llama.cpp/llama.cpp at f647ce040ff06348d2ceaa5443a6a7a8b80c70c9

mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-05-15 05:24:06 +00:00

Files

Evan Jones e216aa0463 llama : only copy used KV cache in get / set state (#1272 )

* llama : only copy used KV cache in get / set state

* switch to ggml for copying k, v

* avoid designated initializers

2023-05-02 22:26:13 -04:00

View Raw