]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: f01bd02)
opencl: use `max_alloc_size` in backend ctx instead of querying again (#12705)
authorlhez <redacted>
Thu, 3 Apr 2025 00:01:42 +0000 (17:01 -0700)
committerGitHub <redacted>
Thu, 3 Apr 2025 00:01:42 +0000 (17:01 -0700)
commit97a20c012be2f9bfbeee0209405a31001f93ccf9
tree242f79c636cfe17b929d07fb17df0d965a7da1bctree
parentf01bd02376f919b05ee635f438311be8dfc91d7ccommit | diff
opencl: use `max_alloc_size` in backend ctx instead of querying again (#12705)
ggml/src/ggml-opencl/ggml-opencl.cpp diff | blob | history
Packaging of ggml-org/llama.cpp