10-14-2026, 06:47 PM
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.
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.
Mostly CUDA, sometimes wrong, usually measured