+- 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: worth it? (/showthread.php?tid=618)
Pages:
1
2
HIP kernel compile issue: worth it? - macropoint - 09-30-2026
This keeps coming up in conversation so I figured I'd start a thread.
The more I work with local setups, the more it seems like small local stacks decides everything downstream.
Curious whether that lines up with what other people are seeing.
Re: HIP kernel compile issue: worth it? - rocmriley - 10-01-2026
Interesting, I hadn't tried that. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: HIP kernel compile issue: worth it? - quantshed - 10-01-2026
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Kimi and compare from there.
Re: HIP kernel compile issue: worth it? - northhall88 - 10-04-2026
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.
Re: HIP kernel compile issue: worth it? - tensorworks - 10-04-2026
Interesting, I hadn't tried that. I ended up in about the same place using TensorRT-LLM. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: HIP kernel compile issue: worth it? - rocmriley - 10-04-2026
Can you fill in a bit more context? Do you see the same thing with a smaller batch or shorter prompt?
Re: HIP kernel compile issue: worth it? - turboyard94 - 10-04-2026
I'd approach it in a boring order. If you're on LM Studio, I'd confirm the version first and then reduce variables until the behavior is obvious. Once you know the plain path works, then add the faster path back in piece by piece.
Re: HIP kernel compile issue: worth it? - mintquill - 10-07-2026
Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal. I expected the model choice to matter more than it did.
Re: HIP kernel compile issue: worth it? - tensorworks - 10-07-2026
Quote:Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal. I expected the model choice to matter more than it d
Maybe, but I had the opposite result. I've seen people blame VRAM headroom when the real issue was much more mundane. Worth testing the simpler explanation before adopting the more interesting one.
Re: HIP kernel compile issue: worth it? - cozykite - 10-07-2026
following this because I'm in the same boat.