check-in dockerfile (#8)

* check-in dockerfile

* check-in dockerfile

README_zh-CN.md

@@ -58,7 +58,7 @@ pip install -e .
 
 ### 部署 [LLaMA](https://github.com/facebookresearch/llama) 服务
 
-请填写[这张表](<(https://docs.google.com/forms/d/e/1FAIpQLSfqNECQnMkycAp2jP4Z9TFX0cGR4uf7b_fBxjY_OjhJILlKGA/viewform?usp=send_form)>)，获取 LLaMA 模型权重。
+请填写[这张表](https://docs.google.com/forms/d/e/1FAIpQLSfqNECQnMkycAp2jP4Z9TFX0cGR4uf7b_fBxjY_OjhJILlKGA/viewform)，获取 LLaMA 模型权重。
 
 执行下面任一命令，可以把 LLaMA 模型部署到 NVIDIA GPU Server：
 

docker/Dockerfile

+FROM nvcr.io/nvidia/tritonserver:22.12-py3
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    rapidjson-dev libgoogle-glog-dev gdb  \
+    && rm -rf /var/lib/apt/lists/*
+
+RUN python3 -m pip install torch==1.13.1+cu117 torchvision==0.14.1+cu117 --extra-index-url https://download.pytorch.org/whl/cu117
+RUN python3 -m pip install sentencepiece cmake
+
+ENV NCCL_LAUNCH_MODE=GROUP