+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Drivers / Frameworks / Toolkits (https://www.datasculpting.ai/inference/forumdisplay.php?fid=8)
+--- Forum: AMD / ROCm (https://www.datasculpting.ai/inference/forumdisplay.php?fid=32)
+--- Thread: is RDNA worth the hassle yet: worth it? (/showthread.php?tid=147)
is RDNA worth the hassle yet: worth it? - torchsmith25 - 09-06-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
Just sharing a setup that ended up working reasonably well: Kimi, TensorRT-LLM, GB200, with a lot of attention on tokens/sec.
If someone wants the exact settings I can clean them up and post them.
Re: is RDNA worth the hassle yet: worth it? - mintquill - 09-06-2026
What worked for me was pretty simple. If you're on TensorRT-LLM, I'd confirm the version first and then reduce variables until the behavior is obvious. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: is RDNA worth the hassle yet: worth it? - rocmriley - 09-07-2026
I'd approach it in a boring order. On A6000, the easiest win is often to back off the aggressive settings and see whether the problem survives. Once you know the plain path works, then add the faster path back in piece by piece.