Skip to content
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.

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

Update docker file #629

Merged
merged 1 commit into from
Jul 16, 2024
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
41 changes: 36 additions & 5 deletions docker/Dockerfile
Original file line number Diff line number Diff line change
@@ -1,6 +1,37 @@
FROM vllm/vllm-openai
ARG CUDA_VERSION=12.4.1

RUN pip install --upgrade pip
RUN pip install "sglang[all]"
RUN pip uninstall -y triton triton-nightly && pip install --no-deps --index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/Triton-Nightly/pypi/simple/ triton-nightly
RUN pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.3/
FROM nvidia/cuda:${CUDA_VERSION}-devel-ubuntu22.04

ARG CUDA_VERSION=12.4.1
ARG PYTHON_VERSION=3

ENV DEBIAN_FRONTEND=noninteractive

RUN echo 'tzdata tzdata/Areas select America' | debconf-set-selections \
&& echo 'tzdata tzdata/Zones/America select Los_Angeles' | debconf-set-selections \
&& apt-get update -y \
&& apt-get install -y ccache software-properties-common \
&& add-apt-repository ppa:deadsnakes/ppa \
&& apt-get update -y \
&& apt-get install -y python${PYTHON_VERSION} python${PYTHON_VERSION}-dev python${PYTHON_VERSION}-venv python3-pip \
&& if [ "${PYTHON_VERSION}" != "3" ]; then update-alternatives --install /usr/bin/python3 python3 /usr/bin/python${PYTHON_VERSION} 1; fi \
&& python3 --version \
&& python3 -m pip --version

RUN apt-get update -y \
&& apt-get install -y python3-pip git curl sudo

# Workaround for https://github.com/openai/triton/issues/2507 and
# https://github.com/pytorch/pytorch/issues/107960 -- hopefully
# this won't be needed for future versions of this docker image
# or future versions of triton.
RUN ldconfig /usr/local/cuda-$(echo $CUDA_VERSION | cut -d. -f1,2)/compat/

WORKDIR /sgl-workspace

RUN pip3 install --upgrade pip
RUN pip3 install "sglang[all]"
RUN pip3 uninstall -y triton triton-nightly && pip3 install --no-deps --index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/Triton-Nightly/pypi/simple/ triton-nightly
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why use the triton-nightly whl? For example, will there be any stability issues?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We observe some random issues around triton, including this one: #548.

RUN pip3 install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.3/

ENV DEBIAN_FRONTEND=interactive