jiahao he
jiahao he
Hello, I am glad to contact you about sitediff toolchain. I try to exploit sitediff in my project to compare two pages that both have been stored in disk locally....
Hi, I want to use JPype to call java lib in my python project. In my project, there are there py model as follow: 1. utilities.py, which call the function...
I used radare-extras to debug the evm bytecode. However, when the contract A enter another contract B through delegatecall opcode, the Disassembly panel display A bytecode but not B bytecdoe....
错误信息如下： python/CMakeFiles/paddle_python.dir/build.make:75: recipe for target '.timestamp' failed make[2]: *** [.timestamp] Error 1 CMakeFiles/Makefile2:1669: recipe for target 'python/CMakeFiles/paddle_python.dir/all' failed make[1]: *** [python/CMakeFiles/paddle_python.dir/all] Error 2 Makefile:129: recipe for target 'all' failed make:...
参考[doc/Compile_CN.md](https://github.com/PaddlePaddle/Serving/blob/v0.8.3/doc/Compile_CN.md)文档尝试编译Serving，一直失败，错误信息如下： python/CMakeFiles/paddle_python.dir/build.make:75: recipe for target '.timestamp' failed make[2]: *** [.timestamp] Error 1 CMakeFiles/Makefile2:1669: recipe for target 'python/CMakeFiles/paddle_python.dir/all' failed make[1]: *** [python/CMakeFiles/paddle_python.dir/all] Error 2 Makefile:129: recipe for target 'all' failed make:...
按照官方文档部署ppOCRv3 fastdeploy服务，使用jmeter压测性能一直卡在10QPS左右，修改instance_group里面的count数值也没有提高并发。 1. 推理后端使用tensorrt，精度是trt_fp8。 2. 从原有的矩阵输入改成了图片base64输入。 参考文档连接：https://github.com/PaddlePaddle/FastDeploy/blob/develop/examples/vision/ocr/PP-OCR/serving/fastdeploy_serving/README.md 部署环境 【GPU】NVIDIA T4 【docker镜像】fastdeploy:1.0.1-gpu-cuda11.4-trt8.4-21.10