# if from main:
# (base) ubuntu@compute-permanent-node-406:~/lmdeploy$ docker build . -f docker/Dockerfile -t internvlmain --no-cache
# then change below "FROM openmmlab/lmdeploy:latest" to "FROM internvlmain"

# docker build - < Dockerfile.internvl -t internvl
FROM openmmlab/lmdeploy:latest

RUN apt-get update && apt-get install -y python3 python3-pip git

WORKDIR /app

RUN pip3 uninstall pkg_resources -y
RUN pip3 install --upgrade pip
RUN pip3 install --upgrade setuptools==66.1.1
RUN pip3 uninstall -y ninja && pip3 install ninja
RUN CUDA_HOME=/usr/local/cuda-11.8/ PIP_EXTRA_INDEX_URL=https://download.pytorch.org/whl/cu118 pip3 install timm xformers triton==2.1.0 transformers
RUN MAX_JOBS=4 CUDA_HOME=/usr/local/cuda-11.8/ PIP_EXTRA_INDEX_URL=https://download.pytorch.org/whl/cu118 FLASH_ATTENTION_FORCE_BUILD=TRUE pip3 install flash-attn==2.5.2 --no-build-isolation
RUN pip3 install git+https://github.com/haotian-liu/LLaVA.git --no-deps

COPY . .

CMD ["lmdeploy", "serve", "api_server", "OpenGVLab/InternVL-Chat-V1-5"]