llama.cpp
server: fix regression on streamed non-chat completion w/ stops
#13785
Merged

server: fix regression on streamed non-chat completion w/ stops #13785

ochafik merged 2 commits into ggml-org:master from ochafik:fix-diff-bug2
ochafik
more forgiving message diffs: partial stop words aren't erased, full …
e8f6e335
ochafik ochafik marked this pull request as ready for review 209 days ago
Add (slow) server test for completion + stream + stop
98982bdf
ochafik ochafik requested a review from ngxson ngxson 209 days ago
github-actions github-actions added examples
github-actions github-actions added python
github-actions github-actions added server
ochafik ochafik changed the title server: fix completion diff regression server: fix streamed completion regression 209 days ago
ochafik ochafik changed the title server: fix streamed completion regression server: fix streamed non-chat completion regression 209 days ago
ochafik ochafik changed the title server: fix streamed non-chat completion regression server: fix regression on streamed non-chat completion w/ stops 209 days ago
ochafik ochafik added bugfix
ggerganov
ggerganov approved these changes on 2025-05-26
ochafik ochafik merged f13847cf into master 208 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone