+- 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
HIP kernel compile issue - phasetrack - 10-03-2026
Posting this in case it saves someone else a little time.
I'm helping a small team set up a local workflow. We don't need a giant stack, but we do care about INT4.
Would rather learn from your scars than collect my own all at once.
Re: HIP kernel compile issue - tensorworks - 10-03-2026
I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with FLUX and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.
Re: HIP kernel compile issue - rocmriley - 10-03-2026
Quote:I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with FLUX and compare from there. Not glamorous advice, but
worth checking the driver first.
Re: HIP kernel compile issue - labline - 10-03-2026
Quote:[quote]I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with FLUX and compare from there. Not glamorous advi
Interesting, I hadn't tried that. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: HIP kernel compile issue - quietarch - 10-04-2026
My first guess would be this: 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 - dockworks23 - 10-06-2026
My first guess would be this: On M3 Max, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: HIP kernel compile issue - torchsmith25 - 10-06-2026
That matches what I was seeing. I ended up in about the same place using TensorRT-LLM.
Re: HIP kernel compile issue - thetarunner - 10-07-2026
Quote:That matches what I was seeing. I ended up in about the same place using TensorRT-LLM.
that fixed it for me too.
Re: HIP kernel compile issue - rocmriley - 10-08-2026
Quote:Quote:That matches what I was seeing. I ended up in about the same place using TensorRT-LLM.
A couple things I'd check first. On 4090, 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.
Re: HIP kernel compile issue - rocmmixer - 10-08-2026
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 you know the plain path works, then add the faster path back in piece by piece.