mirror of
https://github.com/mudler/LocalAI.git
synced 2026-09-12 22:33:54 -04:00
Clamp requested generation to the usable context after prompt sync while preserving the legacy 256-token fallback for omitted limits. Constrain each speculative MTP cycle to the remaining request budget so accepted tokens cannot advance beyond the visible output limit. Assisted-by: Codex:gpt-5.6-sol Signed-off-by: Claudio Maradonna <git@codeshifter.xyz>