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	Georgi Gerganov <redacted>
	Fri, 8 Nov 2024 11:47:22 +0000 (13:47 +0200)
committer	GitHub <redacted>
	Fri, 8 Nov 2024 11:47:22 +0000 (13:47 +0200)
commit	841f27abdbbcecc9daac14dc540ba6202e4ffe40
tree	e730910e0d5b9db2926ab8ff415d1034897f5103	tree
parent	d05b3127bd30515955aa4ee2bacdb68ebafe88f4	commit \| diff

metal : optimize FA kernels (#10171)

* ggml : add ggml_flash_attn_ext_get_prec

* metal : use F16 precision in FA kernels

ggml-ci

* metal : minor clean-up

* metal : compile-guard bf16 FA kernels

ggml-ci

* build : remove obsolete compile flag [no ci]

* metal : prevent int overflows [no ci]

* cuda : disable BF16 FA

ggml-ci

* metal : fix BF16 requirement for FA kernels

ggml-ci

* make : clean-up [no ci]

Packaging of ggml-org/llama.cpp

RSS Atom

examples/llama-bench/llama-bench.cpp		diff \| blob \| history
ggml/include/ggml.h		diff \| blob \| history
ggml/src/ggml-cuda.cu		diff \| blob \| history
ggml/src/ggml-cuda/fattn.cu		diff \| blob \| history
ggml/src/ggml-metal.m		diff \| blob \| history
ggml/src/ggml-metal.metal		diff \| blob \| history
ggml/src/ggml.c		diff \| blob \| history
tests/test-backend-ops.cpp		diff \| blob \| history