Dockerfile

FROM nvidia/cuda:12.8.1-cudnn-devel-ubuntu24.04 AS base

WORKDIR /app

ENV DEBIAN_FRONTEND=noninteractive
ENV LANG=C.UTF-8
ENV LC_ALL=C.UTF-8
ENV LD_LIBRARY_PATH=/usr/local/lib/x86_64-linux-gnu:$LD_LIBRARY_PATH

RUN apt-get update && apt-get install -y vim tmux zip unzip bzip2 wget git git-lfs build-essential libibverbs-dev ca-certificates \
    curl iproute2 libsm6 libxext6 kmod ccache libnuma-dev libssl-dev flex bison libgtk-3-dev libpango1.0-dev \
    libsoup2.4-dev libnice-dev libopus-dev libvpx-dev libx264-dev libsrtp2-dev libglib2.0-dev libdrm-dev libjpeg-dev libpng-dev \
    && apt-get clean && rm -rf /var/lib/apt/lists/* && git lfs install

# install miniconda with Python 3.12
RUN wget https://repo.anaconda.com/miniconda/Miniconda3-py312_25.9.1-1-Linux-x86_64.sh -O /tmp/miniconda.sh && \
    bash /tmp/miniconda.sh -b -p /app/miniconda && \
    rm /tmp/miniconda.sh
ENV PATH=/app/miniconda/bin:$PATH
RUN conda tos accept --override-channels --channel https://repo.anaconda.com/pkgs/main
RUN conda tos accept --override-channels --channel https://repo.anaconda.com/pkgs/r

RUN conda install conda-forge::ffmpeg=8.0.0 -y && conda clean -all -y

# install torch
RUN pip install --no-cache-dir torch==2.8.0 torchvision==0.23.0 torchaudio==2.8.0 --index-url https://download.pytorch.org/whl/cu128

RUN pip install --no-cache-dir packaging ninja cmake scikit-build-core uv meson ruff pre-commit fastapi uvicorn requests -U

RUN git clone https://github.com/vllm-project/vllm.git && cd vllm \
    && python use_existing_torch.py && pip install --no-cache-dir -r requirements/build.txt \
    && pip install --no-cache-dir --no-build-isolation -v -e .

RUN git clone https://github.com/sgl-project/sglang.git && cd sglang/sgl-kernel \
    && make build && make clean

RUN pip install --no-cache-dir diffusers transformers tokenizers accelerate safetensors opencv-python numpy imageio \
    imageio-ffmpeg einops loguru qtorch ftfy av decord matplotlib debugpy

RUN git clone https://github.com/Dao-AILab/flash-attention.git --recursive

RUN cd flash-attention && python setup.py install && rm -rf build

RUN cd flash-attention/hopper && python setup.py install && rm -rf build

RUN git clone https://github.com/ModelTC/SageAttention-1104.git --depth 1

RUN cd SageAttention-1104 && TORCH_CUDA_ARCH_LIST="8.0,8.6,8.9,9.0,12.0" EXT_PARALLEL=4 NVCC_APPEND_FLAGS="--threads 8" MAX_JOBS=32 python setup.py install && rm -rf build

RUN cd SageAttention-1104/sageattention3_blackwell && python setup.py install && rm -rf build

RUN git clone https://github.com/SandAI-org/MagiAttention.git --recursive

RUN cd MagiAttention && TORCH_CUDA_ARCH_LIST="9.0" pip install --no-cache-dir --no-build-isolation -v -e .

RUN git clone https://github.com/ModelTC/FlashVSR.git --depth 1

RUN cd FlashVSR && pip install --no-cache-dir -v -e .

COPY lightx2v_kernel /app/lightx2v_kernel

RUN git clone https://github.com/NVIDIA/cutlass.git --depth 1 && cd /app/lightx2v_kernel && MAX_JOBS=32 && CMAKE_BUILD_PARALLEL_LEVEL=4 \
    uv build --wheel \
        -Cbuild-dir=build . \
        -Ccmake.define.CUTLASS_PATH=/app/cutlass \
        --verbose \
        --color=always \
        --no-build-isolation \
    && pip install dist/*whl --force-reinstall --no-deps \
    && rm -rf /app/lightx2v_kernel && rm -rf /app/cutlass

# cloud deploy
RUN pip install --no-cache-dir aio-pika asyncpg>=0.27.0 aioboto3>=12.0.0 PyJWT alibabacloud_dypnsapi20170525==1.2.2 redis==6.4.0 tos

RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --default-toolchain stable
ENV PATH=/root/.cargo/bin:$PATH

RUN cd /opt \
    && wget https://mirrors.tuna.tsinghua.edu.cn/gnu/libiconv/libiconv-1.15.tar.gz \
    && tar zxvf libiconv-1.15.tar.gz \
    && cd libiconv-1.15 \
    && ./configure \
    && make \
    && make install \
    && rm -rf /opt/libiconv-1.15

RUN cd /opt \
    && git clone https://github.com/GStreamer/gstreamer.git -b 1.27.2 --depth 1 \
    && cd gstreamer \
    && meson setup builddir \
    && meson compile -C builddir \
    && meson install -C builddir \
    && ldconfig \
    && rm -rf /opt/gstreamer

RUN cd /opt \
    && git clone https://github.com/GStreamer/gst-plugins-rs.git -b gstreamer-1.27.2 --depth 1 \
    && cd gst-plugins-rs \
    && cargo build --package gst-plugin-webrtchttp --release \
    && install -m 644 target/release/libgstwebrtchttp.so $(pkg-config --variable=pluginsdir gstreamer-1.0)/ \
    && rm -rf /opt/gst-plugins-rs

RUN ldconfig


# q8f for base docker
RUN git clone https://github.com/KONAKONA666/q8_kernels.git --depth 1
RUN cd q8_kernels && git submodule init && git submodule update && python setup.py install && rm -rf build

# q8f for 5090 docker
# RUN git clone https://github.com/ModelTC/LTX-Video-Q8-Kernels.git --depth 1
# RUN cd LTX-Video-Q8-Kernels && git submodule init && git submodule update && python setup.py install && rm -rf build

WORKDIR /workspace