run file I was able to get a successful installation and was able to run deviceQuery once. → CUDA driver version is insufficient for CUDA runtime versionįirst, I am actually using Mint 17.2 (which I also thought was basically 14.04, but maybe not…) When I went back to run deviceQuery as a sanity check, I no longer got information about my device, but the following error:ĬUDA Device Query (Runtime API) version (CUDART static linking) ![]() If cutorch and cunn are installed, your CUDA toolkit may be improperly configured.Ĭheck your CUDA toolkit installation, rebuild cutorch and cunn, and try again. Sadly, after trying to run some code using the torch packages “cutorch” and “cunn” I received this error: (screenshot of successful deviceQuery attached) ![]() First, I am actually using Mint 17.2 (which I also thought was basically 14.04, but maybe not…) Using the. Does anybody know what might be going on here? ![]() However, when I check I have driver 352.41. This seems to say to me that the package thinks I have an older driver. ![]() If I try to install cuda-7-5 and then cuda-runtime-7-5 I finally come up on the error:Ĭuda-runtime-7-5 : Depends: cuda-drivers (>= 352.39) but it is not going to be installed The following packages have unmet dependencies:Ĭuda : Depends: cuda-7-5 (= 7.5-18) but it is not going to be installedĮ: Unable to correct problems, you have held broken packages. The following information may help to resolve the situation: Requested an impossible situation or if you are using the unstableĭistribution that some required packages have not yet been created I am trying to install cuda for a geforce 960 in a machine running ubuntu 14.04 ***edit: Linux Mint 17.2Īfter following all the directions in ‘getting started’ guide I get the following error when running
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |