mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-05-04 08:04:07 +00:00
* server : fix crash when seq_rm fails for hybrid/recurrent models * server : add allow_processing param to clear_slot
* server : fix crash when seq_rm fails for hybrid/recurrent models * server : add allow_processing param to clear_slot