hello nvidia engineering,
was sent here by Lan-Marie and JoAnn. i would like to integrate NIMs into my local aiml playground running off a local Triton Server.
i prefer downloading the models locally and serving them directly from my server. this month i’ll be installing a Synology NAS w enterprise grade drives. I have an RTX 4090 24gb: MB i9 w 128GB of RAM. currently running on a local SSD (temp/dev) but the server (production) will be installed these next few weeks.
please provide resources, tutorials or tutors willing to help me setup an automated pipeline to download NIMs and serve them with Triton.
thank you very much!!!