+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Inference Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=9)
+--- Forum: Other Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=39)
+--- Thread: prefill bottlenecks on longer prompts (/showthread.php?tid=696)
prefill bottlenecks on longer prompts - llm_wren - 10-04-2026
This keeps coming up in conversation so I figured I'd start a thread.
The more I work with local setups, the more it seems like quant drift decides everything downstream.
Curious whether that lines up with what other people are seeing.
My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.
Re: prefill bottlenecks on longer prompts - macropilot - 10-05-2026
Quote:This keeps coming up in conversation so I figured I'd start a thread.
Did a small comparison this afternoon. The issue went away once I changed one setting and restarted the stack cleanly.
Re: prefill bottlenecks on longer prompts - vrambandit - 10-07-2026
worth checking the driver first.