diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2025-05-30 11:08:17 +0300 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-05-30 11:08:17 +0300 |
| commit | 2cf12eb12dcd82cdfe4785c1bcd8dc6255621790 (patch) | |
| tree | cdc0ef9735f95594ae96272760ce3495ae4a0921 /gguf-py/scripts | |
| parent | 1eac9e8487646ee7af00d6d91e10c0cc21ab38c1 (diff) | |
Replace MLA-specific KV cache with the standard KV cache (#469)
* Remove kv_l, kvt_l and just use k_l and v_l
* Hopefully take care of missing V cache (MLA)
* Replace MLA-specific KV cache with the standard KV cache V2 (#473)
* Fix save and restore when there is no V cache
* Fix double print
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Co-authored-by: saood06 <saood05@gmail.com>
Diffstat (limited to 'gguf-py/scripts')
0 files changed, 0 insertions, 0 deletions