llama.cpp
server : fix crash when seq_rm fails for hybrid/recurrent models
#18391

Merged

server : fix crash when seq_rm fails for hybrid/recurrent models #18391

ngxson merged 2 commits into ggml-org:master from o7si:issue-18235

server : fix crash when seq_rm fails for hybrid/recurrent models

f5468427

o7si requested a review from

ngxson 29 days ago

o7si requested a review from

ggerganov 29 days ago

github-actions added examples

github-actions added server

ngxson commented on 2025-12-26

server : add allow_processing param to clear_slot

0e8829f1

ngxson approved these changes on 2025-12-26

ngxson merged 4893cc07 into master 29 days ago

Reviewers

ngxson

ggerganov

Assignees

No one assigned

Labels

examples server

Milestone

No milestone