FasterTransformer4CodeFuse

pip install --no-cache-dir pybind11==2.6.2 transformers accelerate sentencepiece

echo "export pybind11_DIR=/opt/conda/lib/python3.8/site-packages/pybind11/share/cmake/pybind11/" >> ~/.bashrc
export pybind11_DIR=/opt/conda/lib/python3.8/site-packages/pybind11/share/cmake/pybind11/

mkdir build ; cd build
export TORCH_PYTHON_LIBRARIES=/opt/conda/lib/python3.8/site-packages/torch/lib/libtorch_python.so
cmake -DCMAKE_BUILD_TYPE=Release -DSM="80;75" -DBUILD_PYT=ON -DSPARSITY_SUPPORT=OFF -DMEASURE_BUILD_TIME=ON \
      -DBUILD_CUTLASS_MIXED_GEMM=ON -DBUILD_MULTI_GPU=ON -DBUILD_TRT=OFF \
      -DENABLE_FP8=OFF -DBUILD_PYBIND=ON -DTORCH_PYTHON_LIBRARIES=${TORCH_PYTHON_LIBRARIES} ..
make -j"$(grep -c ^processor /proc/cpuinfo)"

export MODEL_NAME=codefuse
export TENSOR_PARA_SIZE=2

python ../examples/pytorch/codefuse/huggingface_convert.py \
       -o ../models/${MODEL_NAME}/fastertransformer \
       -i ../models/${MODEL_NAME}/transformers \
       -infer_gpu_num ${TENSOR_PARA_SIZE} \
       -processes 20 \
       -weight_data_type fp16 \
       -model_name gptneox

export MODEL_NAME=codefuse
export TENSOR_PARA_SIZE=2

python ../examples/pytorch/codefuse/quant_and_save.py \
       --in_dir ../models/${MODEL_NAME}/fastertransformer/${TENSOR_PARA_SIZE}-gpu \
       --out_dir ../models/${MODEL_NAME}/fastertransformer/${TENSOR_PARA_SIZE}-gpu_int8 \
       --lib_path ../build/lib/libth_common.so \
       --tensor_para_size ${TENSOR_PARA_SIZE} \
       --use_gptj_residual \
       --data_type fp16

export MODEL_NAME=codefuse

# fp16 1gpu
python ../examples/pytorch/codefuse/codefuse_example.py \
       --ckpt_path ../models/${MODEL_NAME}/fastertransformer/1-gpu \
       --tokenizer_path ../models/${MODEL_NAME}/transformers

# int8 1gpu
python ../examples/pytorch/codefuse/codefuse_example.py \
       --ckpt_path ../models/${MODEL_NAME}/fastertransformer/1-gpu_int8 \
       --tokenizer_path ../models/${MODEL_NAME}/transformers \
       --int8_mode 1 \
       --enable_int8_weights 1

# fp16 2gpus
torchrun --nproc_per_node 2 ../examples/pytorch/codefuse/codefuse_example.py \
         --world_size 2 \
         --ckpt_path ../models/${MODEL_NAME}/fastertransformer/2-gpu \
         --tokenizer_path ../models/${MODEL_NAME}/transformers

# int8 2gpus
torchrun --nproc_per_node 2 ../examples/pytorch/codefuse/codefuse_example.py \
         --world_size 2 \
         --ckpt_path ../models/${MODEL_NAME}/fastertransformer/2-gpu_int8 \
         --tokenizer_path ../models/${MODEL_NAME}/transformers \
         --int8_mode 1 \
         --enable_int8_weights 1