NVIDIA driver regression with SGLang

[mintforge]

What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with FLUX and compare from there.

[phaseport36]

I tested this tonight. The issue went away once I changed one setting and restarted the stack cleanly. The surprise was that memory pressure showed up before throughput collapsed.

[edgecoast]

Interesting, I hadn't tried that. That matches what I saw on mini PC. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[cacheplane98]

Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal.

[mintforge]

I'd start with the simpler stack.