Serving

Serving copied to clipboard

pipeline的detection demo一个都没跑通？

1

paddle相关安装包如下： /home/pdemo pip3 list|grep paddle grep: warning: GREP_OPTIONS is deprecated; please use an alias or script paddle-bfloat 0.1.7 paddle-serving-app 0.9.0 paddle-serving-client 0.9.0 paddle-serving-server-gpu 0.9.0.post112 paddlepaddle-gpu 2.4.2.post112 以/Serving/tree/v0.9.0/examples/Pipeline/ppyolo_mbv3/为例，web_service.py输出如下： grep: warning: GREP_OPTIONS...

tommyfgj

PaddleOCR C++ Serving core dump!!!

2

paddleocr的serving部署方式下，发起预测触发core dump报错  环境： `docker image:paddlepaddle/paddle:2.4.2-gpu-cuda11.2-cudnn8.2-trt8.0` 驱动信息：  ``` paddle版本： paddle-bfloat 0.1.2 paddle-serving-app 0.9.0 paddle-serving-client 0.9.0 paddle-serving-server-gpu 0.9.0.post112 paddlepaddle-gpu 2.3.0.post112 ``` 运行参数 ``` Dir：Serving/examples/C++/PaddleOCR/ocr serving：python3 -m paddle_serving_server.serve --model ocr_det_model ocr_rec_model...

yuanhaisu

部署paddlenlp的mbart模型报错

2

python -m paddle_serving_server.serve --model SERVING_SERVER_DIR --thread 10 --port 9393 --gpu_id 0 执行上面命令报以下错误 Error Message Summary: ---------------------- NotFoundError: Operator (fusion_mbart_decoding) is not registered. [Hint: op_info_ptr should not be null.] (at /paddle/paddle/fluid/framework/op_info.h:151)

Amy234543

多个独立模型启动serving服务

1

paddle-serving-app 0.9.0 paddle-serving-client 0.9.0 paddle-serving-server 0.9.0 paddlepaddle 2.4.2 Linux ubuntu 20.04 你好，我现在有100个独立的模型，我想为这100个独立的模型同时启动推理服务，我尝试了pipline和web service,但是还是占用资源太大了，模型本身并不大，只是模型之外的框架解释器之类的占用太多了，我应该怎末启动服务才能最节省内存资源？期待您的回复

gitmhg

【急急急！！！】InvalidArgumentError: Broadcast dimension mismatch. 使用window做客户端，centos为服务端 ，输入尺寸问题

1

InvalidArgumentError: Broadcast dimension mismatch. Operands could not be broadcast together with the shape of X = [1, 361, 1024] and the shape of Y = [1, 400, 1024]. Received [361]...

whisky-12

paddleserving可以只当一个服务接口用吗？

1

我想将fasttext用paddleserving部署，只是借用paddleserving的高并发处理能力，不知道该怎么部署，能指点下吗？

ingale726

serving的重大bug

3

当serving的server端接收到client发送的数据转换不成所需要的数据类型时，server会自动退出，这种bug不可理喻！

whtwhtw

在ma c上运行Serving/examples/Pipeline/PaddleDetection/faster_rcnn异常

2

``` paddle_serving_server.pipeline.error_catch.CustomException: exception_code: 3003 exception_type: INIT_ERROR error_msg: pipeline server init error is_send_to_user: False Traceback (most recent call last): File "web_service.py", line 77, in fasterrcnn_service.run_service() File "/Users/geng/opt/miniconda3/envs/ppdet/lib/python3.8/site-packages/paddle_serving_server/web_service.py", line 69, in run_service...

ddgetget

Adding table recognition model to pdserving

1

Hi, The quick start document shows deployment of paddleocr detection and recognition models. Is it possible to deploy table recognition model as well ? following similar steps as for det...

Tanmay98

docker镜像编译失败啊

4

我用 serving的docker镜像编译serving竟然编译失败了！我使用的镜像是 registry.baidubce.com/paddlepaddle/serving:0.9.0-devel 这是我的日志 [编译.txt](https://github.com/PaddlePaddle/Serving/files/10799546/default.txt)

liuwqiang