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	Eve <redacted>
	Tue, 10 Dec 2024 19:33:23 +0000 (19:33 +0000)
committer	GitHub <redacted>
	Tue, 10 Dec 2024 19:33:23 +0000 (20:33 +0100)
commit	dafae66cc242eb766797194d3c85c5e502625623
tree	7296403b7a3bab918376ba272fa12b0592cd320b	tree
parent	ae4b922614d452477cf5d2fb8cad247c9c12596c	commit \| diff

vulkan: dynamic subgroup size for the remaining k quants (#10745)

* q5_k

q4_k

q3_k

q2_k

q6_k multi row example

* revert as multi row isnt faster for k quants

Packaging of ggml-org/llama.cpp

RSS Atom

ggml/src/ggml-vulkan/ggml-vulkan.cpp		diff \| blob \| history
ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_base.comp		diff \| blob \| history
ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_q2_k.comp		diff \| blob \| history
ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_q3_k.comp		diff \| blob \| history
ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_q4_k.comp		diff \| blob \| history
ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_q5_k.comp		diff \| blob \| history