Jiarui Fang（方佳瑞）
Jiarui Fang（方佳瑞）
例子里应该都处理了吧，encoder和bert类似，改起来很简单。
In your command line set ` export OMP_NUM_THREADS=? `
If you are using onnxrt as backend. The multiple-threading is not managed by OMP env. export MKL_VERBOSE=1. See the number of threads used for GEMM.
没有，因为它们的embedding和bert不一样，所以他们的embedding没有用C++实现，用的pytorch的layer，如果你把它的embedding实现了，就可以全部用C++推理了。
Sorry, I am not familiar with the ViT arch. It has been used in both Encoder and Decoder Transformer architecture, which mainly focused on NLP tasks. If you develop your...
You can manually install the requiremenst in the dockefile on your server.
Hi, could you update your version to the lastest version v0.4.2? If you still need v0.3.0 support, can you give a commit hash id? I am willing to help you...
Hi, I got it. Can you paste your build commands as well as the run scripts which may help me to reproduce the error? I guess you are working on...
Thanks for your report. Compared with my previous results. The QSP of both torch and turbo from your screenshot are not correct. According to a 0418 version, when seq_len 100,...
I have no V100 on hand. Could you please try our previous commit and check if the benchmark results. git reset --hard 64dd569da9ce8bf1f78fcd108356607371b742ed