mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-07-10 21:20:21 +00:00
4f37f51972
* server: accept null sampling params Extend the schema validation to treat a null value as absent, so clients can send null on nullable params (temperature, top_p, ...) to request the server default. This matches the OpenAI spec and the json_value convention used elsewhere. Add has_field() to skip null in the field eval guards. * has_field -> has_value