]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
CUDA: fix partial offloading for ne0 % 256 != 0 (#8572)
authorJohannes Gäßler <redacted>
Thu, 18 Jul 2024 21:48:47 +0000 (23:48 +0200)
committerGitHub <redacted>
Thu, 18 Jul 2024 21:48:47 +0000 (23:48 +0200)
commita15ef8f8a08e12f9c5162c221e67779e71182073
tree36496a6477171ed2bd2255d54baa081917e27d73
parent705b7ecf60e667ced57c15d67aa86865e3cc7aa7
CUDA: fix partial offloading for ne0 % 256 != 0 (#8572)
ggml/include/ggml-backend.h
ggml/src/ggml-alloc.c
ggml/src/ggml-backend.c
ggml/src/ggml-cuda.cu