AJ Isaacs cf88f003ba Add LLM warm-up request at startup to preload model into VRAM ...

Sends a minimal 1-token completion during setup_hook so the model is
ready before Discord messages start arriving, avoiding connection
errors and slow first responses after a restart.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-02-21 15:16:52 -05:00

7.1 KiB

Raw Blame History

View Raw