Posts: 10.551
Threads: 57
Joined: May 2017
30.01.2023, 21:28
(This post was last modified: 30.01.2023, 21:38 by Selur.)
Send you links to my current version.
Do these work for you?
Do you still get the non-printable character error?
Cu Selur
Ps.: removing all the whitespace does not fix the crash here when I enable trt.
----
Dev versions are in the 'experimental'-folder of my GoogleDrive, which is linked on the download page.
Posts: 10.551
Threads: 57
Joined: May 2017
Found a fix, adding:
os.environ["CUDA_MODULE_LOADING"] = "LAZY"
to the script seems to fix my issue.
-> will compile and upload a new dev and send you a link.
Cu Selur
----
Dev versions are in the 'experimental'-folder of my GoogleDrive, which is linked on the download page.
Posts: 738
Threads: 70
Joined: Feb 2020
Hello Selur,
the dev version Hybrid_dev_2023.01.30-201642.exe that you sent, is working for me.
Thanks,
Dan
Posts: 10.551
Threads: 57
Joined: May 2017
Happy that, that version works for you.
Okay, strange that I need the lazy loading thing.
Cu Selur
----
Dev versions are in the 'experimental'-folder of my GoogleDrive, which is linked on the download page.
Posts: 738
Threads: 70
Joined: Feb 2020
Hello Selur,
I simple way to check if there are strange issues in the script is to call:
vspipe --info "script.vpy"
If the output starts with "
Width:" it's all Ok, otherwise it is probable that there are issues not allowing vspipe.exe to work.
I guess that vsViewer is not using vspipe and its implementation is working better.
Dan
Hello Selur,
I'm already using
'CUDA_MODULE_LOADING=LAZY'
see my post:
https://forum.selur.net/thread-2989-post...l#pid17521
Dan
Posts: 27
Threads: 1
Joined: Nov 2022
Dear Selur.
I have the same problem. Can you send a link to
new dev version. Thanks.
Posts: 10.551
Threads: 57
Joined: May 2017
send you a link.
Cu Selur
----
Dev versions are in the 'experimental'-folder of my GoogleDrive, which is linked on the download page.
Posts: 738
Threads: 70
Joined: Feb 2020
Hello Selur,
I noted that in the last dev version was added the support to FeMaSR. I'd like to try it, but I noted that the Streams box is locked to "1", so that I can't increase the number of Streams. It is possible to enable this box ?
Thanks,
Dan
Posts: 10.551
Threads: 57
Joined: May 2017
Ah, atm. you need to enable CUDA Graph to increase the stream count.
----
Dev versions are in the 'experimental'-folder of my GoogleDrive, which is linked on the download page.
Posts: 738
Threads: 70
Joined: Feb 2020
It is strange, usually the streams are supported with RT.
In any case even if I enable CUDA graph and increase the number of streams, this number is not passed in input to the function.
The generated code is the following
clip = FeMaSR(clip=clip, model=0, device_index=0, trt=False, nvfuser=False, cuda_graphs=True)
