stateLoadFile abstract method

Future<StateLoadResult> stateLoadFile(
  1. int contextHandle,
  2. String path,
  3. int tokenCapacity
)

Restores the KV cache of contextHandle from a file previously written by stateSaveFile. tokenCapacity caps how many tokens the caller is willing to receive — typically the context size of the loaded model. Throws if the file is corrupt or was produced by a different llama.cpp build.

Implementation

Future<StateLoadResult> stateLoadFile(
  int contextHandle,
  String path,
  int tokenCapacity,
);