mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-24 10:24:35 +00:00
Use model->gguf_kv for loading the template instead of using the C API. (#10868)
docker.yml #1512:Scheduled
Use model->gguf_kv for loading the template instead of using the C API. (#10868)
close-issue.yml #1511:Scheduled