flux pipeline local tips with SGLang

[kernelmike]

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

I've gone back and forth between SGLang and Ollama for Gemma. The interesting difference for me has been workstation thermals.

Trying to avoid rebuilding the whole thing twice.

[tensorworks]

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

I hit almost the same issue last night.

[minthall]

A couple things I'd check first. On A6000, the easiest win is often to back off the aggressive settings and see whether the problem survives.