News for hackers. Stuff that matters.
Re:GLM-5.2 is the new leading open weights model on Artifici... by meatmanek on Wednesday June 17, 2026 @01:24PM (#48573597)
This is super cool. Do you know if any of the inference backends (llama.cpp, vllm, etc) support this technique?
Re:GLM-5.2 is the new leading open weights model on Artifici... by iaw on Wednesday June 17, 2026 @06:12PM (#48577669)
vLLM supports "banning" certain tokens but I don't know if it can dynamically reduce them.

To my knowledge you can also "ban" with llama.cpp but it is passed in the API call rather than to the server at initialization.