]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 3b43950)
Fix data race in CUDA's "cpy" kernel (influences GGML's DUP, CONT operations). (...
authorRail Chabdarov <redacted>
Sat, 14 Mar 2026 05:19:44 +0000 (06:19 +0100)
committerGitHub <redacted>
Sat, 14 Mar 2026 05:19:44 +0000 (13:19 +0800)
commit5a32a9b8a5bddf3c6234fd2eb17b0a7315328f93
tree9b4bcec1a308bb59518dd9e0d023ef03ddef0ad7tree
parent3b439504ba49d41c75885d34c1353d195e09e028commit | diff
Fix data race in CUDA's "cpy" kernel (influences GGML's DUP, CONT operations). (#20507)

* Fix datarace in CUDA's "cpy" kernel.

* Remove extra barrier by using more of shared memory.
ggml/src/ggml-cuda/cpy.cu diff | blob | history
Packaging of ggml-org/llama.cpp