fix: reranking models limited to 512 tokens in llama.cpp backend (#6344)
Fix reranking models being limited to 512 tokens input in llama.cpp backend Signed-off-by: JonGames <18472148+jongames@users.noreply.github.com>
J
jongames committed
f2b9452ec4c4f54065248073ed83847080f92990
Parent: 585da99
Committed by GitHub <noreply@github.com>
on 9/25/2025, 11:32:07 PM