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	fairydreaming <redacted>
	Thu, 25 Jun 2026 08:06:44 +0000 (10:06 +0200)
committer	GitHub <redacted>
	Thu, 25 Jun 2026 08:06:44 +0000 (10:06 +0200)
commit	f728adab683387b2bdb085b3854a0f3487a13d0a
tree	ca0f16fde1f8f870f3ea21e077dc4e29b2789469	tree
parent	3e61ea0e2f67fd9c76e82aa2aef6f794520f4a75	commit \| diff

ggml : address integer overflows in binary ops CUDA implementation (#24706)

* ggml : address integer overflows in binary ops CUDA implementation

* ggml : add size_t casts to avoid integer overflows

* ggml : add more asserts checking integer overflows in binary ops CUDA implementation

---------

Co-authored-by: Stanisław Szymczyk <redacted>

ggml/src/ggml-cuda/binbcast.cu

diff | blob | history

Packaging of ggml-org/llama.cpp

RSS Atom