Is your feature request related to a problem? Please describe. I make lots of use of these bindings, but frequently find that new models depend on changes in the upstream llama-cpp project that have ...
Batch processing of embeddings is not supported in this fork yet. See this PR of the original binding which added multi-sequence support for embeddings.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback