Skip to content

⬆️ Update ggerganov/llama.cpp (#2696) #5455

⬆️ Update ggerganov/llama.cpp (#2696)

⬆️ Update ggerganov/llama.cpp (#2696) #5455

Workflow file for this run

name: Build and Release
on:
- push
- pull_request
env:
GRPC_VERSION: v1.64.0
permissions:
contents: write
concurrency:
group: ci-releases-${{ github.head_ref || github.ref }}-${{ github.repository }}
cancel-in-progress: true
jobs:
build-linux-arm:
runs-on: ubuntu-latest
steps:
- name: Clone
uses: actions/checkout@v4
with:
submodules: true
- uses: actions/setup-go@v5
with:
go-version: '1.21.x'
cache: false
- name: Dependencies
run: |
sudo apt-get update
sudo apt-get install build-essential ffmpeg protobuf-compiler ccache
sudo apt-get install -qy binutils-aarch64-linux-gnu gcc-aarch64-linux-gnu g++-aarch64-linux-gnu
- name: Install CUDA Dependencies
run: |
curl -O https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/cross-linux-aarch64/cuda-keyring_1.1-1_all.deb
sudo dpkg -i cuda-keyring_1.1-1_all.deb
sudo apt-get update
sudo apt-get install -y cuda-cross-aarch64 cuda-nvcc-cross-aarch64-${CUDA_VERSION} libcublas-cross-aarch64-${CUDA_VERSION}
env:
CUDA_VERSION: 12-5
- name: Cache grpc
id: cache-grpc
uses: actions/cache@v4
with:
path: grpc
key: ${{ runner.os }}-arm-grpc-${{ env.GRPC_VERSION }}
- name: Build grpc
if: steps.cache-grpc.outputs.cache-hit != 'true'
run: |
git clone --recurse-submodules -b ${{ env.GRPC_VERSION }} --depth 1 --shallow-submodules https://github.com/grpc/grpc && \
cd grpc && mkdir -p cmake/build && cd cmake/build && cmake -DgRPC_INSTALL=ON \
-DgRPC_BUILD_TESTS=OFF \
../.. && sudo make --jobs 5 --output-sync=target
- name: Install gRPC
run: |
GNU_HOST=aarch64-linux-gnu
C_COMPILER_ARM_LINUX=$GNU_HOST-gcc
CXX_COMPILER_ARM_LINUX=$GNU_HOST-g++
CROSS_TOOLCHAIN=/usr/$GNU_HOST
CROSS_STAGING_PREFIX=$CROSS_TOOLCHAIN/stage
CMAKE_CROSS_TOOLCHAIN=/tmp/arm.toolchain.cmake
# https://cmake.org/cmake/help/v3.13/manual/cmake-toolchains.7.html#cross-compiling-for-linux
echo "set(CMAKE_SYSTEM_NAME Linux)" >> $CMAKE_CROSS_TOOLCHAIN && \
echo "set(CMAKE_SYSTEM_PROCESSOR arm)" >> $CMAKE_CROSS_TOOLCHAIN && \
echo "set(CMAKE_STAGING_PREFIX $CROSS_STAGING_PREFIX)" >> $CMAKE_CROSS_TOOLCHAIN && \
echo "set(CMAKE_SYSROOT ${CROSS_TOOLCHAIN}/sysroot)" >> $CMAKE_CROSS_TOOLCHAIN && \
echo "set(CMAKE_C_COMPILER /usr/bin/$C_COMPILER_ARM_LINUX)" >> $CMAKE_CROSS_TOOLCHAIN && \
echo "set(CMAKE_CXX_COMPILER /usr/bin/$CXX_COMPILER_ARM_LINUX)" >> $CMAKE_CROSS_TOOLCHAIN && \
echo "set(CMAKE_FIND_ROOT_PATH_MODE_PROGRAM NEVER)" >> $CMAKE_CROSS_TOOLCHAIN && \
echo "set(CMAKE_FIND_ROOT_PATH_MODE_LIBRARY ONLY)" >> $CMAKE_CROSS_TOOLCHAIN && \
echo "set(CMAKE_FIND_ROOT_PATH_MODE_INCLUDE ONLY)" >> $CMAKE_CROSS_TOOLCHAIN && \
echo "set(CMAKE_FIND_ROOT_PATH_MODE_PACKAGE ONLY)" >> $CMAKE_CROSS_TOOLCHAIN
GRPC_DIR=$PWD/grpc
cd grpc && cd cmake/build && sudo make --jobs 5 --output-sync=target install && \
GRPC_CROSS_BUILD_DIR=$GRPC_DIR/cmake/cross_build && \
mkdir -p $GRPC_CROSS_BUILD_DIR && \
cd $GRPC_CROSS_BUILD_DIR && \
cmake -DCMAKE_TOOLCHAIN_FILE=$CMAKE_CROSS_TOOLCHAIN \
-DCMAKE_BUILD_TYPE=Release \
-DCMAKE_INSTALL_PREFIX=$CROSS_TOOLCHAIN/grpc_install \
../.. && \
sudo make -j`nproc` install
- name: Build
id: build
run: |
GNU_HOST=aarch64-linux-gnu
C_COMPILER_ARM_LINUX=$GNU_HOST-gcc
CXX_COMPILER_ARM_LINUX=$GNU_HOST-g++
CROSS_TOOLCHAIN=/usr/$GNU_HOST
CROSS_STAGING_PREFIX=$CROSS_TOOLCHAIN/stage
CMAKE_CROSS_TOOLCHAIN=/tmp/arm.toolchain.cmake
go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@8ba23be9613c672d40ae261d2a1335d639bdd59b
go install google.golang.org/protobuf/cmd/[email protected]
export PATH=$PATH:$GOPATH/bin
export PATH=/usr/local/cuda/bin:$PATH
sudo rm -rf /usr/aarch64-linux-gnu/lib/libstdc++.so.6
sudo cp -rf /usr/aarch64-linux-gnu/lib/libstdc++.so* /usr/aarch64-linux-gnu/lib/libstdc++.so.6
sudo cp /usr/aarch64-linux-gnu/lib/ld-linux-aarch64.so.1 ld.so
GO_TAGS=p2p \
BACKEND_LIBS="./grpc/cmake/cross_build/third_party/re2/libre2.a ./grpc/cmake/cross_build/libgrpc.a ./grpc/cmake/cross_build/libgrpc++.a ./grpc/cmake/cross_build/third_party/protobuf/libprotobuf.a /usr/aarch64-linux-gnu/lib/libc.so.6 /usr/aarch64-linux-gnu/lib/libstdc++.so.6 /usr/aarch64-linux-gnu/lib/libgomp.so.1 /usr/aarch64-linux-gnu/lib/libm.so.6 /usr/aarch64-linux-gnu/lib/libgcc_s.so.1 /usr/aarch64-linux-gnu/lib/libdl.so.2 /usr/aarch64-linux-gnu/lib/libpthread.so.0 ./ld.so" \
GOOS=linux \
GOARCH=arm64 \
CMAKE_ARGS="-DProtobuf_INCLUDE_DIRS=$CROSS_STAGING_PREFIX/include -DProtobuf_DIR=$CROSS_STAGING_PREFIX/lib/cmake/protobuf -DgRPC_DIR=$CROSS_STAGING_PREFIX/lib/cmake/grpc -DCMAKE_TOOLCHAIN_FILE=$CMAKE_CROSS_TOOLCHAIN -DCMAKE_C_COMPILER=aarch64-linux-gnu-gcc -DCMAKE_CXX_COMPILER=aarch64-linux-gnu-g++" make dist-cross-linux-arm64
- uses: actions/upload-artifact@v4
with:
name: LocalAI-linux-arm64
path: release/
- name: Release
uses: softprops/action-gh-release@v2
if: startsWith(github.ref, 'refs/tags/')
with:
files: |
release/*
- name: Setup tmate session if tests fail
if: ${{ failure() }}
uses: mxschmitt/[email protected]
with:
detached: true
connect-timeout-seconds: 180
limit-access-to-actor: true
build-linux:
runs-on: arc-runner-set
steps:
- name: Force Install GIT latest
run: |
sudo apt-get update \
&& sudo apt-get install -y software-properties-common \
&& sudo apt-get update \
&& sudo add-apt-repository -y ppa:git-core/ppa \
&& sudo apt-get update \
&& sudo apt-get install -y git
- name: Clone
uses: actions/checkout@v4
with:
submodules: true
- uses: actions/setup-go@v5
with:
go-version: '1.21.x'
cache: false
- name: Dependencies
run: |
sudo apt-get update
sudo apt-get install -y wget curl build-essential ffmpeg protobuf-compiler ccache cmake
- name: Intel Dependencies
run: |
wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB | gpg --dearmor | sudo tee /usr/share/keyrings/oneapi-archive-keyring.gpg > /dev/null
echo "deb [signed-by=/usr/share/keyrings/oneapi-archive-keyring.gpg] https://apt.repos.intel.com/oneapi all main" | sudo tee /etc/apt/sources.list.d/oneAPI.list
sudo apt update
sudo apt install -y intel-basekit
- name: Install CUDA Dependencies
run: |
curl -O https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.1-1_all.deb
sudo dpkg -i cuda-keyring_1.1-1_all.deb
sudo apt-get update
sudo apt-get install -y cuda-nvcc-${CUDA_VERSION} libcublas-dev-${CUDA_VERSION}
env:
CUDA_VERSION: 12-3
- name: "Install Hipblas"
env:
ROCM_VERSION: "6.1"
AMDGPU_VERSION: "6.1"
run: |
set -ex
sudo apt-get update
sudo DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends ca-certificates curl libnuma-dev gnupg
curl -sL https://repo.radeon.com/rocm/rocm.gpg.key | sudo apt-key add -
printf "deb [arch=amd64] https://repo.radeon.com/rocm/apt/$ROCM_VERSION/ jammy main" | sudo tee /etc/apt/sources.list.d/rocm.list
printf "deb [arch=amd64] https://repo.radeon.com/amdgpu/$AMDGPU_VERSION/ubuntu jammy main" | sudo tee /etc/apt/sources.list.d/amdgpu.list
printf 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600' | sudo tee /etc/apt/preferences.d/rocm-pin-600
sudo apt-get update
sudo DEBIAN_FRONTEND=noninteractive apt-get install -y \
hipblas-dev rocm-dev \
rocblas-dev
sudo apt-get clean
sudo rm -rf /var/lib/apt/lists/*
sudo ldconfig
- name: Cache grpc
id: cache-grpc
uses: actions/cache@v4
with:
path: grpc
key: ${{ runner.os }}-grpc-${{ env.GRPC_VERSION }}
- name: Build grpc
if: steps.cache-grpc.outputs.cache-hit != 'true'
run: |
git clone --recurse-submodules -b ${{ env.GRPC_VERSION }} --depth 1 --shallow-submodules https://github.com/grpc/grpc && \
cd grpc && mkdir -p cmake/build && cd cmake/build && cmake -DgRPC_INSTALL=ON \
-DgRPC_BUILD_TESTS=OFF \
../.. && sudo make --jobs 5 --output-sync=target
- name: Install gRPC
run: |
cd grpc && cd cmake/build && sudo make --jobs 5 --output-sync=target install
# BACKEND_LIBS needed for gpu-workload: /opt/intel/oneapi/*/lib/libiomp5.so /opt/intel/oneapi/*/lib/libmkl_core.so /opt/intel/oneapi/*/lib/libmkl_core.so.2 /opt/intel/oneapi/*/lib/libmkl_intel_ilp64.so /opt/intel/oneapi/*/lib/libmkl_intel_ilp64.so.2 /opt/intel/oneapi/*/lib/libmkl_sycl_blas.so /opt/intel/oneapi/*/lib/libmkl_sycl_blas.so.4 /opt/intel/oneapi/*/lib/libmkl_tbb_thread.so /opt/intel/oneapi/*/lib/libmkl_tbb_thread.so.2 /opt/intel/oneapi/*/lib/libsycl.so /opt/intel/oneapi/*/lib/libsycl.so.7 /opt/intel/oneapi/*/lib/libsycl.so.7.1.0 /opt/rocm-*/lib/libamdhip64.so /opt/rocm-*/lib/libamdhip64.so.5 /opt/rocm-*/lib/libamdhip64.so.6 /opt/rocm-*/lib/libamdhip64.so.6.1.60100 /opt/rocm-*/lib/libhipblas.so /opt/rocm-*/lib/libhipblas.so.2 /opt/rocm-*/lib/libhipblas.so.2.1.60100 /opt/rocm-*/lib/librocblas.so /opt/rocm-*/lib/librocblas.so.4 /opt/rocm-*/lib/librocblas.so.4.1.60100 /usr/lib/x86_64-linux-gnu/libstdc++.so.6 /usr/lib/x86_64-linux-gnu/libOpenCL.so.1 /usr/lib/x86_64-linux-gnu/libOpenCL.so.1.0.0 /usr/lib/x86_64-linux-gnu/libm.so.6 /usr/lib/x86_64-linux-gnu/libgcc_s.so.1 /usr/lib/x86_64-linux-gnu/libc.so.6 /usr/lib/x86_64-linux-gnu/librt.so.1 /usr/local/cuda-*/targets/x86_64-linux/lib/libcublas.so /usr/local/cuda-*/targets/x86_64-linux/lib/libcublasLt.so /usr/local/cuda-*/targets/x86_64-linux/lib/libcudart.so /usr/local/cuda-*/targets/x86_64-linux/lib/stubs/libcuda.so
- name: Build
id: build
run: |
go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@8ba23be9613c672d40ae261d2a1335d639bdd59b
go install google.golang.org/protobuf/cmd/[email protected]
export PATH=$PATH:$GOPATH/bin
export PATH=/usr/local/cuda/bin:$PATH
export PATH=/opt/rocm/bin:$PATH
source /opt/intel/oneapi/setvars.sh
sudo cp /lib64/ld-linux-x86-64.so.2 ld.so
GO_TAGS=p2p \
BACKEND_LIBS="./ld.so /usr/lib/x86_64-linux-gnu/libstdc++.so.6 /usr/lib/x86_64-linux-gnu/libm.so.6 /usr/lib/x86_64-linux-gnu/libgcc_s.so.1 /usr/lib/x86_64-linux-gnu/libc.so.6 /usr/lib/x86_64-linux-gnu/libgomp.so.1" \
make -j4 dist
- uses: actions/upload-artifact@v4
with:
name: LocalAI-linux
path: release/
- name: Release
uses: softprops/action-gh-release@v2
if: startsWith(github.ref, 'refs/tags/')
with:
files: |
release/*
- name: Setup tmate session if tests fail
if: ${{ failure() }}
uses: mxschmitt/[email protected]
with:
detached: true
connect-timeout-seconds: 180
limit-access-to-actor: true
build-stablediffusion:
runs-on: ubuntu-latest
steps:
- name: Clone
uses: actions/checkout@v4
with:
submodules: true
- uses: actions/setup-go@v5
with:
go-version: '1.21.x'
cache: false
- name: Dependencies
run: |
sudo apt-get update
sudo apt-get install -y --no-install-recommends libopencv-dev protobuf-compiler ccache
go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@8ba23be9613c672d40ae261d2a1335d639bdd59b
go install google.golang.org/protobuf/cmd/[email protected]
- name: Build stablediffusion
run: |
export PATH=$PATH:$GOPATH/bin
make backend-assets/grpc/stablediffusion
mkdir -p release && cp backend-assets/grpc/stablediffusion release
env:
GO_TAGS: stablediffusion
- uses: actions/upload-artifact@v4
with:
name: stablediffusion
path: release/
- name: Release
uses: softprops/action-gh-release@v2
if: startsWith(github.ref, 'refs/tags/')
with:
files: |
release/*
build-macOS-arm64:
runs-on: macos-14
steps:
- name: Clone
uses: actions/checkout@v4
with:
submodules: true
- uses: actions/setup-go@v5
with:
go-version: '1.21.x'
cache: false
- name: Dependencies
run: |
brew install protobuf grpc
go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@8ba23be9613c672d40ae261d2a1335d639bdd59b
go install google.golang.org/protobuf/cmd/[email protected]
- name: Build
id: build
run: |
export C_INCLUDE_PATH=/usr/local/include
export CPLUS_INCLUDE_PATH=/usr/local/include
export PATH=$PATH:$GOPATH/bin
BACKEND_LIBS="$(ls /opt/homebrew/opt/grpc/lib/*.dylib /opt/homebrew/opt/re2/lib/*.dylib /opt/homebrew/opt/openssl@3/lib/*.dylib /opt/homebrew/opt/protobuf/lib/*.dylib /opt/homebrew/opt/abseil/lib/*.dylib | xargs)" GO_TAGS=p2p make dist
- uses: actions/upload-artifact@v4
with:
name: LocalAI-MacOS-arm64
path: release/
- name: Release
uses: softprops/action-gh-release@v2
if: startsWith(github.ref, 'refs/tags/')
with:
files: |
release/*
- name: Setup tmate session if tests fail
if: ${{ failure() }}
uses: mxschmitt/[email protected]
with:
detached: true
connect-timeout-seconds: 180
limit-access-to-actor: true