Francis Couture-Harpin aff96920f9 llama : fix Mamba-2 conv state saving ...

* ggml : make the ggml_mul fast broadcast path more consistently formatted

2024-08-21 18:00:34 -04:00

..

cmake

llama : reorganize source code + improve CMake (#8006)

2024-06-26 18:33:02 +03:00

include

llama : initial Mamba-2 support

2024-08-21 18:00:34 -04:00

src

llama : fix Mamba-2 conv state saving

2024-08-21 18:00:34 -04:00

.gitignore

vulkan : cmake integration (#8119)

2024-07-13 18:12:39 +02:00

CMakeLists.txt

Vulkan Optimizations and Fixes (#8959)

2024-08-14 18:32:53 +02:00