mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-06-27 23:50:20 -05:00
491c4d7d2e
* ci : separate CUDA windows workflow + fix names * ci : rename workflow * ci : prefix cache names with workflow name * ci : rename build.yml -> build-cpu.yml * ci : cache keys * ci : fix windows cuda/hip concurrency of release workflow * ci : fix apple cache names * ci : add TODOs * cont : keep just the last cache * ci : update release concurrency to queue * ci : move the release trigger to ubuntu-slim * ci : hip add TODO * cont : improve words Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
135 lines
3.6 KiB
YAML
135 lines
3.6 KiB
YAML
name: CI (CUDA, ubuntu)
|
|
|
|
on:
|
|
workflow_dispatch: # allows manual triggering
|
|
push:
|
|
branches:
|
|
- master
|
|
paths: [
|
|
'.github/workflows/build-cuda-ubuntu.yml',
|
|
'**/CMakeLists.txt',
|
|
'**/.cmake',
|
|
'**/*.h',
|
|
'**/*.hpp',
|
|
'**/*.c',
|
|
'**/*.cpp',
|
|
'**/*.cu',
|
|
'**/*.cuh'
|
|
]
|
|
|
|
pull_request:
|
|
types: [opened, synchronize, reopened]
|
|
paths: [
|
|
'.github/workflows/build-cuda-ubuntu.yml',
|
|
'ggml/src/ggml-cuda/**'
|
|
]
|
|
|
|
concurrency:
|
|
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
|
|
cancel-in-progress: true
|
|
|
|
env:
|
|
GGML_NLOOP: 3
|
|
GGML_N_THREADS: 1
|
|
LLAMA_ARG_LOG_COLORS: 1
|
|
LLAMA_ARG_LOG_PREFIX: 1
|
|
LLAMA_ARG_LOG_TIMESTAMPS: 1
|
|
|
|
jobs:
|
|
cuda:
|
|
runs-on: ubuntu-24.04
|
|
container: nvidia/cuda:12.6.2-devel-ubuntu24.04
|
|
|
|
steps:
|
|
- name: Clone
|
|
id: checkout
|
|
uses: actions/checkout@v6
|
|
|
|
- name: Install dependencies
|
|
env:
|
|
DEBIAN_FRONTEND: noninteractive
|
|
run: |
|
|
apt update
|
|
apt install -y cmake build-essential ninja-build libgomp1 git libssl-dev
|
|
|
|
- name: ccache
|
|
uses: ggml-org/ccache-action@v1.2.21
|
|
with:
|
|
key: cuda-ubuntu-24.04-cuda
|
|
evict-old-files: 1d
|
|
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
|
|
|
|
- name: Build with CMake
|
|
# TODO: Remove GGML_CUDA_CUB_3DOT2 flag once CCCL 3.2 is bundled within CTK and that CTK version is used in this project
|
|
run: |
|
|
cmake -S . -B build -G Ninja \
|
|
-DLLAMA_FATAL_WARNINGS=ON \
|
|
-DCMAKE_BUILD_TYPE=Release \
|
|
-DCMAKE_CUDA_ARCHITECTURES=89-real \
|
|
-DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined \
|
|
-DGGML_NATIVE=OFF \
|
|
-DGGML_CUDA=ON \
|
|
-DGGML_CUDA_CUB_3DOT2=ON
|
|
cmake --build build
|
|
|
|
hip:
|
|
runs-on: ubuntu-22.04
|
|
container: rocm/dev-ubuntu-22.04:6.1.2
|
|
|
|
steps:
|
|
- name: Clone
|
|
id: checkout
|
|
uses: actions/checkout@v6
|
|
|
|
- name: Dependencies
|
|
id: depends
|
|
run: |
|
|
sudo apt-get update
|
|
sudo apt-get install -y build-essential git cmake rocblas-dev hipblas-dev libssl-dev rocwmma-dev
|
|
|
|
- name: ccache
|
|
uses: ggml-org/ccache-action@v1.2.21
|
|
with:
|
|
key: cuda-ubuntu-22.04-hip
|
|
evict-old-files: 1d
|
|
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
|
|
|
|
- name: Build with native CMake HIP support
|
|
id: cmake_build
|
|
run: |
|
|
cmake -B build -S . \
|
|
-DCMAKE_HIP_COMPILER="$(hipconfig -l)/clang" \
|
|
-DGGML_HIP_ROCWMMA_FATTN=ON \
|
|
-DGPU_TARGETS="gfx1030" \
|
|
-DGGML_HIP=ON
|
|
cmake --build build --config Release -j $(nproc)
|
|
|
|
musa:
|
|
runs-on: ubuntu-22.04
|
|
container: mthreads/musa:rc4.3.0-devel-ubuntu22.04-amd64
|
|
|
|
steps:
|
|
- name: Clone
|
|
id: checkout
|
|
uses: actions/checkout@v6
|
|
|
|
- name: Dependencies
|
|
id: depends
|
|
run: |
|
|
apt-get update
|
|
apt-get install -y build-essential git cmake libssl-dev
|
|
|
|
- name: ccache
|
|
uses: ggml-org/ccache-action@v1.2.21
|
|
with:
|
|
key: cuda-ubuntu-22.04-musa
|
|
evict-old-files: 1d
|
|
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
|
|
|
|
- name: Build with native CMake MUSA support
|
|
id: cmake_build
|
|
run: |
|
|
cmake -B build -S . \
|
|
-DGGML_MUSA=ON
|
|
time cmake --build build --config Release -j $(nproc)
|