![]() Try to revert current patch and try patch.sh from commit f674380a0b0.It may have different memory requirements from Pascal ones. So, it may be a good first step to try.Įverything worked perfectly smooth and fine with ubuntu 16.04 and 6GB 1060s, same driver.Īs far as I know 1660 is based on Turing architecture and it's NVENC engine pretty much different from 1060 counterpart. If you use -hwaccel cuvid, plain -resize should work on GPU if specified as a decoder option before input file name. ![]() ![]() But I found some info pointing out scale_npp is not needed in your case. Can't say if scale_npp filter is the reason. I'm not quite sure about memory consumption, but I feel like indication may not display all allocated memory or there is something like 2GB memory limit per CUDA process.
0 Comments
Leave a Reply. |