]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 8a79c59)
CUDA: mul_mat_vec_q for batch sizes > 1 (#5351)
authorJohannes Gäßler <redacted>
Tue, 6 Feb 2024 13:44:06 +0000 (14:44 +0100)
committerGitHub <redacted>
Tue, 6 Feb 2024 13:44:06 +0000 (14:44 +0100)
commit2c516611f1d0f1e5e9754f8ea1cf97cb1b17bf2c
tree6e56c323d077e0823f42e291ca27323a4c6e18fdtree
parent8a79c591de9b7ff3242a94f68b7fb5a17ed8c2becommit | diff
CUDA: mul_mat_vec_q for batch sizes > 1 (#5351)
ggml-cuda.cu diff | blob | history
Packaging of ggml-org/llama.cpp