops/cuda.Dockerfile

@@ -3,13 +3,36 @@
 ARG UBUNTU_VERSION=22.04
 # This needs to generally match the container host's environment.
 ARG CUDA_VERSION=12.4.1
+
+ARG CUDA_VERSION=12.8.1
+ARG GCC_VERSION=14
 # Target the CUDA build image
-ARG BASE_CUDA_DEV_CONTAINER=nvidia/cuda:${CUDA_VERSION}-devel-ubuntu${UBUNTU_VERSION}
+ARG BASE_CUDA_DEV_CONTAINER=docker.io/nvidia/cuda:${CUDA_VERSION}-devel-ubuntu${UBUNTU_VERSION}
+
+ARG BASE_CUDA_RUN_CONTAINER=docker.io/nvidia/cuda:${CUDA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}
+
+
+ARG BUILD_DATE=N/A
+ARG APP_VERSION=N/A
+ARG APP_REVISION=N/A
 
-ARG BASE_CUDA_RUN_CONTAINER=nvidia/cuda:${CUDA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}
+ARG NODE_VERSION=24
+
+FROM docker.io/node:$NODE_VERSION AS web
+
+ARG APP_VERSION
+
+WORKDIR /app/tools/ui
+
+COPY tools/ui/package.json tools/ui/package-lock.json ./
+RUN npm ci
+
+COPY tools/ui/ ./
+RUN LLAMA_BUILD_NUMBER="$APP_VERSION" npm run build
 
 FROM ${BASE_CUDA_DEV_CONTAINER} AS build
 
+ARG GCC_VERSION
 # CUDA architecture to build for (defaults to all supported archs)
 ARG CUDA_DOCKER_ARCH=default
 # CMake target to build. Keep "all" for full/local images; CI server images set this to llama-server.
@@ -22,12 +45,21 @@ RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
 
 ENV CC=gcc CXX=g++ CUDAHOSTCXX=g++ CCACHE_SLOPPINESS=time_macros CCACHE_MAXSIZE=5G
 
+RUN apt-get update && \
+    apt-get install -y gcc-${GCC_VERSION} g++-${GCC_VERSION} build-essential cmake python3 python3-pip git libssl-dev libgomp1
+
+ENV CC=gcc-${GCC_VERSION} CXX=g++-${GCC_VERSION} CUDAHOSTCXX=g++-${GCC_VERSION}
+
 WORKDIR /app
 
 COPY . .
 
 RUN --mount=type=cache,target=/root/.ccache \
     if [ "${CUDA_DOCKER_ARCH}" != "default" ]; then \
+
+COPY --from=web /app/tools/ui/dist tools/ui/dist
+
+RUN if [ "${CUDA_DOCKER_ARCH}" != "default" ]; then \
     export CMAKE_ARGS="-DCMAKE_CUDA_ARCHITECTURES=${CUDA_DOCKER_ARCH}"; \
     fi && \
     cmake -S . -B build -G Ninja \
@@ -86,6 +118,17 @@ LABEL org.opencontainers.image.created=$BUILD_DATE \
       org.opencontainers.image.url=$IMAGE_URL \
       org.opencontainers.image.source=$IMAGE_SOURCE
 
+
+RUN apt-get update \
+    && apt-get install -y libgomp1 curl ffmpeg \
+    && apt autoremove -y \
+    && apt clean -y \
+    && rm -rf /tmp/* /var/tmp/* \
+    && find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
+    && find /var/cache -type f -delete
+
+COPY --from=build /app/lib/ /app
+
 ### Full
 FROM base AS full
 
@@ -113,7 +156,7 @@ ENTRYPOINT ["/app/tools.sh"]
 ### Light, CLI only
 FROM base AS light
 
-COPY --from=build /app/full/llama-cli /app/full/llama-completion /app
+COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app
 
 WORKDIR /app
 
@@ -124,7 +167,7 @@ FROM base AS server
 
 ENV LLAMA_ARG_HOST=0.0.0.0
 
-COPY --from=build /app/full/llama-server /app
+COPY --from=build /app/full/llama /app/full/llama-server /app
 
 WORKDIR /app
 

.devops/intel.Dockerfile

@@ -4,10 +4,26 @@ ARG ONEAPI_VERSION=2025.3.3-0-devel-ubuntu24.04
 
 ## Build Image
 
-FROM intel/deep-learning-essentials:$ONEAPI_VERSION AS build
+ARG NODE_VERSION=24
 
 ARG GGML_SYCL_F16=OFF
 ARG SYCL_BUILD_TARGET=all
+
+FROM docker.io/node:$NODE_VERSION AS web
+
+ARG APP_VERSION
+
+WORKDIR /app/tools/ui
+
+COPY tools/ui/package.json tools/ui/package-lock.json ./
+RUN npm ci
+
+COPY tools/ui/ ./
+RUN LLAMA_BUILD_NUMBER="$APP_VERSION" npm run build
+
+FROM docker.io/intel/deep-learning-essentials:$ONEAPI_VERSION AS build
+
+ARG GGML_SYCL_F16=ON
 ARG LEVEL_ZERO_VERSION=1.28.2
 ARG LEVEL_ZERO_UBUNTU_VERSION=u24.04
 RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
@@ -28,8 +44,13 @@ COPY . .
 
 RUN --mount=type=cache,target=/root/.ccache \
     if [ "${GGML_SYCL_F16}" = "ON" ]; then \
+
+COPY --from=web /app/tools/ui/dist tools/ui/dist
+
+RUN if [ "${GGML_SYCL_F16}" = "ON" ]; then \
         echo "GGML_SYCL_F16 is set" \
-        && export OPT_SYCL_F16="-DGGML_SYCL_F16=ON"; \
+        && export OPT_SYCL_F16="-DGGML_SYCL_F16=ON" \
+        && export SYCL_PROGRAM_COMPILE_OPTIONS="-cl-fp32-correctly-rounded-divide-sqrt"; \
     fi && \
     echo "Building with dynamic libs" && \
     cmake -B build \
@@ -63,13 +84,42 @@ RUN mkdir -p /app/full \
     && cp requirements.txt /app/full \
     && cp .devops/tools.sh /app/full/tools.sh
 
-FROM intel/deep-learning-essentials:$ONEAPI_VERSION AS base
+FROM docker.io/intel/deep-learning-essentials:$ONEAPI_VERSION AS base
 
 ARG IGC_VERSION=v2.20.5
 ARG IGC_VERSION_FULL=2_2.20.5+19972
 ARG COMPUTE_RUNTIME_VERSION=25.40.35563.10
 ARG COMPUTE_RUNTIME_VERSION_FULL=25.40.35563.10-0
 ARG IGDGMM_VERSION=22.8.2
+
+ARG BUILD_DATE=N/A
+ARG APP_VERSION=N/A
+ARG APP_REVISION=N/A
+ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp
+ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp
+LABEL org.opencontainers.image.created=$BUILD_DATE \
+      org.opencontainers.image.version=$APP_VERSION \
+      org.opencontainers.image.revision=$APP_REVISION \
+      org.opencontainers.image.title="llama.cpp" \
+      org.opencontainers.image.description="LLM inference in C/C++" \
+      org.opencontainers.image.url=$IMAGE_URL \
+      org.opencontainers.image.source=$IMAGE_SOURCE
+
+#Following versions are for multiple GPUs, since 26.x has known issue:
+#   https://github.com/ggml-org/llama.cpp/issues/21747,
+#   https://github.com/intel/compute-runtime/issues/921.
+#ARG IGC_VERSION=v2.20.5
+#ARG IGC_VERSION_FULL=2_2.20.5+19972
+#ARG COMPUTE_RUNTIME_VERSION=25.40.35563.10
+#ARG COMPUTE_RUNTIME_VERSION_FULL=25.40.35563.10-0
+#ARG IGDGMM_VERSION=22.8.2
+
+
+ARG IGC_VERSION=v2.34.4
+ARG IGC_VERSION_FULL=2_2.34.4+21428
+ARG COMPUTE_RUNTIME_VERSION=26.18.38308.1
+ARG COMPUTE_RUNTIME_VERSION_FULL=26.18.38308.1-0
+ARG IGDGMM_VERSION=22.10.0
 RUN mkdir /tmp/neo/ && cd /tmp/neo/ \
   && wget https://github.com/intel/intel-graphics-compiler/releases/download/$IGC_VERSION/intel-igc-core-${IGC_VERSION_FULL}_amd64.deb \
   && wget https://github.com/intel/intel-graphics-compiler/releases/download/$IGC_VERSION/intel-igc-opencl-${IGC_VERSION_FULL}_amd64.deb \
@@ -101,6 +151,14 @@ LABEL org.opencontainers.image.created=$BUILD_DATE \
       org.opencontainers.image.url=$IMAGE_URL \
       org.opencontainers.image.source=$IMAGE_SOURCE
 
+RUN apt-get update \
+    && apt-get install -y libgomp1 curl ffmpeg \
+    && apt autoremove -y \
+    && apt clean -y \
+    && rm -rf /tmp/* /var/tmp/* \
+    && find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
+    && find /var/cache -type f -delete
+
 ### Full
 FROM base AS full
 
@@ -133,7 +191,7 @@ ENTRYPOINT ["/app/tools.sh"]
 FROM base AS light
 
 COPY --from=build /app/lib/ /app
-COPY --from=build /app/full/llama-cli /app/full/llama-completion /app
+COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app
 
 WORKDIR /app
 
@@ -145,7 +203,7 @@ FROM base AS server
 ENV LLAMA_ARG_HOST=0.0.0.0
 
 COPY --from=build /app/lib/ /app
-COPY --from=build /app/full/llama-server /app
+COPY --from=build /app/full/llama /app/full/llama-server /app
 
 WORKDIR /app
 

.devops/llama-cli-cann.Dockerfile

@@ -3,7 +3,7 @@ ARG BUILD_DATE=N/A
 ARG APP_VERSION=N/A
 ARG APP_REVISION=N/A
 
-FROM ascendai/cann:$ASCEND_VERSION AS build
+FROM docker.io/ascendai/cann:$ASCEND_VERSION AS build
 
 WORKDIR /app
 
@@ -30,7 +30,7 @@ RUN echo "Building with static libs" && \
     cmake --build build --config Release --target llama-completion
 
 # TODO: use image with NNRT
-FROM ascendai/cann:$ASCEND_VERSION AS runtime
+FROM docker.io/ascendai/cann:$ASCEND_VERSION AS runtime
 
 ARG BUILD_DATE=N/A
 ARG APP_VERSION=N/A