eryyes

using a Agent and wanted to stream just the final response

16

I am using a Agent and wanted to stream just the final response, do you know if that is supported already? and how to do it?

gpu显存不释放

11

PaddleClasModel 通过gpu启动，后面和教程中的一样，在启动多线程的同时，进行clone()，但是线程执行完后gpu不释放，请问该如何解决？

docker容器部署后，每次调用gpu显存不释放，直到溢出，这个问题有很多issues，但没找到解决方案

3

容器镜像：registry.baidubce.com/paddlepaddle/fastdeploy:1.0.7-gpu-cuda11.4-trt8.5-21.10 调用一万次后，显存直接爆了 W0314 04:50:46.438977 62225 memory.cc:135] Failed to allocate CUDA memory with byte size 79027200 on GPU 1: CNMEM_STATUS_OUT_OF_MEMORY, falling back to pinned system memory 0314 05:01:17.338640 62420 pb_stub.cc:402] Failed...

vgt能否识别中文版面？该如何实现呢？