ci : move ARM jobs to self-hosted + disable kleidiai mac release (#23780)
* ci : move ARM jobs to 3rd-party runners + disable kleidiai release * cont : fix deps + fix names * ocd : fix names * cont : fix PR links
This commit is contained in:
Georgi Gerganov
@@ -55,7 +55,7 @@ env:
|
|||||||
LLAMA_ARG_LOG_TIMESTAMPS: 1
|
LLAMA_ARG_LOG_TIMESTAMPS: 1
|
||||||
|
|
||||||
jobs:
|
jobs:
|
||||||
ggml-ci-nvidia-cuda:
|
gpu-cuda:
|
||||||
runs-on: [self-hosted, Linux, NVIDIA]
|
runs-on: [self-hosted, Linux, NVIDIA]
|
||||||
|
|
||||||
steps:
|
steps:
|
||||||
@@ -69,7 +69,7 @@ jobs:
|
|||||||
nvidia-smi
|
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:
|
gpu-vulkan-nvidia-cm:
|
||||||
runs-on: [self-hosted, Linux, NVIDIA]
|
runs-on: [self-hosted, Linux, NVIDIA]
|
||||||
|
|
||||||
steps:
|
steps:
|
||||||
@@ -83,7 +83,7 @@ jobs:
|
|||||||
vulkaninfo --summary
|
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:
|
gpu-vulkan-nvidia-cm2:
|
||||||
runs-on: [self-hosted, Linux, NVIDIA, COOPMAT2]
|
runs-on: [self-hosted, Linux, NVIDIA, COOPMAT2]
|
||||||
|
|
||||||
steps:
|
steps:
|
||||||
@@ -97,7 +97,7 @@ jobs:
|
|||||||
vulkaninfo --summary
|
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:
|
gpu-webgpu-nvidia:
|
||||||
runs-on: [self-hosted, Linux, NVIDIA, X64]
|
runs-on: [self-hosted, Linux, NVIDIA, X64]
|
||||||
|
|
||||||
steps:
|
steps:
|
||||||
@@ -127,7 +127,7 @@ jobs:
|
|||||||
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
|
# TODO: provision AMX-compatible machine
|
||||||
#ggml-ci-cpu-amx:
|
#cpu-amx:
|
||||||
# runs-on: [self-hosted, Linux, CPU, AMX]
|
# runs-on: [self-hosted, Linux, CPU, AMX]
|
||||||
|
|
||||||
# steps:
|
# steps:
|
||||||
@@ -141,7 +141,7 @@ jobs:
|
|||||||
# 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
|
# TODO: provision AMD GPU machine
|
||||||
# ggml-ci-amd-vulkan:
|
# amd-vulkan:
|
||||||
# runs-on: [self-hosted, Linux, AMD]
|
# runs-on: [self-hosted, Linux, AMD]
|
||||||
|
|
||||||
# steps:
|
# steps:
|
||||||
@@ -156,7 +156,7 @@ jobs:
|
|||||||
# 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
|
# TODO: provision AMD GPU machine
|
||||||
# ggml-ci-amd-rocm:
|
# amd-rocm:
|
||||||
# runs-on: [self-hosted, Linux, AMD]
|
# runs-on: [self-hosted, Linux, AMD]
|
||||||
|
|
||||||
# steps:
|
# steps:
|
||||||
@@ -170,7 +170,7 @@ jobs:
|
|||||||
# amd-smi static
|
# 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:
|
gpu-metal:
|
||||||
runs-on: [self-hosted, macOS, ARM64]
|
runs-on: [self-hosted, macOS, ARM64]
|
||||||
|
|
||||||
steps:
|
steps:
|
||||||
@@ -183,7 +183,7 @@ jobs:
|
|||||||
run: |
|
run: |
|
||||||
GG_BUILD_METAL=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
|
GG_BUILD_METAL=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
|
||||||
|
|
||||||
ggml-ci-mac-webgpu:
|
gpu-webgpu-apple:
|
||||||
runs-on: [self-hosted, macOS, ARM64]
|
runs-on: [self-hosted, macOS, ARM64]
|
||||||
|
|
||||||
steps:
|
steps:
|
||||||
@@ -210,7 +210,7 @@ jobs:
|
|||||||
GG_BUILD_WEBGPU=1 GG_BUILD_WEBGPU_DAWN_PREFIX="$GITHUB_WORKSPACE/dawn" \
|
GG_BUILD_WEBGPU=1 GG_BUILD_WEBGPU_DAWN_PREFIX="$GITHUB_WORKSPACE/dawn" \
|
||||||
bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
|
bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
|
||||||
|
|
||||||
ggml-ci-mac-vulkan:
|
gpu-vulkan:
|
||||||
runs-on: [self-hosted, macOS, ARM64]
|
runs-on: [self-hosted, macOS, ARM64]
|
||||||
|
|
||||||
steps:
|
steps:
|
||||||
@@ -224,7 +224,7 @@ jobs:
|
|||||||
vulkaninfo --summary
|
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-linux-intel-vulkan:
|
gpu-vulkan-intel-linux:
|
||||||
runs-on: [self-hosted, Linux, Intel]
|
runs-on: [self-hosted, Linux, Intel]
|
||||||
|
|
||||||
steps:
|
steps:
|
||||||
@@ -240,7 +240,7 @@ jobs:
|
|||||||
vulkaninfo --summary
|
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-win-intel-vulkan:
|
gpu-vulkan-intel-windows:
|
||||||
runs-on: [self-hosted, Windows, X64, Intel]
|
runs-on: [self-hosted, Windows, X64, Intel]
|
||||||
|
|
||||||
steps:
|
steps:
|
||||||
@@ -261,7 +261,7 @@ jobs:
|
|||||||
# a valid python environment for testing
|
# a valid python environment for testing
|
||||||
LLAMA_FATAL_WARNINGS=OFF GG_BUILD_NINJA=1 GG_BUILD_VULKAN=1 GG_BUILD_LOW_PERF=1 ./ci/run.sh ./results/llama.cpp ./mnt/llama.cpp
|
LLAMA_FATAL_WARNINGS=OFF GG_BUILD_NINJA=1 GG_BUILD_VULKAN=1 GG_BUILD_LOW_PERF=1 ./ci/run.sh ./results/llama.cpp ./mnt/llama.cpp
|
||||||
|
|
||||||
ggml-ci-intel-openvino-gpu-low-perf:
|
cpu-openvino-low-perf:
|
||||||
runs-on: [self-hosted, Linux, Intel, OpenVINO]
|
runs-on: [self-hosted, Linux, Intel, OpenVINO]
|
||||||
|
|
||||||
concurrency:
|
concurrency:
|
||||||
@@ -297,7 +297,7 @@ jobs:
|
|||||||
source ./openvino_toolkit/setupvars.sh
|
source ./openvino_toolkit/setupvars.sh
|
||||||
GG_BUILD_OPENVINO=1 GGML_OPENVINO_DEVICE=GPU GG_BUILD_LOW_PERF=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
|
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-cpu-low-perf:
|
cpu-any-low-perf:
|
||||||
runs-on: [self-hosted, CPU]
|
runs-on: [self-hosted, CPU]
|
||||||
|
|
||||||
steps:
|
steps:
|
||||||
@@ -310,7 +310,7 @@ jobs:
|
|||||||
run: |
|
run: |
|
||||||
LLAMA_ARG_THREADS=$(nproc) GG_BUILD_LOW_PERF=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
|
LLAMA_ARG_THREADS=$(nproc) GG_BUILD_LOW_PERF=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
|
||||||
|
|
||||||
ggml-ci-cpu-high-perf:
|
cpu-any-high-perf:
|
||||||
runs-on: [self-hosted, CPU]
|
runs-on: [self-hosted, CPU]
|
||||||
|
|
||||||
steps:
|
steps:
|
||||||
@@ -323,39 +323,46 @@ jobs:
|
|||||||
run: |
|
run: |
|
||||||
LLAMA_ARG_THREADS=$(nproc) GG_BUILD_HIGH_PERF=1 GG_BUILD_NO_SVE=1 GG_BUILD_NO_BF16=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
|
LLAMA_ARG_THREADS=$(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:
|
cpu-arm64-graviton4:
|
||||||
# CMake Warning at ggml/src/ggml-cpu/CMakeLists.txt:147 (message):
|
runs-on: ah-ubuntu_22_04-c8g_8x
|
||||||
# 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:
|
|
||||||
# runs-on: [self-hosted, Linux, ARM64, CPU]
|
|
||||||
#
|
|
||||||
# steps:
|
|
||||||
# - name: Clone
|
|
||||||
# id: checkout
|
|
||||||
# uses: actions/checkout@v6
|
|
||||||
#
|
|
||||||
# - name: Test
|
|
||||||
# id: ggml-ci
|
|
||||||
# run: |
|
|
||||||
# LLAMA_ARG_THREADS=$(nproc) GG_BUILD_NO_BF16=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
|
|
||||||
#
|
|
||||||
# ggml-ci-arm64-cpu-kleidiai:
|
|
||||||
# runs-on: [self-hosted, Linux, ARM64, CPU]
|
|
||||||
#
|
|
||||||
# steps:
|
|
||||||
# - name: Clone
|
|
||||||
# id: checkout
|
|
||||||
# uses: actions/checkout@v6
|
|
||||||
#
|
|
||||||
# - name: Test
|
|
||||||
# id: ggml-ci
|
|
||||||
# run: |
|
|
||||||
# GG_BUILD_KLEIDIAI=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
|
|
||||||
|
|
||||||
ggml-ci-arm64-cpu-kleidiai-graviton4:
|
steps:
|
||||||
|
- name: Clone
|
||||||
|
id: checkout
|
||||||
|
uses: actions/checkout@v6
|
||||||
|
|
||||||
|
- name: Dependencies
|
||||||
|
id: depends
|
||||||
|
run: |
|
||||||
|
set -euxo pipefail
|
||||||
|
sudo apt-get update
|
||||||
|
sudo DEBIAN_FRONTEND=noninteractive NEEDRESTART_MODE=a \
|
||||||
|
apt-get install -y \
|
||||||
|
build-essential \
|
||||||
|
python3-venv \
|
||||||
|
gpg \
|
||||||
|
wget \
|
||||||
|
time \
|
||||||
|
git-lfs
|
||||||
|
|
||||||
|
git lfs install
|
||||||
|
|
||||||
|
# install the latest cmake
|
||||||
|
sudo install -d /usr/share/keyrings
|
||||||
|
wget -O - https://apt.kitware.com/keys/kitware-archive-latest.asc \
|
||||||
|
| gpg --dearmor \
|
||||||
|
| sudo tee /usr/share/keyrings/kitware-archive-keyring.gpg >/dev/null
|
||||||
|
echo 'deb [signed-by=/usr/share/keyrings/kitware-archive-keyring.gpg] https://apt.kitware.com/ubuntu/ jammy main' \
|
||||||
|
| sudo tee /etc/apt/sources.list.d/kitware.list
|
||||||
|
sudo apt-get update
|
||||||
|
sudo apt-get install -y cmake
|
||||||
|
|
||||||
|
- name: Test
|
||||||
|
id: ggml-ci
|
||||||
|
run: |
|
||||||
|
LLAMA_ARG_THREADS=$(nproc) GG_BUILD_NO_BF16=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
|
||||||
|
|
||||||
|
cpu-arm64-graviton4-kleidiai:
|
||||||
runs-on: ah-ubuntu_22_04-c8g_8x
|
runs-on: ah-ubuntu_22_04-c8g_8x
|
||||||
|
|
||||||
steps:
|
steps:
|
||||||
@@ -393,7 +400,7 @@ jobs:
|
|||||||
#- name: ccache
|
#- name: ccache
|
||||||
# uses: ggml-org/ccache-action@v1.2.21
|
# uses: ggml-org/ccache-action@v1.2.21
|
||||||
# with:
|
# with:
|
||||||
# key: ggml-ci-arm64-cpu-kleidiai-graviton4
|
# key: arm64-cpu-kleidiai-graviton4
|
||||||
# evict-old-files: 1d
|
# evict-old-files: 1d
|
||||||
# save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
|
# save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
|
||||||
|
|
||||||
|
|||||||
@@ -353,166 +353,3 @@ jobs:
|
|||||||
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
|
||||||
|
|
||||||
# TODO: simplify the following workflows using a matrix
|
|
||||||
# TODO: run lighter CI on PRs and the full CI only on master (if needed)
|
|
||||||
|
|
||||||
# note: moved to build-self-hosted.yml - can remove from here when everything is stable
|
|
||||||
# ggml-ci-x64-cpu-low-perf:
|
|
||||||
# runs-on: ubuntu-22.04
|
|
||||||
#
|
|
||||||
# steps:
|
|
||||||
# - name: Clone
|
|
||||||
# id: checkout
|
|
||||||
# uses: actions/checkout@v6
|
|
||||||
#
|
|
||||||
# - name: ccache
|
|
||||||
# uses: ggml-org/ccache-action@v1.2.21
|
|
||||||
# with:
|
|
||||||
# key: ggml-ci-x64-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
|
|
||||||
|
|
||||||
# note: moved to build-self-hosted.yml - can remove from here when everything is stable
|
|
||||||
# ggml-ci-x64-cpu-high-perf:
|
|
||||||
# runs-on: ubuntu-22.04
|
|
||||||
#
|
|
||||||
# steps:
|
|
||||||
# - name: Clone
|
|
||||||
# id: checkout
|
|
||||||
# uses: actions/checkout@v6
|
|
||||||
#
|
|
||||||
# - name: ccache
|
|
||||||
# uses: ggml-org/ccache-action@v1.2.21
|
|
||||||
# with:
|
|
||||||
# key: ggml-ci-x64-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 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
|
|
||||||
|
|
||||||
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-sve
|
|
||||||
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_NO_BF16=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt
|
|
||||||
|
|
||||||
ggml-ci-arm64-cpu-kleidiai:
|
|
||||||
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-kleidiai
|
|
||||||
evict-old-files: 1d
|
|
||||||
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
|
|
||||||
|
|
||||||
- name: Dependencies
|
|
||||||
id: depends
|
|
||||||
run: |
|
|
||||||
sudo apt-get update
|
|
||||||
sudo apt-get install -y build-essential
|
|
||||||
|
|
||||||
- name: Test
|
|
||||||
id: ggml-ci
|
|
||||||
run: |
|
|
||||||
GG_BUILD_KLEIDIAI=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt
|
|
||||||
|
|||||||
@@ -68,10 +68,12 @@ jobs:
|
|||||||
arch: 'arm64'
|
arch: 'arm64'
|
||||||
os: macos-14
|
os: macos-14
|
||||||
defines: "-DGGML_METAL_USE_BF16=ON -DGGML_METAL_EMBED_LIBRARY=ON"
|
defines: "-DGGML_METAL_USE_BF16=ON -DGGML_METAL_EMBED_LIBRARY=ON"
|
||||||
- build: 'arm64-kleidiai'
|
# TODO: this build is disabled to save Github Actions resources (https://github.com/ggml-org/llama.cpp/pull/23780)
|
||||||
arch: 'arm64'
|
# in order to enable it again, we have to provision dedicated runners to run it
|
||||||
os: macos-14
|
#- build: 'arm64-kleidiai'
|
||||||
defines: "-DGGML_METAL_USE_BF16=ON -DGGML_METAL_EMBED_LIBRARY=ON -DGGML_CPU_KLEIDIAI=ON"
|
# arch: 'arm64'
|
||||||
|
# os: macos-14
|
||||||
|
# defines: "-DGGML_METAL_USE_BF16=ON -DGGML_METAL_EMBED_LIBRARY=ON -DGGML_CPU_KLEIDIAI=ON"
|
||||||
- build: 'x64'
|
- build: 'x64'
|
||||||
arch: 'x64'
|
arch: 'x64'
|
||||||
os: macos-15-intel
|
os: macos-15-intel
|
||||||
@@ -1396,7 +1398,7 @@ jobs:
|
|||||||
|
|
||||||
**macOS/iOS:**
|
**macOS/iOS:**
|
||||||
- [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.tar.gz)
|
- [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.tar.gz)
|
||||||
- [macOS Apple Silicon (arm64, KleidiAI enabled)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-macos-arm64-kleidiai.tar.gz)
|
- macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780)
|
||||||
- [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-macos-x64.tar.gz)
|
- [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-macos-x64.tar.gz)
|
||||||
- [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-xcframework.zip)
|
- [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-xcframework.zip)
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user