jobs:
determine-tag:
name: Determine tag name
- runs-on: ubuntu-slim
+ runs-on: [self-hosted, fast]
outputs:
tag_name: ${{ steps.tag.outputs.name }}
steps:
HF_UI_VERSION: ${{ needs.determine-tag.outputs.tag_name }}
run: |
nvidia-smi
- GG_BUILD_CUDA=1 bash ./ci/run.sh ~/results/llama.cpp /mnt/llama.cpp
+ GG_BUILD_CUDA=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
ggml-ci-nvidia-vulkan-cm:
needs: determine-tag
HF_UI_VERSION: ${{ needs.determine-tag.outputs.tag_name }}
run: |
vulkaninfo --summary
- GG_BUILD_VULKAN=1 GGML_VK_DISABLE_COOPMAT2=1 bash ./ci/run.sh ~/results/llama.cpp /mnt/llama.cpp
+ GG_BUILD_VULKAN=1 GGML_VK_DISABLE_COOPMAT2=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
ggml-ci-nvidia-vulkan-cm2:
needs: determine-tag
HF_UI_VERSION: ${{ needs.determine-tag.outputs.tag_name }}
run: |
vulkaninfo --summary
- GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp /mnt/llama.cpp
+ GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
ggml-ci-nvidia-webgpu:
- runs-on: [self-hosted, Linux, NVIDIA]
+ needs: determine-tag
+ runs-on: [self-hosted, Linux, NVIDIA, X64]
steps:
- name: Clone
GG_BUILD_WEBGPU=1 \
GG_BUILD_WEBGPU_DAWN_PREFIX="$GITHUB_WORKSPACE/dawn" \
GG_BUILD_WEBGPU_DAWN_DIR="$GITHUB_WORKSPACE/dawn/lib64/cmake/Dawn" \
- bash ./ci/run.sh ~/results/llama.cpp /mnt/llama.cpp
+ bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
# TODO: provision AMX-compatible machine
#ggml-ci-cpu-amx:
+ # needs: determine-tag
# runs-on: [self-hosted, Linux, CPU, AMX]
# steps:
# - name: Test
# id: ggml-ci
# run: |
- # bash ./ci/run.sh ~/results/llama.cpp /mnt/llama.cpp
+ # bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
# TODO: provision AMD GPU machine
# ggml-ci-amd-vulkan:
+ # needs: determine-tag
# runs-on: [self-hosted, Linux, AMD]
# steps:
# id: ggml-ci
# run: |
# vulkaninfo --summary
- # GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp /mnt/llama.cpp
+ # GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
# TODO: provision AMD GPU machine
# ggml-ci-amd-rocm:
+ # needs: determine-tag
# runs-on: [self-hosted, Linux, AMD]
# steps:
# id: ggml-ci
# run: |
# amd-smi static
- # GG_BUILD_ROCM=1 GG_BUILD_AMDGPU_TARGETS="gfx1101" bash ./ci/run.sh ~/results/llama.cpp /mnt/llama.cpp
+ # GG_BUILD_ROCM=1 GG_BUILD_AMDGPU_TARGETS="gfx1101" bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
ggml-ci-mac-metal:
needs: determine-tag
HF_UI_VERSION: ${{ needs.determine-tag.outputs.tag_name }}
run: |
source ./openvino_toolkit/setupvars.sh
- GG_BUILD_OPENVINO=1 GGML_OPENVINO_DEVICE=GPU GG_BUILD_LOW_PERF=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt
+ GG_BUILD_OPENVINO=1 GGML_OPENVINO_DEVICE=GPU GG_BUILD_LOW_PERF=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
+
+ ggml-ci-arm64-cpu-low-perf:
+ needs: determine-tag
+ runs-on: [self-hosted, Linux, ARM64]
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: Test
+ id: ggml-ci
+ run: |
+ LLAMA_ARG_THREADS=$(nproc) GG_BUILD_LOW_PERF=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
+
+ ggml-ci-arm64-cpu-high-perf:
+ needs: determine-tag
+ runs-on: [self-hosted, Linux, ARM64]
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: Test
+ id: ggml-ci
+ run: |
+ LLAMA_ARG_THREADS=$(nproc) GG_BUILD_HIGH_PERF=1 GG_BUILD_NO_SVE=1 GG_BUILD_NO_BF16=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
+
+# TODO: not sure how to detect ARM flags on DGX Spark. currently get this error during cmake:
+# CMake Warning at ggml/src/ggml-cpu/CMakeLists.txt:147 (message):
+# ARM -march/-mcpu not found, -mcpu=native will be used
+#
+# if we resolve this, we should be able to offload these jobs to the self-hosted runners
+#
+# ggml-ci-arm64-cpu-high-perf-sve:
+# needs: determine-tag
+# runs-on: [self-hosted, Linux, NVIDIA, ARM64]
+#
+# steps:
+# - name: Clone
+# id: checkout
+# uses: actions/checkout@v6
+#
+# - name: Test
+# id: ggml-ci
+# run: |
+# LLAMA_ARG_THREADS=$(nproc) GG_BUILD_NO_BF16=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
+#
+# ggml-ci-arm64-cpu-kleidiai:
+# needs: determine-tag
+# runs-on: [self-hosted, Linux, NVIDIA, ARM64]
+#
+# steps:
+# - name: Clone
+# id: checkout
+# uses: actions/checkout@v6
+#
+# - name: Test
+# id: ggml-ci
+# run: |
+# GG_BUILD_KLEIDIAI=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
run: |
LLAMA_ARG_THREADS=$(nproc) GG_BUILD_LOW_PERF=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt
- ggml-ci-arm64-cpu-low-perf:
- runs-on: ubuntu-22.04-arm
-
- steps:
- - name: Clone
- id: checkout
- uses: actions/checkout@v6
-
- - name: ccache
- uses: ggml-org/ccache-action@v1.2.21
- with:
- key: ggml-ci-arm64-cpu-low-perf
- evict-old-files: 1d
- save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
-
- - name: Dependencies
- id: depends
- run: |
- sudo apt-get update
- sudo apt-get install build-essential
-
- - name: Test
- id: ggml-ci
- run: |
- LLAMA_ARG_THREADS=$(nproc) GG_BUILD_LOW_PERF=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt
+# note: moved to build-self-hosted.yml - can remove from here when everything is stable
+# ggml-ci-arm64-cpu-low-perf:
+# runs-on: ubuntu-22.04-arm
+#
+# steps:
+# - name: Clone
+# id: checkout
+# uses: actions/checkout@v6
+#
+# - name: ccache
+# uses: ggml-org/ccache-action@v1.2.21
+# with:
+# key: ggml-ci-arm64-cpu-low-perf
+# evict-old-files: 1d
+# save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+#
+# - name: Dependencies
+# id: depends
+# run: |
+# sudo apt-get update
+# sudo apt-get install build-essential
+#
+# - name: Test
+# id: ggml-ci
+# run: |
+# LLAMA_ARG_THREADS=$(nproc) GG_BUILD_LOW_PERF=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt
ggml-ci-x64-cpu-high-perf:
runs-on: ubuntu-22.04
run: |
LLAMA_ARG_THREADS=$(nproc) GG_BUILD_HIGH_PERF=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt
- ggml-ci-arm64-cpu-high-perf:
- runs-on: ubuntu-22.04-arm
-
- steps:
- - name: Clone
- id: checkout
- uses: actions/checkout@v6
-
- - name: ccache
- uses: ggml-org/ccache-action@v1.2.21
- with:
- key: ggml-ci-arm64-cpu-high-perf
- evict-old-files: 1d
- save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
-
- - name: Dependencies
- id: depends
- run: |
- sudo apt-get update
- sudo apt-get install build-essential
-
- - name: Test
- id: ggml-ci
- run: |
- LLAMA_ARG_THREADS=$(nproc) GG_BUILD_HIGH_PERF=1 GG_BUILD_NO_SVE=1 GG_BUILD_NO_BF16=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt
+# note: moved to build-self-hosted.yml - can remove from here when everything is stable
+# ggml-ci-arm64-cpu-high-perf:
+# runs-on: ubuntu-22.04-arm
+#
+# steps:
+# - name: Clone
+# id: checkout
+# uses: actions/checkout@v6
+#
+# - name: ccache
+# uses: ggml-org/ccache-action@v1.2.21
+# with:
+# key: ggml-ci-arm64-cpu-high-perf
+# evict-old-files: 1d
+# save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+#
+# - name: Dependencies
+# id: depends
+# run: |
+# sudo apt-get update
+# sudo apt-get install build-essential
+#
+# - name: Test
+# id: ggml-ci
+# run: |
+# LLAMA_ARG_THREADS=$(nproc) GG_BUILD_HIGH_PERF=1 GG_BUILD_NO_SVE=1 GG_BUILD_NO_BF16=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt
ggml-ci-arm64-cpu-high-perf-sve:
runs-on: ubuntu-22.04-arm
export ${{ matrix.extra_args }}
pytest -v -x -m "not slow"
- # TODO: provision CUDA runner
- # server-cuda:
- # runs-on: [self-hosted, llama-server, Linux, NVIDIA]
- #
- # name: server-cuda (${{ matrix.wf_name }})
- # strategy:
- # matrix:
- # build_type: [Release]
- # wf_name: ["GPUx1"]
- # include:
- # - build_type: Release
- # extra_args: "LLAMA_ARG_BACKEND_SAMPLING=1"
- # wf_name: "GPUx1, backend-sampling"
- # fail-fast: false
- #
- # steps:
- # - name: Clone
- # id: checkout
- # uses: actions/checkout@v6
- # with:
- # fetch-depth: 0
- # ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }}
- #
- # - name: Build
- # id: cmake_build
- # run: |
- # cmake -B build -DGGML_SCHED_NO_REALLOC=ON
- # cmake --build build --config ${{ matrix.build_type }} -j $(sysctl -n hw.logicalcpu) --target llama-server
- #
- # - name: Tests
- # id: server_integration_tests
- # if: ${{ (!matrix.disabled_on_pr || !github.event.pull_request) }}
- # run: |
- # cd tools/server/tests
- # python3 -m venv venv
- # source venv/bin/activate
- # pip install -r requirements.txt
- # export ${{ matrix.extra_args }}
- # pytest -v -x -m "not slow"
+ server-cuda:
+ runs-on: [self-hosted, llama-server, Linux, NVIDIA]
+
+ name: server-cuda (${{ matrix.wf_name }})
+ strategy:
+ matrix:
+ build_type: [Release]
+ wf_name: ["GPUx1"]
+ include:
+ - build_type: Release
+ extra_args: "LLAMA_ARG_BACKEND_SAMPLING=1"
+ wf_name: "GPUx1, backend-sampling"
+ fail-fast: false
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+ with:
+ fetch-depth: 0
+ ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }}
+
+ - name: Build
+ id: cmake_build
+ run: |
+ cmake -B build -DGGML_CUDA=ON -DGGML_SCHED_NO_REALLOC=ON
+ cmake --build build --config ${{ matrix.build_type }} -j $(nproc) --target llama-server
+
+ - name: Tests
+ id: server_integration_tests
+ if: ${{ (!matrix.disabled_on_pr || !github.event.pull_request) }}
+ run: |
+ cd tools/server/tests
+ python3 -m venv venv
+ source venv/bin/activate
+ pip install -r requirements.txt
+ export ${{ matrix.extra_args }}
+ pytest -v -x -m "not slow"
server-kleidiai:
runs-on: ah-ubuntu_22_04-c8g_8x
(cmake -G "${CMAKE_GENERATOR}" -DCMAKE_BUILD_TYPE=Debug ${CMAKE_EXTRA} .. ) 2>&1 | tee -a $OUT/${ci}-cmake.log
(time cmake --build . --config Debug -j$(nproc)) 2>&1 | tee -a $OUT/${ci}-make.log
- (time ctest -C Debug --output-on-failure -L main -E "test-opt|test-backend-ops" ${CTEST_EXTRA}) 2>&1 | tee -a $OUT/${ci}-ctest.log
+ (time ctest -C Debug --output-on-failure -L main -E "test-opt|test-backend-ops|test-llama-archs" ${CTEST_EXTRA}) 2>&1 | tee -a $OUT/${ci}-ctest.log
set +e
}
overview / pkg / ggml / sources / llama.cpp / commitdiff