]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 051e1b0)
Only one CUDA stream per device for async compute (#1898)
authorJohannes Gäßler <redacted>
Sat, 17 Jun 2023 17:15:02 +0000 (19:15 +0200)
committerGitHub <redacted>
Sat, 17 Jun 2023 17:15:02 +0000 (19:15 +0200)
commit2c9380dd2f77e41149340f3ecb09764d793b16db
tree55a8e2cfc2dce879981d9610f499f292a4702b31tree
parent051e1b0e6a6e3aee7d989b47760980e6fda5861ccommit | diff
Only one CUDA stream per device for async compute (#1898)
README.md diff | blob | history
examples/common.cpp diff | blob | history
ggml-cuda.cu diff | blob | history
Packaging of ggml-org/llama.cpp