install fp8 on nanotron

gistfile1.txt

conda create --prefix ./env python=3.10

module load cuda/12.1
export CUDNN_PATH=/usr/local/cuda-12.1/lib


pip install pyyaml packaging

pip install torch==2.1.2 
pip install numpy

pip install git+https://github.com/NVIDIA/TransformerEngine.git@stable

git clone git@github.com:huggingface/nanotron.git
cd nanotron
pip install -e .

pip install pytest pytest-xdist

# NOTE: keep these packages in the following version
# triton==2.1.0 nvidia-nccl-cu12==2.18.1 torch==2.1.2