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

TritonModelException: inference request batch-size must be <= 128 for 'cls_pp' #12135

Open
sheiy opened this issue May 17, 2024 · 3 comments
Open
Assignees

Comments

@sheiy
Copy link
Contributor

sheiy commented May 17, 2024

  • 系统环境/System Environment:
  • 版本号/Version:Paddle:
  • PaddleOCR: 问题相关组件/Related components:
  • 运行指令/Command Code:
FROM registry.baidubce.com/paddlepaddle/fastdeploy:1.0.7-gpu-cuda11.4-trt8.5-21.10
COPY ./models-gpu.tar /ocr_serving/
WORKDIR /ocr_serving
RUN tar -xf models-gpu.tar
RUN rm models-gpu.tar
EXPOSE 8000
CMD ["fastdeployserver","--model-repository=/ocr_serving/models"]

  • 完整报错/Complete Error Message:
image image
@sheiy
Copy link
Contributor Author

sheiy commented May 17, 2024

麻烦问下 需要怎么处理啊 直接修改配置吗?这个max_batch_size是什么意思?我只传了一张图
改了这个batchSize直接启动不了了
image

image

@zhangyubo0722
Copy link
Collaborator

OCR套件并不支持Triton部署,请问你是在哪里看到的命令或文档呢

@sheiy
Copy link
Contributor Author

sheiy commented May 24, 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