INSTALLATION.md

🛠️ Installation

• Clone this repository:

  git clone https://github.com/OpenGVLab/InternVL.git

• Create a conda virtual environment and activate it:

  conda create -n internvl python=3.9 -y
  conda activate internvl

• Install dependencies using requirements.txt:

  pip install -r requirements.txt

  By default, our requirements.txt file includes the following dependencies:

  • -r requirements/internvl_chat.txt
  • -r requirements/streamlit_demo.txt
  • -r requirements/classification.txt
  • -r requirements/segmentation.txt

  The clip_benchmark.txt is not included in the default installation. If you require the clip_benchmark functionality, please install it manually by running the following command:

  pip install -r requirements/clip_benchmark.txt

Additional Instructions

• Install flash-attn==2.3.6:

  pip install flash-attn==2.3.6 --no-build-isolation

  Alternatively you can compile from source:

  git clone https://github.com/Dao-AILab/flash-attention.git
  cd flash-attention
  git checkout v2.3.6
  python setup.py install

• Install mmcv-full==1.6.2 (optional, for segmentation):

  pip install -U openmim
  mim install mmcv-full==1.6.2

• Install apex (optional, for segmentation):

  git clone https://github.com/NVIDIA/apex.git
  git checkout 2386a912164b0c5cfcd8be7a2b890fbac5607c82  # https://github.com/NVIDIA/apex/issues/1735
  pip install -v --disable-pip-version-check --no-cache-dir --no-build-isolation --config-settings "--build-option=--cpp_ext" --config-settings "--build-option=--cuda_ext" ./

  If you encounter ModuleNotFoundError: No module named 'fused_layer_norm_cuda', it is because apex's CUDA extensions are not being installed successfully. You can try uninstalling apex and the code will default to the PyTorch version of RMSNorm. Alternatively, if you prefer using apex, try adding a few lines to setup.py and then recompiling.