latest release actually worth attention with SGLang

[phaseshed]

I'm trying to sanity-check my setup.

I'm mostly working with FLUX in PyTorch on mini PC. The part I'm trying to understand is router policy.

Would appreciate practical advice rather than theory.

[fastlab]

Did a small comparison this afternoon. 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.

[emberquill]

worth checking the driver first.

[kernelhouse70]

Good point. The pattern around embeddings has been pretty similar for me. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[vectorpoint]

I'd approach it in a boring order. If you're on vLLM, I'd confirm the version first and then reduce variables until the behavior is obvious.

[audiopoint18]

Did a small comparison this afternoon. My result was mixed: first run looked bad, second run looked normal. I expected the model choice to matter more than it did.

[nanogarden]

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

[modbench]

worth checking the driver first.

[deepseeked]

I'd approach it in a boring order. On A6000, the easiest win is often to back off the aggressive settings and see whether the problem survives.

[bytestack]

Thanks, that helps. That matches what I saw on M3 Max.