add trt docker file && add warning for ascend

recipes/finetune/ascend/README.md

@@ -1,5 +1,5 @@
 # Fine-tuning Qwen by Ascend NPU
-Below, we provide a simple example to show how to finetune Qwen by Ascend NPU. You can also refer to the official [mindformers](https://gitee.com/mindspore/mindformers/blob/dev/research/qwen/qwen.md) for detailed usage.
+Below, we provide a simple example to show how to finetune Qwen by Ascend NPU. Currently, fine-tuning and inference are supported for Qwen 7B and 14B models. You can also refer to the official [mindformers](https://gitee.com/mindspore/mindformers/blob/dev/research/qwen/qwen.md) for detailed usage.
 
 ## Environment Requirement
 
@@ -137,6 +137,7 @@ python research/qwen/run_qwen.py \
     --predict_data '比较适合深度学习入门的书籍有' \
     --run_mode predict \
     --load_checkpoint output/merged_model/rank_0/checkpoint_0.ckpt \
+    --vocab_file Qwen/Qwen-7B-Chat/qwen.tiktoken \
     --auto_trans_ckpt False \
     --device_id 0
 ```

recipes/inference/tensorrt/docker/Dockerfile

@@ -0,0 +1,14 @@
+FROM nvidia/cuda:12.1.0-devel-ubuntu22.04
+
+RUN apt-get update && \
+    apt-get -y install python3.10 python3-pip openmpi-bin libopenmpi-dev git && \
+    rm -rf /var/lib/apt/lists/*
+
+RUN pip install tensorrt_llm==0.8.0.dev2024011601 -U --no-cache-dir --pre --extra-index-url https://pypi.nvidia.com
+
+RUN pip install --no-cache-dir modelscope==1.11.1
+
+RUN git clone https://github.com/NVIDIA/TensorRT-LLM.git && \
+    cd TensorRT-LLM && \ 
+    git checkout c89653021e66ca78c55f02b366f404455bc12e8d && \
+    pip install --no-cache-dir -r examples/qwen/requirements.txt