+- 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: HIP kernel compile issue (/showthread.php?tid=706)
Pages:
1
2
Re: HIP kernel compile issue - rocmriley - 10-08-2026
Quote:What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at VRAM headroom. Once y
I think the bottleneck is somewhere else. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Could be a workload difference, but I wouldn't generalize too fast from one setup.
Re: HIP kernel compile issue - quantshed - 10-08-2026
Can you fill in a bit more context? What model, what runtime, and roughly what context size?
Re: HIP kernel compile issue - rocmmixer - 10-09-2026
I'd start with the simpler stack.
Re: HIP kernel compile issue - thetatinker77 - 10-10-2026
That matches what I was seeing. The pattern around embeddings has been pretty similar for me.
Re: HIP kernel compile issue - thetashed24 - 10-10-2026
I don't think that's the whole story. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.