Unverified Commit adba172f authored by ishandhanani's avatar ishandhanani Committed by GitHub
Browse files

ci: free space on workers for build (#10786)


Co-authored-by: default avatarzhyncs <me@zhyncs.com>
parent cd641a99
name: Build Development Docker Image
name: Build and Push Development Docker Images
on:
workflow_dispatch:
......@@ -8,7 +8,7 @@ on:
jobs:
build-dev-x86:
if: ${{ github.repository == 'sgl-project/sglang' }}
runs-on: ubuntu-22.04
runs-on: nvidia
strategy:
matrix:
variant:
......@@ -16,19 +16,22 @@ jobs:
type: all
tag: dev
steps:
- name: Delete huge unnecessary tools folder
run: rm -rf /opt/hostedtoolcache
- name: Checkout repository
uses: actions/checkout@v4
- name: Free disk space
uses: jlumbroso/free-disk-space@main
with:
tool-cache: false
docker-images: false
tool-cache: true
docker-images: true
android: true
dotnet: true
haskell: true
large-packages: true
swap-storage: false
swap-storage: true
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
......@@ -43,54 +46,9 @@ jobs:
run: |
docker buildx build --platform linux/amd64 --push -f docker/Dockerfile --build-arg CUDA_VERSION=${{ matrix.variant.version }} --build-arg BUILD_TYPE=${{ matrix.variant.type }} --build-arg CMAKE_BUILD_PARALLEL_LEVEL=$(nproc) -t lmsysorg/sglang:${{ matrix.variant.tag }} --no-cache .
build-blackwell-x86:
if: ${{ github.repository == 'sgl-project/sglang' }}
runs-on: ubuntu-latest
strategy:
matrix:
variant:
- version: 12.8.1
type: blackwell
tag: blackwell
- version: 12.9.1
type: blackwell
tag: blackwell-cu129
steps:
- name: Checkout repository
uses: actions/checkout@v4
- name: Free disk space
uses: jlumbroso/free-disk-space@main
with:
tool-cache: false
docker-images: false
android: true
dotnet: true
haskell: true
large-packages: true
swap-storage: false
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
- name: Login to Docker Hub
uses: docker/login-action@v2
with:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
- name: Build and Push Blackwell Image (x86)
run: |
if [ "${{ matrix.variant.version }}" = "12.9.1" ]; then
docker buildx build --platform linux/amd64 --push -f docker/Dockerfile --build-arg CUDA_VERSION=${{ matrix.variant.version }} --build-arg BUILD_TYPE=${{ matrix.variant.type }} --build-arg CMAKE_BUILD_PARALLEL_LEVEL=$(nproc) -t lmsysorg/sglang:${{ matrix.variant.tag }}-x86 --no-cache .
else
docker buildx build --platform linux/amd64 --push -f docker/Dockerfile --build-arg CUDA_VERSION=${{ matrix.variant.version }} --build-arg BUILD_TYPE=${{ matrix.variant.type }} --build-arg CMAKE_BUILD_PARALLEL_LEVEL=$(nproc) -t lmsysorg/sglang:${{ matrix.variant.tag }} --no-cache .
fi
build-blackwell-arm:
if: ${{ github.repository == 'sgl-project/sglang' }}
runs-on: ubuntu-22.04-arm
runs-on: labubu
strategy:
matrix:
variant:
......@@ -98,19 +56,22 @@ jobs:
type: blackwell_aarch
tag: blackwell-cu129
steps:
- name: Delete huge unnecessary tools folder
run: rm -rf /opt/hostedtoolcache
- name: Checkout repository
uses: actions/checkout@v4
- name: Free disk space
uses: jlumbroso/free-disk-space@main
with:
tool-cache: false
docker-images: false
tool-cache: true
docker-images: true
android: true
dotnet: true
haskell: true
large-packages: true
swap-storage: false
swap-storage: true
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
......@@ -128,14 +89,14 @@ jobs:
create-manifests:
runs-on: ubuntu-22.04
needs: [build-blackwell-x86, build-blackwell-arm]
needs: [build-dev-x86, build-blackwell-arm]
if: ${{ github.repository == 'sgl-project/sglang' }}
strategy:
matrix:
variant:
- tag: blackwell-cu129
x86_tag: blackwell-cu129-x86
arm64_tag: blackwell-cu129-arm64
- tag: dev
x86_tag: dev-x86
arm64_tag: dev-arm64
steps:
- uses: docker/setup-buildx-action@v3
- uses: docker/login-action@v2
......
......@@ -20,7 +20,7 @@ jobs:
build_type: 'blackwell'
- cuda_version: '12.9.1'
build_type: 'blackwell'
runs-on: ubuntu-latest
runs-on: nvidia
steps:
- name: Delete huge unnecessary tools folder
run: rm -rf /opt/hostedtoolcache
......@@ -88,7 +88,7 @@ jobs:
variant:
- cuda_version: '12.9.1'
build_type: 'blackwell_aarch'
runs-on: ubuntu-22.04-arm
runs-on: labubu
steps:
- name: Delete huge unnecessary tools folder
run: rm -rf /opt/hostedtoolcache
......
......@@ -90,12 +90,12 @@ RUN python3 -m pip install --no-cache-dir --upgrade pip setuptools wheel html5li
fi \
&& python3 -m pip install --no-cache-dir -e "python[${BUILD_TYPE}]" --extra-index-url https://download.pytorch.org/whl/cu${CUINDEX} \
&& python3 -m pip install --no-cache-dir nvidia-nccl-cu12==2.27.6 --force-reinstall --no-deps \
&& python3 -m flashinfer --download-cubin
&& FLASHINFER_LOGGING_LEVEL=warning python3 -m flashinfer --download-cubin
# Download source files
RUN wget https://developer.download.nvidia.com/compute/redist/nvshmem/3.3.9/source/nvshmem_src_cuda12-all-all-3.3.9.tar.gz && \
if [ "$BUILD_TYPE" = "blackwell" ] && [ "$(uname -m)" = "aarch64" ]; then \
if [ "$BUILD_TYPE" = "blackwell_aarch" ] && [ "$(uname -m)" = "aarch64" ]; then \
git clone https://github.com/fzyzcjy/DeepEP.git \
&& cd DeepEP && git checkout 1b14ad661c7640137fcfe93cccb2694ede1220b0 && sed -i 's/#define NUM_CPU_TIMEOUT_SECS 100/#define NUM_CPU_TIMEOUT_SECS 1000/' csrc/kernels/configs.cuh && cd .. ; \
else \
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment