git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit

]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit

overview / pkg / ggml / sources / llama.cpp / commit

author	0cc4m <redacted>
	Mon, 3 Jun 2024 08:59:14 +0000 (10:59 +0200)
committer	GitHub <redacted>
	Mon, 3 Jun 2024 08:59:14 +0000 (10:59 +0200)
commit	3d7ebf63123b8652fb7bbecef7ba731202309901
tree	8adfcc3dd20946ece9c0b8d15b131823b24455ae	tree
parent	a10cda58d3199cd85305e0f03a8c6056714ae2e8	commit \| diff

Vulkan Mixture of Experts (MoE) support (#7628)

* Finish Vulkan mul_mat_id implementation

* Add Vulkan sum_rows and div ops

* Fix MUL_MAT_ID matrix matrix shader

* Fix MUL_MAT_ID matrix vector shader dispatch size

* Fix MUL_MAT_ID matrix vector shader and dispatch code

* Update Vulkan CPU offload for MUL_MAT_ID

* Fix crash when using split mode none and setting a main GPU

common/common.cpp		diff \| blob \| history
ggml-vulkan-shaders.hpp		diff \| blob \| history
ggml-vulkan.cpp		diff \| blob \| history
ggml_vk_generate_shaders.py		diff \| blob \| history
llama.cpp		diff \| blob \| history

Packaging of ggml-org/llama.cpp

RSS Atom