Skip to content
Open
Changes from all commits
Commits
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
10 changes: 2 additions & 8 deletions images/runtime/training/py312-cuda128-torch280/Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -34,9 +34,7 @@ ENV CUDA_VERSION=12.8.0 \

# Ref: https://gitlab.com/nvidia/container-images/cuda/-/blob/master/dist/12.8.0/ubi9/base/Dockerfile
# nvcc is required for Flash Attention
RUN dnf config-manager \
--add-repo https://developer.download.nvidia.com/compute/cuda/repos/rhel9/x86_64/cuda-rhel9.repo \
&& dnf install -y \
RUN dnf install -y \
--disablerepo=rhel-9-for-x86_64-baseos-rpms \
--disablerepo=rhel-9-for-x86_64-appstream-rpms \
cuda-cudart-12-8-${NV_CUDA_CUDART_VERSION} \
Expand All @@ -50,11 +48,7 @@ ENV CUDA_HOME="/usr/local/cuda" \
PATH="/usr/local/nvidia/bin:${CUDA_HOME}/bin:${PATH}" \
LD_LIBRARY_PATH="/usr/local/nvidia/lib:/usr/local/nvidia/lib64:$CUDA_HOME/lib64:$CUDA_HOME/extras/CUPTI/lib64:$LD_LIBRARY_PATH"

# Install InfiniBand and RDMA packages
RUN dnf config-manager \
--add-repo https://linux.mellanox.com/public/repo/mlnx_ofed/latest/rhel9.5/mellanox_mlnx_ofed.repo

RUN dnf install -y --disablerepo="*" --enablerepo="cuda-rhel9-x86_64,mlnx_ofed_24.10-1.1.4.0_base,ubi-9-appstream-rpms,ubi-9-baseos-rpms" \
RUN dnf install -y --disablerepo="*" --enablerepo="cuda-rhel9-x86_64,ubi-9-appstream-rpms,ubi-9-baseos-rpms" \
libibverbs-utils \
infiniband-diags \
libibumad3 \
Expand Down