Skip to content

[CUDA] [CI] Add cu124 docker images #125944

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
nWEIdia wants to merge 6 commits into from
Closed

[CUDA] [CI] Add cu124 docker images #125944

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
d498107
Build cu124 related docker images
nWEIdia May 10, 2024
6927acf
use ucc v1.2.0
nWEIdia May 10, 2024
6f5d79e
Change ucc to v1.3.0
nWEIdia May 10, 2024
b5b8f25
Update install_cudnn to support cuda12.4 and cudnn 8.9.7.29
nWEIdia May 10, 2024
0135402
Extend cusparselt to download for cu124
nWEIdia May 11, 2024
198cba4
Update ucc commit to be consistent with the version that was tested
nWEIdia May 14, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
47 changes: 45 additions & 2 deletions .ci/docker/build.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -84,13 +84,27 @@ fi
# CMake 3.18 is needed to support CUDA17 language variant
CMAKE_VERSION=3.18.5

_UCX_COMMIT=00bcc6bb18fc282eb160623b4c0d300147f579af
_UCC_COMMIT=7cb07a76ccedad7e56ceb136b865eb9319c258ea
_UCX_COMMIT=7bb2722ff2187a0cad557ae4a6afa090569f83fb
_UCC_COMMIT=20eae37090a4ce1b32bcce6144ccad0b49943e0b

# It's annoying to rename jobs every time you want to rewrite a
# configuration, so we hardcode everything here rather than do it
# from scratch
case "$image" in
pytorch-linux-focal-cuda12.4-cudnn8-py3-gcc9)
CUDA_VERSION=12.4.0
CUDNN_VERSION=8
ANACONDA_PYTHON_VERSION=3.10
GCC_VERSION=9
PROTOBUF=yes
DB=yes
VISION=yes
KATEX=yes
UCX_COMMIT=${_UCX_COMMIT}
UCC_COMMIT=${_UCC_COMMIT}
CONDA_CMAKE=yes
TRITON=yes
;;
pytorch-linux-focal-cuda12.1-cudnn8-py3-gcc9)
CUDA_VERSION=12.1.1
CUDNN_VERSION=8
Expand All @@ -105,6 +119,21 @@ case "$image" in
CONDA_CMAKE=yes
TRITON=yes
;;
pytorch-linux-focal-cuda12.4-cudnn8-py3-gcc9-inductor-benchmarks)
CUDA_VERSION=12.4.0
CUDNN_VERSION=8
ANACONDA_PYTHON_VERSION=3.10
GCC_VERSION=9
PROTOBUF=yes
DB=yes
VISION=yes
KATEX=yes
UCX_COMMIT=${_UCX_COMMIT}
UCC_COMMIT=${_UCC_COMMIT}
CONDA_CMAKE=yes
TRITON=yes
INDUCTOR_BENCHMARKS=yes
;;
pytorch-linux-focal-cuda12.1-cudnn8-py3-gcc9-inductor-benchmarks)
CUDA_VERSION=12.1.1
CUDNN_VERSION=8
Expand Down Expand Up @@ -134,6 +163,20 @@ case "$image" in
CONDA_CMAKE=yes
TRITON=yes
;;
pytorch-linux-focal-cuda12.4-cudnn8-py3-gcc9)
CUDA_VERSION=12.4.0
CUDNN_VERSION=8
ANACONDA_PYTHON_VERSION=3.10
GCC_VERSION=9
PROTOBUF=yes
DB=yes
VISION=yes
KATEX=yes
UCX_COMMIT=${_UCX_COMMIT}
UCC_COMMIT=${_UCC_COMMIT}
CONDA_CMAKE=yes
TRITON=yes
;;
pytorch-linux-focal-cuda12.1-cudnn8-py3-gcc9)
CUDA_VERSION=12.1.1
CUDNN_VERSION=8
Expand Down
5 changes: 4 additions & 1 deletion .ci/docker/common/install_cudnn.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,10 @@ if [[ ${CUDNN_VERSION} == 8 ]]; then
# cuDNN license: https://developer.nvidia.com/cudnn/license_agreement
mkdir tmp_cudnn
pushd tmp_cudnn
if [[ ${CUDA_VERSION:0:4} == "12.1" ]]; then
if [[ ${CUDA_VERSION:0:4} == "12.4" ]]; then
CUDNN_NAME="cudnn-linux-x86_64-8.9.7.29_cuda12-archive"
curl --retry 3 -OLs https://developer.download.nvidia.com/compute/cudnn/redist/cudnn/linux-x86_64/${CUDNN_NAME}.tar.xz
elif [[ ${CUDA_VERSION:0:4} == "12.1" ]]; then
CUDNN_NAME="cudnn-linux-x86_64-8.9.2.26_cuda12-archive"
curl --retry 3 -OLs https://developer.download.nvidia.com/compute/cudnn/redist/cudnn/linux-x86_64/${CUDNN_NAME}.tar.xz
elif [[ ${CUDA_VERSION:0:4} == "11.8" ]]; then
Expand Down
11 changes: 8 additions & 3 deletions .ci/docker/common/install_cusparselt.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,9 +5,14 @@ set -ex
# cuSPARSELt license: https://docs.nvidia.com/cuda/cusparselt/license.html
mkdir tmp_cusparselt && cd tmp_cusparselt

if [[ ${CUDA_VERSION:0:4} == "12.1" ]]; then
CUSPARSELT_NAME="libcusparse_lt-linux-x86_64-0.5.2.1-archive"
curl --retry 3 -OLs https://developer.download.nvidia.com/compute/cusparselt/redist/libcusparse_lt/linux-x86_64/${CUSPARSELT_NAME}.tar.xz
if [[ ${CUDA_VERSION:0:4} =~ ^12\.[1-4]$ ]]; then
arch_path='sbsa'
export TARGETARCH=${TARGETARCH:-$(uname -m)}
if [ ${TARGETARCH} = 'amd64' ] || [ "${TARGETARCH}" = 'x86_64' ]; then
arch_path='x86_64'
fi
CUSPARSELT_NAME="libcusparse_lt-linux-${arch_path}-0.5.2.1-archive"
curl --retry 3 -OLs https://developer.download.nvidia.com/compute/cusparselt/redist/libcusparse_lt/linux-${arch_path}/${CUSPARSELT_NAME}.tar.xz
elif [[ ${CUDA_VERSION:0:4} == "11.8" ]]; then
CUSPARSELT_NAME="libcusparse_lt-linux-x86_64-0.4.0.7-archive"
curl --retry 3 -OLs https://developer.download.nvidia.com/compute/cusparselt/redist/libcusparse_lt/linux-x86_64/${CUSPARSELT_NAME}.tar.xz
Expand Down
1 change: 1 addition & 0 deletions .ci/docker/ubuntu-cuda/Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -152,6 +152,7 @@ RUN rm install_cusparselt.sh
RUN if [ -h /usr/local/cuda-11.6/cuda-11.6 ]; then rm /usr/local/cuda-11.6/cuda-11.6; fi
RUN if [ -h /usr/local/cuda-11.7/cuda-11.7 ]; then rm /usr/local/cuda-11.7/cuda-11.7; fi
RUN if [ -h /usr/local/cuda-12.1/cuda-12.1 ]; then rm /usr/local/cuda-12.1/cuda-12.1; fi
RUN if [ -h /usr/local/cuda-12.1/cuda-12.4 ]; then rm /usr/local/cuda-12.1/cuda-12.4; fi

USER jenkins
CMD ["bash"]
2 changes: 2 additions & 0 deletions .github/workflows/docker-builds.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,6 +38,8 @@ jobs:
matrix:
runner: [linux.12xlarge]
docker-image-name: [
pytorch-linux-focal-cuda12.4-cudnn8-py3-gcc9,
pytorch-linux-focal-cuda12.4-cudnn8-py3-gcc9-inductor-benchmarks,
pytorch-linux-focal-cuda12.1-cudnn8-py3-gcc9,
pytorch-linux-focal-cuda12.1-cudnn8-py3-gcc9-inductor-benchmarks,
pytorch-linux-focal-cuda11.8-cudnn8-py3-gcc9,
Expand Down