prefill bottlenecks on longer prompts

[llm_wren]

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.

[macropilot]

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.

[vrambandit]

worth checking the driver first.