10-19-2026, 04:42 AM
A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at INT4. Not glamorous advice, but repeatable baselines save a lot of time.
|
dual GPU split inference
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
dual GPU split inference - by dockworks23 - 10-19-2026, 04:34 AM
Re: dual GPU split inference - by dockkite69 - 10-18-2026, 06:38 PM
Re: dual GPU split inference - by turboyard94 - 10-18-2026, 07:14 PM
Re: dual GPU split inference - by embersmith - 10-18-2026, 07:55 PM
Re: dual GPU split inference - by sanevault - 10-19-2026, 02:19 AM
Re: dual GPU split inference - by flintriver50 - 10-19-2026, 01:30 AM
Re: dual GPU split inference - by rocmriley - 10-19-2026, 01:39 AM
Re: dual GPU split inference - by batchember - 10-19-2026, 03:14 AM
Re: dual GPU split inference - by torchshed - 10-19-2026, 04:42 AM
Re: dual GPU split inference - by rocmriley - 10-19-2026, 04:50 AM
Re: dual GPU split inference - by emberquill - 10-19-2026, 05:15 AM
Re: dual GPU split inference - by quantshed - 10-19-2026, 05:30 AM
|