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>
	Mon, 16 Sep 2024 06:48:24 +0000 (06:48 +0000)
committer	GitHub <redacted>
	Mon, 16 Sep 2024 06:48:24 +0000 (09:48 +0300)
commit	5c3d0f1824714e9a97fc9b06e046eefcb6ecc721
tree	a5ad9dba854abf86e85545e812a177b890a31b0c	tree
parent	0aadac10c7dd704f8285ddf5a63d6f764cb340aa	commit \| diff

ggml : IQ4_NL sgemm + Q4_0 AVX optimization (#9422)

* squashed

readd my iq4_nl sgemm PR https://github.com/ggerganov/llama.cpp/pull/8049

have ggml_vec_dot_q4_0 do two blocks per loop for avx

try out f16c ggml_vec_dot_iq4_nl, but it's not really faster. as per https://github.com/ggerganov/llama.cpp/pull/8549 we can calculate several blocks at a time with no issue

* shuffle

* remove f16c iq4_nl as i cant make it faster than before

ggml/src/ggml-quants.c		diff \| blob \| history
ggml/src/llamafile/sgemm.cpp		diff \| blob \| history

Packaging of ggml-org/llama.cpp

RSS Atom