Dockerfile

FROM pytorch/pytorch:2.4.0-cuda12.1-cudnn9-devel 
# FOR HF

USER root

ENV DEBIAN_FRONTEND=noninteractive
RUN apt-get update && apt-get install -y \
    git \
    cmake \
    python3 \
    python3-pip \
    python3-venv \
    python3-dev \
    python3-numpy \
    gcc \
    build-essential \
    gfortran \
    wget \
    curl \
    pkg-config \
    software-properties-common \
    zip \
    && apt-get clean && rm -rf /tmp/* /var/tmp/*

RUN apt-get update && DEBIAN_FRONTEND=noninteractive \
    apt-get install -y python3.10 python3-pip

RUN apt-get install -y libopenblas-base libopenmpi-dev

ENV TZ=Asia/Dubai
RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone


RUN useradd -m -u 1000 user
    
RUN apt-get update && apt-get install -y sudo && \
echo 'user ALL=(ALL) NOPASSWD:ALL' >> /etc/sudoers

USER user
ENV HOME=/home/user \
	PATH=/home/user/.local/bin:$PATH

RUN mkdir $HOME/app

# WORKDIR $HOME/app

RUN chown -R user:user $HOME/app   

USER user
WORKDIR $HOME/app


RUN  python3 -m pip install chromadb db-sqlite3 auto-gptq exllama sqlalchemy  
WORKDIR $HOME/app
# ENV FLASH_ATTENTION_FORCE_BUILD=TRUE
RUN python -m pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121
RUN python -m pip install  accelerate diffusers datasets timm flash-attn==2.6.1 gradio

RUN  python3 -m pip install --no-deps optimum  

#This seems to be a must : Intel Extension for PyTorch 2.4 needs to work with PyTorch 2.4.*, but PyTorch 2.2.2 is
RUN python -m pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121
RUN  python3 -m pip install -U accelerate bitsandbytes
RUN  python3 -m pip install -U git+https://github.com/huggingface/transformers


ENV PYTHONUNBUFFERED=1 	GRADIO_ALLOW_FLAGGING=never 	GRADIO_NUM_PORTS=1 	GRADIO_SERVER_NAME=0.0.0.0     GRADIO_SERVER_PORT=7860 	SYSTEM=spaces
RUN python3 -m pip  install pennylane sympy pennylane-qiskit duckdb qutip qutip-qip
WORKDIR $HOME/app

EXPOSE 8097 7842 8501 8000 6666 7860

CMD ["python", "app.py"]

# mlc-llm server HF://mlc-ai/Llama-3.2-1B-Instruct-q4f16_1-MLC