09-29-2026, 04:44 AM
Ran a quick check on my box. On A6000 with PyTorch, I saw basically the same behavior. I expected the model choice to matter more than it did.
|
ROCm version that finally behaves for Qwen
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
ROCm version that finally behaves for Qwen - by routecraft - 09-26-2026, 11:26 PM
Re: ROCm version that finally behaves for Qwen - by rocmriley - 09-27-2026, 02:12 AM
Re: ROCm version that finally behaves for Qwen - by tensorworks - 09-27-2026, 03:54 AM
Re: ROCm version that finally behaves for Qwen - by macropoint - 09-27-2026, 04:02 PM
Re: ROCm version that finally behaves for Qwen - by dockworks23 - 09-29-2026, 04:44 AM
Re: ROCm version that finally behaves for Qwen - by batchyard - 09-29-2026, 05:15 AM
Re: ROCm version that finally behaves for Qwen - by quantshed - 09-29-2026, 06:49 AM
|
Users browsing this thread: 1 Guest(s)