llama.cpp
server: use pos_next instead of n_tokens for m-rope
#22439

Merged

server: use pos_next instead of n_tokens for m-rope #22439

ggerganov merged 1 commit into ggml-org:master from am17an:server-spec-pos-rollback

server: use pos_next instead of n_tokens for m-rope

96b8eabb

am17an requested a review 113 days ago

github-actions added examples

github-actions added server

ngxson approved these changes on 2026-04-27

ggerganov approved these changes on 2026-04-28

ggerganov merged 516e8d7a into master 113 days ago

am17an deleted the server-spec-pos-rollback branch 113 days ago

Reviewers

ggerganov

ngxson

Assignees

No one assigned

Labels

examples server

Milestone

No milestone