赞
踩
git lfs install
git clone https://github.com/NVIDIA/TensorRT-LLM.git
cd TensorRT-LLM
git submodule update --init --recursive
make -C docker release_build
make -C docker release_run LOCAL_USER=1
pip install -r examples/bloom/requirements.txt
git lfs install
cd examples/bloom
rm -rf ./bloom/560M
mkdir -p ./bloom/560M && git clone https://huggingface.co/bigscience/bloom-560m ./bloom/560M
# Single GPU on BLOOM 560M
python convert_checkpoint.py --model_dir ./bloom/560M/ \
--dtype float16 \
--output_dir ./bloom/560M/trt_ckpt/fp16/1-gpu/
# May need to add trtllm-build to PATH, export PATH=/usr/local/bin:$PATH
trtllm-build --checkpoint_dir ./bloom/560M/trt_ckpt/fp16/1-gpu/ \
--gemm_plugin float16 \
--gpt_attention_plugin float16 \
--output_dir ./bloom/560M/trt_engines/fp16/1-gpu/
python ../summarize.py --test_trt_llm \
--hf_model_dir ./bloom/560M/ \
--data_type fp16 \
--engine_dir ./bloom/560M/trt_engines/fp16/1-gpu/
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。