Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

升级ppdiffusers 使用paddle_tensorrt后端报错 #2330

Closed
co63oc opened this issue Dec 20, 2023 · 1 comment
Closed

升级ppdiffusers 使用paddle_tensorrt后端报错 #2330

co63oc opened this issue Dec 20, 2023 · 1 comment

Comments

@co63oc
Copy link
Contributor

co63oc commented Dec 20, 2023

环境

  • 【FastDeploy版本】: develop版本,安装命令 pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
  • 【编译命令】
  • 【系统平台】: Linux x64(Ubuntu 18.04)
  • 【硬件】: Nvidia GPU V100 32G, CUDA 11.7 CUDNN 8.6
  • 【编译语言】: Python(3.7或3.8等)

问题日志及出现问题的操作流程

  • 附上详细的问题日志有助于快速定位分析
  • 【模型跑不通】
    • 先执行examples下的部署示例,包括使用examples提供的模型,确认是否可以正确执行
    • 如若examples下的代码可以运行,但自己的模型,或自己的代码不能运行
      • 提供复现问题的 代码+模型+错误log,供工程师快速定位问题

PaddlePaddle/PaddleMIX#322 (comment) 升级PaddleMIX代码
代码分支 https://github.com/co63oc/PaddleMIX/tree/attention

使用这里的脚本,参考这里的文档 顺利跑出结果

使用paddle后端可以正常运行
python infer.py --model_dir static_model/stable-diffusion-v1-5 --scheduler "preconfig-euler-ancestral" --backend paddle --device gpu --task_name text2img
使用paddle_tensorrt后端报错
python infer.py --model_dir static_model/stable-diffusion-v1-5 --scheduler "preconfig-euler-ancestral" --backend paddle_tensorrt --device gpu --task_name text2img
错误堆栈为C++错误
创建 CustomSkipLayerNormPluginDynamic 失败
image

@co63oc co63oc closed this as completed Dec 20, 2023
@co63oc co63oc reopened this Dec 20, 2023
@rainyfly
Copy link
Collaborator

rainyfly commented Feb 6, 2024

收到您的反馈,可能是paddle tensorrt对这个的支持还存在点问题,后续找人看下

@co63oc co63oc closed this as completed Dec 12, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants