Skip to content

Conversation

ggerganov
Copy link
Member

@ggerganov ggerganov commented Aug 28, 2025

  • Enable /slots endpoint by default
  • Remove sensitive information such as prompt, stopping strings, grammar, etc.
  • Update server readme
  • /props now lists which endpoints are enabled

The /slots endpoint can be useful to query the server about various slot properties such as performance, processed tokens, sampling parameters, context length, etc.

@ggerganov ggerganov requested a review from ngxson as a code owner August 28, 2025 08:26
@github-actions github-actions bot added examples python python script changes server labels Aug 28, 2025
@ggerganov ggerganov merged commit 0d161f0 into master Aug 31, 2025
50 checks passed
@ggerganov ggerganov deleted the gg/server-enable-slots-by-default branch August 31, 2025 17:12
@Mushoz
Copy link

Mushoz commented Sep 4, 2025

Is there a way to restore the previous behavior? I am investigating an issue for which I have to inspect the prompt, but at the moment, I cannot. Any ideas?

walidbr pushed a commit to walidbr/llama.cpp that referenced this pull request Sep 7, 2025
* server : enable /slots by default and make it secure

ggml-ci

* server : fix tests to pass `--no-slots` when necessary

* server : extend /props with info about enabled endpoints
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
examples python python script changes server
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants