Skip to content
Merged
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
51 changes: 51 additions & 0 deletions applications/DeepSpeed-Chat/dockerfiles/Dockerfile-GB300
Original file line number Diff line number Diff line change
@@ -0,0 +1,51 @@
FROM nvidia/cuda:13.0.2-cudnn-devel-ubuntu22.04

ENV DEBIAN_FRONTEND=noninteractive
ENV PYTHONUNBUFFERED=1

# Install system dependencies including SSH and nvtop
RUN apt-get update && apt-get install -y \
python3.10 \
python3.10-dev \
python3-pip \
python3-pybind11 \
git \
curl \
wget \
build-essential \
openssh-server \
openssh-client \
nvtop \
pdsh \
rdma-core \
ibverbs-providers \
libibverbs-dev \
libmlx5-1 \
&& rm -rf /var/lib/apt/lists/*

# Set python3.10 as default
RUN update-alternatives --install /usr/bin/python python /usr/bin/python3.10 1 && \
update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.10 1

# Configure SSH
RUN mkdir -p /var/run/sshd && \
sed -i 's/#PermitRootLogin prohibit-password/PermitRootLogin yes/' /etc/ssh/sshd_config && \
sed -i 's/#PubkeyAuthentication yes/PubkeyAuthentication yes/' /etc/ssh/sshd_config

# Upgrade pip
RUN python -m pip install --upgrade pip setuptools wheel

WORKDIR /workspace

# Copy and install non-torch dependencies
COPY training/requirements_freeze.txt ./
RUN pip install -r requirements_freeze.txt

# Install PyTorch with CUDA 13.0 support
RUN pip install torch==2.9.1+cu130 torchvision==0.24.1 torchaudio==2.9.1 --index-url https://download.pytorch.org/whl/cu130

# Copy project code
COPY . .

CMD ["/bin/bash"]