Tencent / TurboTransformers

a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.
Other
1.47k stars 197 forks source link

RuntimeError: code is not compiled with CUDA. #258

Open zhanghaoie opened 2 years ago

zhanghaoie commented 2 years ago

跑完build_and_run_unitest,unittest都pass了,但是运行benchmark gpu_fixed的时候,报code is not compiled with CUDA。

feifeibear commented 2 years ago

README写了,编译时候应该 cmake .. -DWITH_GPU=ON,或者你下载成了cpu-only的镜像了

zhanghaoie commented 2 years ago

sh tools/build_and_run_unittests.sh $PWD -DWITH_GPU=ON 按照readme运行的这个指令,难道这个不是支持gpu的吗?

zhanghaoie commented 2 years ago

按照gpu docker的方式编译的,应该没什么问题的。。。