update std

README.md

@@ -69,7 +69,7 @@ python offline_inference.py
 ### 离线批量推理性能测试
 1、指定输入输出
 ```bash
-python benchmark_throughput.py -num-prompts 1 --input-len 32 --output-len 128 --model meta-llama/Llama-2-7b-chat-hf -tp 1 --trust-remote-code --enforce-eager --dtype float16
+python benchmark_throughput.py --num-prompts 1 --input-len 32 --output-len 128 --model meta-llama/Llama-2-7b-chat-hf -tp 1 --trust-remote-code --enforce-eager --dtype float16
 ```
 其中`--num-prompts`是batch数，`--input-len`是输入seqlen，`--output-len`是输出token长度，`--model`为模型路径，`-tp`为使用卡数，`dtype="float16"`为推理数据类型，如果模型权重是bfloat16,需要修改为float16推理。若指定`--output-len  1`即为首字延迟。
 
@@ -80,7 +80,7 @@ wget https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/r
 ```
 
 ```bash
-python benchmark_throughput.py -num-prompts 1 --model meta-llama/Llama-2-7b-chat-hf --dataset ShareGPT_V3_unfiltered_cleaned_split.json -tp 1 --trust-remote-code --enforce-eager --dtype float16
+python benchmark_throughput.py --num-prompts 1 --model meta-llama/Llama-2-7b-chat-hf --dataset ShareGPT_V3_unfiltered_cleaned_split.json -tp 1 --trust-remote-code --enforce-eager --dtype float16
 ```
 其中`--num-prompts`是batch数，`--model`为模型路径，`--dataset`为使用的数据集，`-tp`为使用卡数，`dtype="float16"`为推理数据类型，如果模型权重是bfloat16,需要修改为float16推理。
 
@@ -145,7 +145,7 @@ curl http://localhost:8000/v1/chat/completions \
 Prompt: 'I believe the meaning of life is', Generated text: ' to find purpose, happiness, and fulfillment. Here are some reasons why:\n\n1. Purpose: Having a sense of purpose gives life meaning and direction. It helps individuals set goals and work towards achieving them, which can lead to a sense of accomplishment and fulfillment.\n2. Happiness: Happiness is a fundamental aspect of life that brings joy and satisfaction.
 ```
 
-## 精度
+### 精度
 无
 
 ## 应用场景

model.properties

@@ -7,4 +7,4 @@ modelDescription=LLama是一个基础语言模型的集合,参数范围从7B到7
 # 应用场景
 appScenario=推理,对话问答,金融,科研,教育
 # 框架类型
-frameType=llama_vllm
+frameType=vllm