公司局域网服务器上部署无法访问[BUG] <title>

[lzy83925]

是否已有关于该错误的issue或讨论？ | Is there an existing issue / discussion for this?

• [X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions

该问题是否在FAQ中有解答？ | Is there an existing answer for this in FAQ?

• [X] 我已经搜索过FAQ | I have searched FAQ

当前行为 | Current Behavior

我们现在是在公司的局域网 GPU 服务器上部署的 QAnything.

服务器本身是能访问外网的，但是只有局域网的 IP 地址.

在启动 run.sh 的时候我选的是 remote，然后输入公网 IP 的时候我输入的是局域网的 192.168..的 IP，启动是成功的没问题，但是在公司局域网其他电脑上访问http://192.168..:5052/qanything/怎么都无法访问。这个是怎么回事儿。看到 docker ps 都是 启动 OK 的，端口也是正常映射的

期望行为 | Expected Behavior

期望能在局域网里的其他机器能正常访问 QAnything的服务

运行环境 | Environment

- OS: Ubuntu 22.04
- NVIDIA Driver:535.154.05
- CUDA:12.3
- docker:25.0.3
- docker-compose:2.24.6
- NVIDIA GPU:Tesla P100-PCIE-16GB*2
- NVIDIA GPU Memory:16GB

QAnything日志 | QAnything logs

qanything-container-local | qanything-container-local | ============================= qanything-container-local | == Triton Inference Server == qanything-container-local | ============================= qanything-container-local | qanything-container-local | NVIDIA Release 23.05 (build 61161506) qanything-container-local | Triton Server Version 2.34.0 qanything-container-local | qanything-container-local | Copyright (c) 2018-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. qanything-container-local | qanything-container-local | Various files include modifications (c) NVIDIA CORPORATION & AFFILIATES. All rights reserved. qanything-container-local | qanything-container-local | This container image and its contents are governed by the NVIDIA Deep Learning Container License. qanything-container-local | By pulling and using the container, you accept the terms and conditions of this license: qanything-container-local | https://developer.nvidia.com/ngc/nvidia-deep-learning-container-license qanything-container-local | qanything-container-local | llm_api is set to [local] qanything-container-local | device_id is set to [0,1] qanything-container-local | runtime_backend is set to [default] qanything-container-local | model_name is set to [-t] qanything-container-local | conv_template is set to [] qanything-container-local | tensor_parallel is set to [1] qanything-container-local | gpu_memory_utilization is set to [0.81] qanything-container-local | checksum 77275c133c7dfcf1553a7b5ef043168d qanything-container-local | default_checksum 77275c133c7dfcf1553a7b5ef043168d qanything-container-local | qanything-container-local | [notice] A new release of pip is available: 23.3.2 -> 24.0 qanything-container-local | [notice] To update, run: python3 -m pip install --upgrade pip qanything-container-local | GPU ID: 0, 1 qanything-container-local | GPU1 Model: Tesla P100-PCIE-16GB qanything-container-local | Compute Capability: null qanything-container-local | OCR_USE_GPU=False because null < 7.5 qanything-container-local | ==================================================== qanything-container-local | ******************** 重要提示 ******************** qanything-container-local | ==================================================== qanything-container-local | qanything-container-local | 默认后端为FasterTransformer，仅支持Nvidia RTX 30系列或40系列显卡，您的显卡型号为： Tesla P100-PCIE-16GB, 不在支持列表中，将自动为您切换后端： qanything-container-local | 根据匹配算法，已自动为您切换为huggingface后端 qanything-container-local | 您当前的显存为 16384 MiB 推荐部署小于等于7B的大模型 qanything-container-local | 为了防止显存溢出，tokens上限默认设置为2300 qanything-container-local | The triton server for embedding and reranker will start on 1 GPUs qanything-container-local | The -t folder does not exist under QAnything/assets/custom_models/. Please check your setup. qanything-container-local | 在QAnything/assets/custom_models/下不存在-t文件夹。请检查您的模型文件。

复现方法 | Steps To Reproduce

bash ./run.sh -c local -i 0,1 -b default

模式选：remote 输入公网 IP：192.168..

备注 | Anything else?

No response