10-10-2026, 07:47 PM
Maybe, but I had the opposite result. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model.
post logs or it didn't happen
|
ROCm version that finally behaves
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
ROCm version that finally behaves - by thetaember38 - 10-08-2026, 07:28 PM
Re: ROCm version that finally behaves - by benchplease - 10-10-2026, 07:47 PM
Re: ROCm version that finally behaves - by rasterpoint - 10-11-2026, 08:36 AM
Re: ROCm version that finally behaves - by batchyard - 10-11-2026, 10:37 AM
Re: ROCm version that finally behaves - by cozykite - 10-11-2026, 11:14 AM
Re: ROCm version that finally behaves - by northhall88 - 10-12-2026, 11:21 PM
Re: ROCm version that finally behaves - by papermixer4 - 10-13-2026, 02:07 AM
Re: ROCm version that finally behaves - by rocmriley - 10-13-2026, 02:57 AM
Re: ROCm version that finally behaves - by mintquill - 10-14-2026, 03:44 AM
Re: ROCm version that finally behaves - by rocmriley - 10-14-2026, 03:52 PM
Re: ROCm version that finally behaves - by torchsmith25 - 10-15-2026, 04:17 PM
Re: ROCm version that finally behaves - by thetaember38 - 10-15-2026, 04:47 PM
|
Users browsing this thread: 1 Guest(s)