vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

release : pack /lib in the packages (#11392)

Browse source 
* release : pack /lib and /include in the packages

* cmake : put libs in /bin

* TMP : push artifacts

* Revert "TMP : push artifacts"

This reverts commit 4decf2c4df.

* ci : fix HIP cmake compiler options to be on first line

* ci : restore the original HIP commands

* ci : change ubuntu build from latest to 20.04

* ci : try to fix macos build rpaths

* ci : remove obsolete MacOS build

* TMP : push artifacts

* ci : change back to ubuntu latest

* ci : macos set build rpath to "@loader_path"

* ci : fix typo

* ci : change ubuntu package to 22.04

* Revert "TMP : push artifacts"

This reverts commit 537b09e70f.
This commit is contained in:
Georgi Gerganov 2025-01-24 18:41:30 +02:00 • committed by GitHub
parent a07c2c8a52
commit 9755129c27
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 53 additions and 49 deletions
Download patch file Download diff file Expand all files Collapse all files

101
.github/workflows/build.yml vendored
View file

@ -56,6 +56,7 @@ jobs:
mkdir build mkdir build
cd build cd build
cmake .. \ cmake .. \
-DCMAKE_BUILD_RPATH="@loader_path" \
-DLLAMA_FATAL_WARNINGS=ON \ -DLLAMA_FATAL_WARNINGS=ON \
-DLLAMA_CURL=ON \ -DLLAMA_CURL=ON \
-DGGML_METAL_USE_BF16=ON \ -DGGML_METAL_USE_BF16=ON \
@ -120,6 +121,7 @@ jobs:
# Metal is disabled due to intermittent failures with Github runners not having a GPU: # Metal is disabled due to intermittent failures with Github runners not having a GPU:
# https://github.com/ggerganov/llama.cpp/actions/runs/8635935781/job/23674807267#step:5:2313 # https://github.com/ggerganov/llama.cpp/actions/runs/8635935781/job/23674807267#step:5:2313
cmake -B build \ cmake -B build \
-DCMAKE_BUILD_RPATH="@loader_path" \
-DLLAMA_FATAL_WARNINGS=ON \ -DLLAMA_FATAL_WARNINGS=ON \
-DLLAMA_CURL=ON \ -DLLAMA_CURL=ON \
-DGGML_METAL=OFF \ -DGGML_METAL=OFF \
@ -160,8 +162,8 @@ jobs:
path: llama-${{ steps.tag.outputs.name }}-bin-macos-x64.zip path: llama-${{ steps.tag.outputs.name }}-bin-macos-x64.zip
name: llama-bin-macos-x64.zip name: llama-bin-macos-x64.zip
ubuntu-latest-cmake: ubuntu-cpu-cmake:
runs-on: ubuntu-latest runs-on: ubuntu-22.04
steps: steps:
- name: Clone - name: Clone
@ -181,7 +183,10 @@ jobs:
run: | run: |
mkdir build mkdir build
cd build cd build
cmake .. -DLLAMA_FATAL_WARNINGS=ON -DLLAMA_CURL=ON -DGGML_RPC=ON cmake .. \
-DLLAMA_FATAL_WARNINGS=ON \
-DLLAMA_CURL=ON \
-DGGML_RPC=ON
cmake --build . --config Release -j $(nproc) cmake --build . --config Release -j $(nproc)
- name: Test - name: Test
@ -256,7 +261,10 @@ jobs:
run: | run: |
mkdir build mkdir build
cd build cd build
cmake .. -DLLAMA_FATAL_WARNINGS=ON -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} cmake .. \
-DLLAMA_FATAL_WARNINGS=ON \
-DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \
-DCMAKE_BUILD_TYPE=${{ matrix.build_type }}
cmake --build . --config ${{ matrix.build_type }} -j $(nproc) cmake --build . --config ${{ matrix.build_type }} -j $(nproc)
- name: Build (no OpenMP) - name: Build (no OpenMP)
@ -265,7 +273,11 @@ jobs:
run: | run: |
mkdir build mkdir build
cd build cd build
cmake .. -DLLAMA_FATAL_WARNINGS=ON -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} -DGGML_OPENMP=OFF cmake .. \
-DLLAMA_FATAL_WARNINGS=ON \
-DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \
-DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \
-DGGML_OPENMP=OFF
cmake --build . --config ${{ matrix.build_type }} -j $(nproc) cmake --build . --config ${{ matrix.build_type }} -j $(nproc)
- name: Test - name: Test
@ -295,7 +307,8 @@ jobs:
run: | run: |
mkdir build mkdir build
cd build cd build
cmake -DGGML_RPC=ON .. cmake .. \
-DGGML_RPC=ON
cmake --build . --config Release -j $(nproc) cmake --build . --config Release -j $(nproc)
- name: Test - name: Test
@ -325,7 +338,8 @@ jobs:
run: | run: |
mkdir build mkdir build
cd build cd build
cmake -DGGML_VULKAN=ON .. cmake .. \
-DGGML_VULKAN=ON
cmake --build . --config Release -j $(nproc) cmake --build . --config Release -j $(nproc)
- name: Test - name: Test
@ -352,13 +366,18 @@ jobs:
- name: Build with native CMake HIP support - name: Build with native CMake HIP support
id: cmake_build id: cmake_build
run: | run: |
cmake -B build -S . -DCMAKE_HIP_COMPILER="$(hipconfig -l)/clang" -DGGML_HIP=ON cmake -B build -S . \
-DCMAKE_HIP_COMPILER="$(hipconfig -l)/clang" \
-DGGML_HIP=ON
cmake --build build --config Release -j $(nproc) cmake --build build --config Release -j $(nproc)
- name: Build with legacy HIP support - name: Build with legacy HIP support
id: cmake_build_legacy_hip id: cmake_build_legacy_hip
run: | run: |
cmake -B build2 -S . -DCMAKE_C_COMPILER=hipcc -DCMAKE_CXX_COMPILER=hipcc -DGGML_HIP=ON cmake -B build2 -S . \
-DCMAKE_C_COMPILER=hipcc \
-DCMAKE_CXX_COMPILER=hipcc \
-DGGML_HIP=ON
cmake --build build2 --config Release -j $(nproc) cmake --build build2 --config Release -j $(nproc)
ubuntu-22-cmake-musa: ubuntu-22-cmake-musa:
@ -379,7 +398,8 @@ jobs:
- name: Build with native CMake MUSA support - name: Build with native CMake MUSA support
id: cmake_build id: cmake_build
run: | run: |
cmake -B build -S . -DGGML_MUSA=ON cmake -B build -S . \
-DGGML_MUSA=ON
cmake --build build --config Release -j $(nproc) cmake --build build --config Release -j $(nproc)
ubuntu-22-cmake-sycl: ubuntu-22-cmake-sycl:
@ -420,7 +440,10 @@ jobs:
source /opt/intel/oneapi/setvars.sh source /opt/intel/oneapi/setvars.sh
mkdir build mkdir build
cd build cd build
cmake -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx .. cmake .. \
-DGGML_SYCL=ON \
-DCMAKE_C_COMPILER=icx \
-DCMAKE_CXX_COMPILER=icpx
cmake --build . --config Release -j $(nproc) cmake --build . --config Release -j $(nproc)
ubuntu-22-cmake-sycl-fp16: ubuntu-22-cmake-sycl-fp16:
@ -461,42 +484,13 @@ jobs:
source /opt/intel/oneapi/setvars.sh source /opt/intel/oneapi/setvars.sh
mkdir build mkdir build
cd build cd build
cmake -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DGGML_SYCL_F16=ON .. cmake .. \
-DGGML_SYCL=ON \
-DCMAKE_C_COMPILER=icx \
-DCMAKE_CXX_COMPILER=icpx \
-DGGML_SYCL_F16=ON
cmake --build . --config Release -j $(nproc) cmake --build . --config Release -j $(nproc)
# TODO: build with GGML_METAL=OFF because test-backend-ops fail on "Apple Paravirtual device" and I don't know
# how to debug it.
# ref: https://github.com/ggerganov/llama.cpp/actions/runs/7132125951/job/19422043567?pr=4359#step:5:6584
# would be great if we fix these
macOS-latest-cmake:
runs-on: macos-latest
steps:
- name: Clone
id: checkout
uses: actions/checkout@v4
- name: Dependencies
id: depends
continue-on-error: true
run: |
brew update
- name: Build
id: cmake_build
run: |
sysctl -a
mkdir build
cd build
cmake -DLLAMA_FATAL_WARNINGS=ON -DGGML_METAL=OFF ..
cmake --build . --config Release -j $(sysctl -n hw.logicalcpu)
- name: Test
id: cmake_test
run: |
cd build
ctest -L main --verbose --timeout 900
macOS-latest-cmake-ios: macOS-latest-cmake-ios:
runs-on: macos-latest runs-on: macos-latest
@ -827,7 +821,13 @@ jobs:
- name: Build with CMake - name: Build with CMake
run: | run: |
cmake -S . -B build -G Ninja -DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=OFF -DGGML_CUDA=ON -DCMAKE_CUDA_ARCHITECTURES=89-real -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined -DLLAMA_FATAL_WARNINGS=ON cmake -S . -B build -G Ninja \
-DCMAKE_BUILD_TYPE=Release \
-DCMAKE_CUDA_ARCHITECTURES=89-real \
-DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined \
-DLLAMA_FATAL_WARNINGS=ON \
-DGGML_NATIVE=OFF \
-DGGML_CUDA=ON
cmake --build build cmake --build build
windows-2019-cmake-cuda: windows-2019-cmake-cuda:
@ -916,7 +916,11 @@ jobs:
shell: cmd shell: cmd
run: | run: |
call "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\VC\Auxiliary\Build\vcvars64.bat" call "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\VC\Auxiliary\Build\vcvars64.bat"
cmake -S . -B build -G "Ninja Multi-Config" -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_CUDA=ON -DGGML_RPC=ON cmake -S . -B build -G "Ninja Multi-Config" \
-DLLAMA_BUILD_SERVER=ON \
-DGGML_NATIVE=OFF \
-DGGML_CUDA=ON \
-DGGML_RPC=ON
set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1 set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1
cmake --build build --config Release -j %NINJA_JOBS% -t ggml cmake --build build --config Release -j %NINJA_JOBS% -t ggml
cmake --build build --config Release cmake --build build --config Release
@ -1201,8 +1205,7 @@ jobs:
runs-on: ubuntu-latest runs-on: ubuntu-latest
needs: needs:
- ubuntu-latest-cmake - ubuntu-cpu-cmake
- macOS-latest-cmake
- windows-latest-cmake - windows-latest-cmake
- windows-2019-cmake-cuda - windows-2019-cmake-cuda
- windows-latest-cmake-hip-release - windows-latest-cmake-hip-release

1
CMakeLists.txt
View file

@ -16,6 +16,7 @@ endif()
list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/cmake/") list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/cmake/")
set(CMAKE_RUNTIME_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR}/bin) set(CMAKE_RUNTIME_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR}/bin)
set(CMAKE_LIBRARY_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR}/bin)
if (CMAKE_SOURCE_DIR STREQUAL CMAKE_CURRENT_SOURCE_DIR) if (CMAKE_SOURCE_DIR STREQUAL CMAKE_CURRENT_SOURCE_DIR)
set(LLAMA_STANDALONE ON) set(LLAMA_STANDALONE ON)