mirror of
https://github.com/TheTom/turboquant_plus.git
synced 2026-10-23 11:32:33 -05:00
Community feedback: setting iogpu.wired_limit_mb above 90% of physical RAM risks kernel panics under sustained inference load. 90% is now the recommended safe default. Credit: @treblewoe Co-Authored-By: tturney@psyguard.ai Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>