a10ef3eb00
* laguna: compacted sliding-window KV cache (--swa-compress) * llama: fold the model-level ctx-shift gate into get_can_shift --------- Co-authored-by: Joel Farthing <262452229+joelfarthing@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| llama.h | ||