Jadyn

同样的问题, 最新的代码, 使用docker-compose vllm部署, GPU只有embedding模型的占用, 日志也不报错. 请求404 LOG ```log ============= == PyTorch == ============= NVIDIA Release 23.10 (build 71422337) PyTorch Version 2.1.0a0+32f93b1 Container image Copyright (c) 2023, NVIDIA CORPORATION &...

 https://github.com/xusenlinzy/api-for-open-llm/blob/e46e48056a02ffbd90e0dfe4bc2f803df1e7e4e1/api/models.py#L100 此处加了一行打印异常日志 今天下午才拉取的代码, 重新构建的镜像, 期间没有任何报错 ``` docker build -f docker/Dockerfile.vllm -t llm-api:vllm . ``` 可能相关的问题 https://github.com/vllm-project/vllm/issues/3528

You can add an `ActionFilter` to validate the model using `FluentValidate`. https://github.com/JadynWong/AbpIssue/commit/eec5290d5c1ac20c0ae7abedb2141fade058e61b#diff-e7c9195c610944a0f739a7bca415e73d593bdd5712205d1b8322af4aedb8e0dd > Refer https://github.com/SharpGrip/FluentValidation.AutoValidation Only basic tests were performed. It would be better if abp could provide built-in support.

https://github.com/microsoft/chat-copilot