Compare commits

...

3 Commits

Author SHA1 Message Date
728c365e4d Use uv to install python in Dockerfile
Signed-off-by: mgoin <mgoin64@gmail.com>
2025-10-02 11:05:47 -04:00
be8921fbba Change size of single CUDA graph for CI to 4 (#26089)
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
2025-10-02 14:14:28 +00:00
d4e7a1152d Update base image to 22.04 (jammy) (#26065)
Signed-off-by: Huy Do <huydhn@gmail.com>
2025-10-02 05:48:04 -07:00
4 changed files with 15 additions and 55 deletions

View File

@ -13,8 +13,8 @@ ARG PYTHON_VERSION=3.12
# private registries that use a different repository naming conventions.
#
# Example:
# docker build --build-arg BUILD_BASE_IMAGE=registry.acme.org/mirror/nvidia/cuda:${CUDA_VERSION}-devel-ubuntu20.04
ARG BUILD_BASE_IMAGE=nvidia/cuda:${CUDA_VERSION}-devel-ubuntu20.04
# docker build --build-arg BUILD_BASE_IMAGE=registry.acme.org/mirror/nvidia/cuda:${CUDA_VERSION}-devel-ubuntu22.04
ARG BUILD_BASE_IMAGE=nvidia/cuda:${CUDA_VERSION}-devel-ubuntu22.04
# TODO: Restore to base image after FlashInfer AOT wheel fixed
ARG FINAL_BASE_IMAGE=nvidia/cuda:${CUDA_VERSION}-devel-ubuntu22.04
@ -79,31 +79,11 @@ ARG DEADSNAKES_MIRROR_URL
ARG DEADSNAKES_GPGKEY_URL
ARG GET_PIP_URL
# Install Python and other dependencies
# Install minimal dependencies
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 git curl sudo \
&& if [ ! -z ${DEADSNAKES_MIRROR_URL} ] ; then \
if [ ! -z "${DEADSNAKES_GPGKEY_URL}" ] ; then \
mkdir -p -m 0755 /etc/apt/keyrings ; \
curl -L ${DEADSNAKES_GPGKEY_URL} | gpg --dearmor > /etc/apt/keyrings/deadsnakes.gpg ; \
sudo chmod 644 /etc/apt/keyrings/deadsnakes.gpg ; \
echo "deb [signed-by=/etc/apt/keyrings/deadsnakes.gpg] ${DEADSNAKES_MIRROR_URL} $(lsb_release -cs) main" > /etc/apt/sources.list.d/deadsnakes.list ; \
fi ; \
else \
for i in 1 2 3; do \
add-apt-repository -y ppa:deadsnakes/ppa && break || \
{ echo "Attempt $i failed, retrying in 5s..."; sleep 5; }; \
done ; \
fi \
&& apt-get update -y \
&& apt-get install -y python${PYTHON_VERSION} python${PYTHON_VERSION}-dev python${PYTHON_VERSION}-venv \
&& update-alternatives --install /usr/bin/python3 python3 /usr/bin/python${PYTHON_VERSION} 1 \
&& update-alternatives --set python3 /usr/bin/python${PYTHON_VERSION} \
&& ln -sf /usr/bin/python${PYTHON_VERSION}-config /usr/bin/python3-config \
&& curl -sS ${GET_PIP_URL} | python${PYTHON_VERSION} \
&& python3 --version && python3 -m pip --version
&& apt-get install -y ccache software-properties-common git curl sudo
ARG PIP_INDEX_URL UV_INDEX_URL
ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL
@ -111,9 +91,9 @@ ARG PYTORCH_CUDA_INDEX_BASE_URL
ARG PYTORCH_CUDA_NIGHTLY_INDEX_BASE_URL
ARG PIP_KEYRING_PROVIDER UV_KEYRING_PROVIDER
# Install uv for faster pip installs
RUN --mount=type=cache,target=/root/.cache/uv \
python3 -m pip install uv
# Install uv and Python
COPY --from=ghcr.io/astral-sh/uv:0.8.22 /uv /uvx /bin/
RUN uv python install ${PYTHON_VERSION} --default --verbose
# This timeout (in seconds) is necessary when installing some dependencies via uv since it's likely to time out
# Reference: https://github.com/astral-sh/uv/pull/1694
@ -296,32 +276,12 @@ ARG GET_PIP_URL
RUN PYTHON_VERSION_STR=$(echo ${PYTHON_VERSION} | sed 's/\.//g') && \
echo "export PYTHON_VERSION_STR=${PYTHON_VERSION_STR}" >> /etc/environment
# Install Python and other dependencies
# Install minimal dependencies
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 git curl wget sudo vim python3-pip \
&& apt-get install -y ffmpeg libsm6 libxext6 libgl1 \
&& if [ ! -z ${DEADSNAKES_MIRROR_URL} ] ; then \
if [ ! -z "${DEADSNAKES_GPGKEY_URL}" ] ; then \
mkdir -p -m 0755 /etc/apt/keyrings ; \
curl -L ${DEADSNAKES_GPGKEY_URL} | gpg --dearmor > /etc/apt/keyrings/deadsnakes.gpg ; \
sudo chmod 644 /etc/apt/keyrings/deadsnakes.gpg ; \
echo "deb [signed-by=/etc/apt/keyrings/deadsnakes.gpg] ${DEADSNAKES_MIRROR_URL} $(lsb_release -cs) main" > /etc/apt/sources.list.d/deadsnakes.list ; \
fi ; \
else \
for i in 1 2 3; do \
add-apt-repository -y ppa:deadsnakes/ppa && break || \
{ echo "Attempt $i failed, retrying in 5s..."; sleep 5; }; \
done ; \
fi \
&& apt-get update -y \
&& apt-get install -y python${PYTHON_VERSION} python${PYTHON_VERSION}-dev python${PYTHON_VERSION}-venv libibverbs-dev \
&& update-alternatives --install /usr/bin/python3 python3 /usr/bin/python${PYTHON_VERSION} 1 \
&& update-alternatives --set python3 /usr/bin/python${PYTHON_VERSION} \
&& ln -sf /usr/bin/python${PYTHON_VERSION}-config /usr/bin/python3-config \
&& curl -sS ${GET_PIP_URL} | python${PYTHON_VERSION} \
&& python3 --version && python3 -m pip --version
&& apt-get install -y ccache software-properties-common git curl wget sudo vim \
&& apt-get install -y ffmpeg libsm6 libxext6 libgl1
ARG PIP_INDEX_URL UV_INDEX_URL
ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL
@ -329,9 +289,9 @@ ARG PYTORCH_CUDA_INDEX_BASE_URL
ARG PYTORCH_CUDA_NIGHTLY_INDEX_BASE_URL
ARG PIP_KEYRING_PROVIDER UV_KEYRING_PROVIDER
# Install uv for faster pip installs
RUN --mount=type=cache,target=/root/.cache/uv \
python3 -m pip install uv
# Install uv and Python
COPY --from=ghcr.io/astral-sh/uv:0.8.22 /uv /uvx /bin/
RUN uv python install ${PYTHON_VERSION} --default --verbose
# This timeout (in seconds) is necessary when installing some dependencies via uv since it's likely to time out
# Reference: https://github.com/astral-sh/uv/pull/1694

View File

@ -6,7 +6,7 @@ ARG CUDA_VERSION=12.8.0
#
#################### BASE BUILD IMAGE ####################
# prepare basic build environment
FROM nvidia/cuda:${CUDA_VERSION}-devel-ubuntu20.04 AS base
FROM nvidia/cuda:${CUDA_VERSION}-devel-ubuntu22.04 AS base
ARG CUDA_VERSION=12.8.0
ARG PYTHON_VERSION=3.12
ARG TARGETPLATFORM

Binary file not shown.

Before

Width:  |  Height:  |  Size: 119 KiB

After

Width:  |  Height:  |  Size: 127 KiB

View File

@ -732,7 +732,7 @@ class VllmRunner:
set_default_torch_num_threads(default_torch_num_threads))
if not kwargs.get("compilation_config", None):
kwargs["compilation_config"] = {"cudagraph_capture_sizes": [8]}
kwargs["compilation_config"] = {"cudagraph_capture_sizes": [4]}
with init_ctx:
self.llm = LLM(