HIP kernel compile issue for Mixtral

[rocmriley]

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. Worth testing the simpler explanation before adopting the more interesting one.

[rocmriley]

I don't think that's the whole story. I've seen people blame prefix caching when the real issue was much more mundane. Could be a workload difference, but I wouldn't generalize too fast from one setup.

[phasetrack]

Maybe, but I had the opposite result. I get why that seems right, but on 7900 XTX the bottleneck felt elsewhere. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.

[rocmriley]

My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Mixtral and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.