AidanBeltonS fadde67135 Dequant improvements rebase (#8255) ...

* Single load for half2

* Store scales in local mem

* Vec load quantized values

2024-07-03 09:55:34 +08:00

..

cmake

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

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

include

Removes multiple newlines at the end of files that is breaking the editorconfig step of CI. (#8258)

2024-07-02 12:18:10 -04:00

src

Dequant improvements rebase (#8255)

2024-07-03 09:55:34 +08:00

CMakeLists.txt

ggml : add GGML_CUDA_USE_GRAPHS option, restore GGML_CUDA_FORCE_CUBLAS (cmake) (#8140)

2024-06-26 21:34:14 +02:00

ggml_vk_generate_shaders.py

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

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