Skip to content

fix: wrap generate() in inference_mode() to stop a host-RAM leak from watermarking - #164

Open
malammar wants to merge 1 commit into
devnen:mainfrom
malammar:upstream-pr/watermark-inference-mode
Open

malammar wants to merge 1 commit into
devnen:mainfrom
malammar:upstream-pr/watermark-inference-mode

Commits

  1. Commits on Aug 11, 2026