]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 31d2b5f)
Fixed WSL cuda's OOM error (#1594)
authorKyle Liang <redacted>
Sun, 11 Jun 2023 13:20:52 +0000 (21:20 +0800)
committerGitHub <redacted>
Sun, 11 Jun 2023 13:20:52 +0000 (15:20 +0200)
commit12b063f0ecf280e98028e444fc492ee6222cdcdc
tree5833ace805c7f035356b7b5ff7ee14d12ecadf11tree
parent31d2b5f4a4bae081e59b36ab37c6ff6f5b5940adcommit | diff
Fixed WSL cuda's OOM error (#1594)

* In the function , add the cuda error bypass.

* remove excessive codes and prints

---------

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