]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
CUDA: use MMQ instead of cuBLAS by default (#8075)
authorJohannes Gäßler <redacted>
Mon, 24 Jun 2024 15:43:42 +0000 (17:43 +0200)
committerGitHub <redacted>
Mon, 24 Jun 2024 15:43:42 +0000 (17:43 +0200)
commita818f3028d1497a51cb2b8eb7d993ad58784940e
treed9e8d6e15813cbe17ba2dcf2cfa70dabf78d8e90
parentd62e4aaa02540c89be8b59426340b909d02bbc9e
CUDA: use MMQ instead of cuBLAS by default (#8075)
CMakeLists.txt
Makefile
README.md
ggml-cuda.cu
ggml-cuda/common.cuh
ggml-cuda/mmq.cu
ggml-cuda/mmq.cuh
ggml-cuda/mmvq.cuh