]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 8c0a10e)
Leverage mmap for offloading tensors to GPU (#1597)
authorHoward Su <redacted>
Mon, 12 Jun 2023 12:44:16 +0000 (20:44 +0800)
committerGitHub <redacted>
Mon, 12 Jun 2023 12:44:16 +0000 (14:44 +0200)
commit58970a4c39124a647ac2a640d9e178ea6c961e65
tree28c041035a12587390b4263667532cb416ce16dctree
parent8c0a10e64dbf60fd9946c0cd5e6f59690800b123commit | diff
Leverage mmap for offloading tensors to GPU (#1597)

* Rebase to latest

* Show progress

* Add assert to make sure we only allocate temp buffer for non-CPU backend tensor

Co-authored-by: Johannes Gäßler <redacted>
---------

Co-authored-by: Johannes Gäßler <redacted>
ggml-cuda.cu diff | blob | history
ggml-cuda.h diff | blob | history
ggml-opencl.cpp diff | blob | history
ggml-opencl.h diff | blob | history
llama.cpp diff | blob | history
Packaging of ggml-org/llama.cpp