Skip to content

main : insert bos if no tokens#2727

Merged
klosax merged 3 commits into
ggml-org:masterfrom
klosax:main-ins-fix
Aug 23, 2023
Merged

main : insert bos if no tokens#2727
klosax merged 3 commits into
ggml-org:masterfrom
klosax:main-ins-fix

Conversation

@klosax
Copy link
Copy Markdown
Contributor

@klosax klosax commented Aug 22, 2023

Fixes #2716 #2741 by inserting BOS when there is no prompt tokens.

Comment thread examples/main/main.cpp Outdated
Comment thread examples/main/main.cpp Outdated
@klosax klosax merged commit 5290c38 into ggml-org:master Aug 23, 2023
@klosax klosax deleted the main-ins-fix branch August 23, 2023 14:46
Seunghhon pushed a commit to Seunghhon/llama.cpp that referenced this pull request Apr 26, 2026
* main.cpp : insert bos if no tokens

* Update examples/main/main.cpp

* Update examples/main/main.cpp

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
phuongncn pushed a commit to phuongncn/llama.cpp-gx10-dgx-sparks-deepseekv4 that referenced this pull request Apr 28, 2026
* main.cpp : insert bos if no tokens

* Update examples/main/main.cpp

* Update examples/main/main.cpp

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
ljubomirj pushed a commit to ljubomirj/llama.cpp that referenced this pull request May 6, 2026
* main.cpp : insert bos if no tokens

* Update examples/main/main.cpp

* Update examples/main/main.cpp

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

GGUF converted model won't inference when --instruct is set. ./main GGUF CUBLAS allocating GPU memory but not using it

2 participants