]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 90b19bd)
cuBLAS: fall back to pageable memory if pinned alloc fails (#1233)
authorslaren <redacted>
Mon, 1 May 2023 11:32:22 +0000 (13:32 +0200)
committerGitHub <redacted>
Mon, 1 May 2023 11:32:22 +0000 (13:32 +0200)
commitb925f1f1b082319ee69943f8d1a83ac9b6ff09ca
treecb636a894e6b11918aafce061f3836a24b021e4ftree
parent90b19bd6eee943832584f9cac0b6f9ea29cc42a4commit | diff
cuBLAS: fall back to pageable memory if pinned alloc fails (#1233)

* cuBLAS: fall back to pageable memory if pinned alloc fails

* cuBLAS: do not use pinned memory if env variable GGML_CUDA_NO_PINNED is set
ggml-cuda.cu diff | blob | history
llama-util.h diff | blob | history
llama.cpp diff | blob | history
Packaging of ggml-org/llama.cpp