10-05-2026, 08:00 PM
Quote:[quote]Ran a quick check on my box. I couldn't reproduce the slowdown until I pushed context much higher. The main thing that moved was latency, not q
Interesting, I hadn't tried that. I ended up in about the same place using SGLang. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
routing beats arguing over one perfect model
