Jetson still a thing

[thetatinker77]

I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with FLUX and compare from there.

[homelabhenry]

I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with FLUX and compare from there.

I tested this tonight. My result was mixed: first run looked bad, second run looked normal. The surprise was that memory pressure showed up before throughput collapsed.

[batchfield55]

What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at tail latency. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[promptfield]

I tested this tonight. My result was mixed: first run looked bad, second run looked normal. The main thing that moved was latency, not quality.

[homelabhenry]

Thanks, that helps. I ended up in about the same place using vLLM. The biggest change for me was simplifying the stack instead of adding one more optimization layer.

[macrotinker]

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. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

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