Iwan Kawrakow 39ef8eeb9d Two things ...

* Use iq2_kl instead of q2_K in the default recipes
* Fine-tune the iq2_ks block scales

2025-07-17 11:25:36 +03:00

..

cmake

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

include

Bump GGML_MAX_CONTEXTS to allow loading more shards (#611)

2025-07-16 14:11:19 +02:00

src

Two things

2025-07-17 11:25:36 +03:00

.gitignore

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

CMakeLists.txt

Add GGML_MAX_CONTEXTS definition in CMakeLists.txt (#622)

2025-07-17 08:50:42 +02:00