HIP kernel compile issue

[dockworks23]

Spent some time on this today and wanted to compare notes.

I'm comparing two approaches here: keep it simple on mini PC, or squeeze more out of the stack and deal with the complexity.

Interested in tradeoffs more than fan loyalty.

[rocmriley]

What worked for me was pretty simple. 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.

[mangofield33]

What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with FLUX and compare from there. Not glamorous advice,

Interesting, I hadn't tried that. I ended up in about the same place using LM Studio. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[dockworks23]

Tried to reproduce it just now. My result was mixed: first run looked bad, second run looked normal. The main thing that moved was latency, not quality.

[labnest]

Tried to reproduce it just now. My result was mixed: first run looked bad, second run looked normal. The main thing that moved was latency, not qualit

subscribed, curious where this lands.

I'm happy to test one more variant if you want a second data point.

[rocmriley]

What worked for me was pretty simple. If you're on Ollama, 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.

[kernelpeak]

My first guess would be this: On 5090, the easiest win is often to back off the aggressive settings and see whether the problem survives.

[llm_wren]

Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal. The surprise was that memory pressure showed up before throughput collapsed.

[cudascope]

Can you fill in a bit more context? Is this local-only or are you routing anything externally?

[mangofield33]

Can you fill in a bit more context? Are you testing this on 7900 XTX or something else?

There are a few different conversations hiding inside this thread, so being explicit about the goal helps.