You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
![]() |
9 months ago | |
---|---|---|
.idea | 2 years ago | |
.gitignore | 1 year ago | |
README.md | 1 year ago | |
articles_directory_predict.py | 1 year ago | |
config_llama_api.py | 2 years ago | |
flask_batch.py | 2 years ago | |
flask_predict.py | 2 years ago | |
flask_test.py | 2 years ago | |
gen_paper.py | 2 years ago | |
gunicorn_config.py | 1 year ago | |
img.png | 2 years ago | |
img_1.png | 2 years ago | |
mistral_api.py | 9 months ago | |
mistral_model_predict_vllm.py | 1 year ago | |
predict.py | 2 years ago | |
requirements.txt | 1 year ago | |
run_api_gunicorn.sh | 1 year ago | |
run_model.sh | 1 year ago | |
run_model_predict.sh | 2 years ago | |
tokenizer.py | 2 years ago | |
vllm_predict_batch.py | 2 years ago | |
yace.py | 2 years ago | |
yace2.py | 2 years ago | |
yuce3.py | 2 years ago | |
测试并发性能.py | 1 year ago | |
测试并发请求.py | 1 year ago |
README.md
安装环境
conda create -n vllm python=3.8
pip install -r requirements.txt
启动项目
conda activate vllm
bash run_api_nohup.sh
bash run_model.sh
测试
curl -H "Content-Type: application/json" -X POST -d '{"texts": "User: 你好\nAssistant:"}' http://192.168.31.149:12000/predict
curl -H "Content-Type: application/json" -X POST -d '{"id": "b412fc98-bdd7-11ee-8d23-d5e5c66dd02e"}' http://192.168.31.149:12000/search
返回"status_code"不出现 400 则调用成功