]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: b08e75b)
Enable build with CUDA 11.0 (make) (#3132)
authorVlad <redacted>
Sat, 16 Sep 2023 14:55:43 +0000 (17:55 +0300)
committerGitHub <redacted>
Sat, 16 Sep 2023 14:55:43 +0000 (16:55 +0200)
commit5dbc2b3213126a31d3be4ade8ca042cb93019682
tree32562635eca8877925e4ea4e1545162ce63eb473tree
parentb08e75baea294e366628b898e85c0bd359b58115commit | diff
Enable build with CUDA 11.0 (make) (#3132)

* CUDA 11.0 fixes

* Cleaner CUDA/host flags separation

Also renamed GGML_ASSUME into GGML_CUDA_ASSUME
Makefile diff | blob | history
ggml-cuda.cu diff | blob | history
Packaging of ggml-org/llama.cpp