hopper架构上安装后使用报错

[onecatcn]

---

温馨提示：根据社区不完全统计，按照模板提问，可以加快回复和解决问题的速度

---

环境

• 【FastDeploy版本】： fastdeploy_gpu_python-1.0.7-cp310-cp310-manylinux1_x86_64.whl
• 【编译命令】pip install
• 【系统平台】: Linux x64(centOS 7)
• 【硬件】： Nvidia Hopper GPU， CUDA 12.0 CUDNN 8.3
• 【编译语言】：Python 3.10

问题日志及出现问题的操作流程

代码：https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/cn/quick_start/models/python.md#1-%E8%8E%B7%E5%8F%96%E6%A8%A1%E5%9E%8B%E5%92%8C%E6%B5%8B%E8%AF%95%E5%9B%BE%E5%83%8F

`import fastdeploy as fd

model_url = "https://bj.bcebos.com/paddlehub/fastdeploy/ppyoloe_crn_l_300e_coco.tgz" image_url = "https://bj.bcebos.com/fastdeploy/tests/test_det.jpg" fd.download_and_decompress(model_url, path=".") fd.download(image_url, path=".")`

报错信息

(paddle-2.6.1) [root@Hopper-Paddle-BBC test]# python fd1.py Traceback (most recent call last): File "/root/miniconda3/envs/paddle-2.6.1/lib/python3.10/site-packages/fastdeploy/c_lib_wrap.py", line 164, in from .libs.fastdeploy_main import * ImportError: libcudart.so.11.0: cannot open shared object file: No such file or directory

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/test/fd1.py", line 1, in import fastdeploy as fd File "/root/miniconda3/envs/paddle-2.6.1/lib/python3.10/site-packages/fastdeploy/init.py", line 122, in from .c_lib_wrap import ( File "/root/miniconda3/envs/paddle-2.6.1/lib/python3.10/site-packages/fastdeploy/c_lib_wrap.py", line 166, in raise RuntimeError(f"FastDeploy initalized failed! Error: {e}") RuntimeError: FastDeploy initalized failed! Error: libcudart.so.11.0: cannot open shared object file: No such file or directory

[Jiang-Jia-Jun]

目前未支持高版本GPU显卡，如要支持，需自行更新内部的Paddle版本

[tymons]

某处有这方面的说明吗，您能建议从哪里开始吗