llm / docker /docker-cuda /Dockerfile.base

Upload folder using huggingface_hub

db704cb verified 9 months ago

2.27 kB

# Start from the pytorch official image (ubuntu-22.04 + cuda-12.4.1 + python-3.11)
# https://hub.docker.com/r/pytorch/pytorch/tags
FROM pytorch/pytorch:2.6.0-cuda12.4-cudnn9-devel

# Define environments
ENV MAX_JOBS=16
ENV VLLM_WORKER_MULTIPROC_METHOD=spawn
ENV DEBIAN_FRONTEND=noninteractive
ENV NODE_OPTIONS=""
ENV PIP_ROOT_USER_ACTION=ignore

# Define installation arguments
ARG APT_SOURCE=https://mirrors.tuna.tsinghua.edu.cn/ubuntu/
ARG PIP_INDEX=https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple

# Set apt source
RUN cp /etc/apt/sources.list /etc/apt/sources.list.bak && \
    { \
    echo "deb ${APT_SOURCE} jammy main restricted universe multiverse"; \
    echo "deb ${APT_SOURCE} jammy-updates main restricted universe multiverse"; \
    echo "deb ${APT_SOURCE} jammy-backports main restricted universe multiverse"; \
    echo "deb ${APT_SOURCE} jammy-security main restricted universe multiverse"; \
    } > /etc/apt/sources.list

# Install systemctl and wget
RUN apt-get update && \
    apt-get install -y -o Dpkg::Options::="--force-confdef" systemd wget && \
    apt-get clean

# Install git and vim
RUN apt-get update && \
    apt-get install -y git vim && \
    apt-get clean

# Install gcc and g++
RUN apt-get update && \
    apt-get install -y gcc g++ && \
    apt-get clean

# Change pip source
RUN pip config set global.index-url "${PIP_INDEX}" && \
    pip config set global.extra-index-url "${PIP_INDEX}" && \
    pip install --no-cache-dir --upgrade pip packaging wheel setuptools

# Install flash-attn-2.7.4.post1 (cxx11abi=False)
RUN wget -nv https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiFALSE-cp311-cp311-linux_x86_64.whl && \
    pip install --no-cache-dir flash_attn-2.7.4.post1+cu12torch2.6cxx11abiFALSE-cp311-cp311-linux_x86_64.whl

# Install flashinfer-0.2.2.post1+cu124 (cxx11abi=False)
RUN wget -nv https://github.com/flashinfer-ai/flashinfer/releases/download/v0.2.2.post1/flashinfer_python-0.2.2.post1+cu124torch2.6-cp38-abi3-linux_x86_64.whl && \
    pip install --no-cache-dir flashinfer_python-0.2.2.post1+cu124torch2.6-cp38-abi3-linux_x86_64.whl

# Reset pip config
RUN pip config unset global.index-url && \
    pip config unset global.extra-index-url

	# Start from the pytorch official image (ubuntu-22.04 + cuda-12.4.1 + python-3.11)
	# https://hub.docker.com/r/pytorch/pytorch/tags
	FROM pytorch/pytorch:2.6.0-cuda12.4-cudnn9-devel

	# Define environments
	ENV MAX_JOBS=16
	ENV VLLM_WORKER_MULTIPROC_METHOD=spawn
	ENV DEBIAN_FRONTEND=noninteractive
	ENV NODE_OPTIONS=""
	ENV PIP_ROOT_USER_ACTION=ignore

	# Define installation arguments
	ARG APT_SOURCE=https://mirrors.tuna.tsinghua.edu.cn/ubuntu/
	ARG PIP_INDEX=https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple

	# Set apt source
	RUN cp /etc/apt/sources.list /etc/apt/sources.list.bak && \
	{ \
	echo "deb ${APT_SOURCE} jammy main restricted universe multiverse"; \
	echo "deb ${APT_SOURCE} jammy-updates main restricted universe multiverse"; \
	echo "deb ${APT_SOURCE} jammy-backports main restricted universe multiverse"; \
	echo "deb ${APT_SOURCE} jammy-security main restricted universe multiverse"; \
	} > /etc/apt/sources.list

	# Install systemctl and wget
	RUN apt-get update && \
	apt-get install -y -o Dpkg::Options::="--force-confdef" systemd wget && \
	apt-get clean

	# Install git and vim
	RUN apt-get update && \
	apt-get install -y git vim && \
	apt-get clean

	# Install gcc and g++
	RUN apt-get update && \
	apt-get install -y gcc g++ && \
	apt-get clean

	# Change pip source
	RUN pip config set global.index-url "${PIP_INDEX}" && \
	pip config set global.extra-index-url "${PIP_INDEX}" && \
	pip install --no-cache-dir --upgrade pip packaging wheel setuptools

	# Install flash-attn-2.7.4.post1 (cxx11abi=False)
	RUN wget -nv https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiFALSE-cp311-cp311-linux_x86_64.whl && \
	pip install --no-cache-dir flash_attn-2.7.4.post1+cu12torch2.6cxx11abiFALSE-cp311-cp311-linux_x86_64.whl

	# Install flashinfer-0.2.2.post1+cu124 (cxx11abi=False)
	RUN wget -nv https://github.com/flashinfer-ai/flashinfer/releases/download/v0.2.2.post1/flashinfer_python-0.2.2.post1+cu124torch2.6-cp38-abi3-linux_x86_64.whl && \
	pip install --no-cache-dir flashinfer_python-0.2.2.post1+cu124torch2.6-cp38-abi3-linux_x86_64.whl

	# Reset pip config
	RUN pip config unset global.index-url && \
	pip config unset global.extra-index-url