Merge pull request #724 from cgruver/add-intel-gpu

Add logic to build intel-gpu image to build_llama_and_whisper.sh

container-images/intel-gpu/Containerfile

@@ -1,32 +1,24 @@
 FROM quay.io/fedora/fedora:41 as builder
 
 COPY intel-gpu/oneAPI.repo /etc/yum.repos.d/
+COPY scripts/build_llama_and_whisper.sh /
 
-RUN dnf install -y intel-opencl g++ cmake git tar libcurl-devel intel-oneapi-mkl-sycl-devel intel-oneapi-dnnl-devel intel-oneapi-compiler-dpcpp-cpp ; \
-    git clone https://github.com/ggerganov/llama.cpp.git -b b4523 ; \
-    cd llama.cpp ; \
-    mkdir -p build ; \
-    cd build ; \
-    source /opt/intel/oneapi/setvars.sh ; \
-    cmake .. -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_CURL=ON -DGGML_CCACHE=OFF -DGGML_NATIVE=OFF ; \
-    cmake --build . --config Release -j -v ; \
-    cmake --install . --prefix /llama-cpp
+RUN chmod +x /build_llama_and_whisper.sh ; \
+    /build_llama_and_whisper.sh intel-gpu
 
 FROM quay.io/fedora/fedora:41
 
-ENV LD_LIBRARY_PATH="/usr/local/lib64:/usr/local/lib/:/opt/intel/oneapi/mkl/2025.0/lib:/opt/intel/oneapi/compiler/2025.0/opt/compiler/lib:/opt/intel/oneapi/compiler/2025.0/lib/clang/19/lib:/opt/intel/oneapi/compiler/2025.0/lib:/opt/intel/oneapi/umf/0.9/lib:/opt/intel/oneapi/tbb/2022.0/lib:/opt/intel/oneapi/tcm/1.2/lib:/opt/intel/oneapi/redist/opt/compiler/lib:/opt/intel/oneapi/redist/lib/clang/19/lib:/opt/intel/oneapi/redist/lib:/opt/intel/oneapi/mkl/2025.0/lib:/opt/intel/oneapi/compiler/2025.0/opt/compiler/lib:/opt/intel/oneapi/compiler/2025.0/lib/clang/19/lib:/opt/intel/oneapi/compiler/2025.0/lib:/opt/intel/oneapi/umf/0.9/lib:/opt/intel/oneapi/tbb/2022.0/lib:/opt/intel/oneapi/tcm/1.2/lib:/opt/intel/oneapi/redist/opt/compiler/lib:/opt/intel/oneapi/redist/lib/clang/19/lib:/opt/intel/oneapi/redist/lib"
-
-COPY --from=builder /llama-cpp/bin/ /usr/local/bin/
-COPY --from=builder /llama-cpp/lib/ /usr/local/lib/
-COPY --from=builder /llama-cpp/lib64/ /usr/local/lib64/
-COPY --from=builder /llama-cpp/include/ /usr/local/include/
+COPY --from=builder /tmp/install/ /usr/
 COPY intel-gpu/oneAPI.repo /etc/yum.repos.d/
+COPY --chown=0:0 intel-gpu/entrypoint.sh /
 
-RUN dnf install -y intel-opencl libcurl lspci clinfo intel-oneapi-runtime-compilers intel-oneapi-mkl-core intel-oneapi-mkl-sycl-blas intel-oneapi-runtime-dnnl ; \
+RUN dnf install -y procps-ng python3 python3-pip python3-devel intel-level-zero oneapi-level-zero intel-compute-runtime libcurl lspci clinfo intel-oneapi-runtime-compilers intel-oneapi-mkl-core intel-oneapi-mkl-sycl-blas intel-oneapi-runtime-dnnl ; \
     chown 0:0 /etc/passwd ; \
     chown 0:0 /etc/group ; \
-    chmod g=u /etc/passwd /etc/group ; \
-    useradd -u 1000 -g render -G video -s /bin/bash -d /home/llama-user llama-user
+    chmod g=u /etc/passwd /etc/group /home ; \
+    chmod +x /entrypoint.sh
+
+USER 10000
 
-USER 1000
-WORKDIR /home/llama-user
+ENTRYPOINT ["/entrypoint.sh"]
+CMD [ "tail", "-f", "/dev/null" ]

container-images/intel-gpu/entrypoint.sh

@@ -0,0 +1,46 @@
+#!/usr/bin/env bash
+
+if [ -z ${HOME} ]
+then
+  export HOME=/home/llama-user
+fi
+
+# Create Home directory
+if [ ! -d "${HOME}" ]
+then
+  mkdir -p "${HOME}"
+fi
+
+# Create User ID
+if ! whoami &> /dev/null
+then
+  if [ -w /etc/passwd ] && [ -w /etc/group ]
+  then
+    echo "${USER_NAME:-llama-user}:x:$(id -u):0:${USER_NAME:-llama-user} user:${HOME}:/bin/bash" >> /etc/passwd
+    echo "${USER_NAME:-llama-user}:x:$(id -u):" >> /etc/group
+    render_group="$(cat /etc/group | grep 'render:x')"
+    video_group="$(cat /etc/group | grep 'video:x')"
+    render_group_new="${render_group}${USER_NAME:-llama-user}"
+    video_group_new="${video_group}${USER_NAME:-llama-user}"
+    sed "s|${render_group}|${render_group_new}|g" /etc/group > /tmp/group
+    cat /tmp/group > /etc/group
+    sed "s|${video_group}|${video_group_new}|g" /etc/group > /tmp/group
+    cat /tmp/group > /etc/group
+  fi
+fi
+
+# Configure Z shell
+if [ ! -f ${HOME}/.zshrc ]
+then
+  (echo "source /opt/intel/oneapi/setvars.sh") > ${HOME}/.zshrc
+fi
+
+# Configure Bash shell
+if [ ! -f ${HOME}/.bashrc ]
+then
+  (echo "source /opt/intel/oneapi/setvars.sh") > ${HOME}/.bashrc
+fi
+
+source /opt/intel/oneapi/setvars.sh
+
+exec "$@"

container-images/scripts/build_llama_and_whisper.sh

@@ -6,6 +6,9 @@ dnf_install() {
                   "procps-ng" "git" "dnf-plugins-core" "libcurl-devel")
   local vulkan_rpms=("vulkan-headers" "vulkan-loader-devel" "vulkan-tools" \
                      "spirv-tools" "glslc" "glslang")
+  local intel_rpms=("intel-oneapi-mkl-sycl-devel" "intel-oneapi-dnnl-devel" \
+                  "intel-oneapi-compiler-dpcpp-cpp" "intel-level-zero" \
+                  "oneapi-level-zero" "oneapi-level-zero-devel" "intel-compute-runtime")
 
   # All the UBI-based ones
   if [ "$containerfile" = "ramalama" ] || [ "$containerfile" = "rocm" ] || \
@@ -37,6 +40,11 @@ dnf_install() {
     # shellcheck disable=SC1091
     . /opt/rh/gcc-toolset-12/enable
   fi
+
+  if [ "$containerfile" = "intel-gpu" ]; then
+    dnf install -y "${rpm_list[@]}" "${intel_rpms[@]}"
+    source /opt/intel/oneapi/setvars.sh
+  fi
 }
 
 cmake_check_warnings() {
@@ -51,7 +59,7 @@ cmake_steps() {
 }
 
 set_install_prefix() {
-  if [ "$containerfile" = "cuda" ]; then
+  if [ "$containerfile" = "cuda" ] || [ "$containerfile" = "intel-gpu" ]; then
     install_prefix="/tmp/install"
   else
     install_prefix="/usr"
@@ -70,6 +78,9 @@ configure_common_flags() {
     vulkan | asahi)
       common_flags+=("-DGGML_VULKAN=1")
       ;;
+    intel-gpu)
+      common_flags+=("-DGGML_SYCL=ON" "-DCMAKE_C_COMPILER=icx" "-DCMAKE_CXX_COMPILER=icpx")
+      ;;
   esac
 }