- 127comments
- 66comments
- 9comments
- 132comments
- 10comments
- 793comments
- 131comments
- 1014comments
- 2comments
- 35comments
- 2comments
- —discuss
- 27comments
- 110comments
- 46comments
- 22comments
- 248comments
- 411comments
- 11comments
- 7comments
- 223comments
- 12comments
- 530comments
- 61comments
- 167comments
- 519comments
- 153comments
- 31comments
- 112comments
- 396comments
But… why???
created something similar but specific to llama-server. it takes advantage of logprob output and completes decisions in a single forward pass https://github.com/khimaros/verdict