]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
CUDA: int8 tensor cores for MMQ (q4_K, q5_K, q6_K) (llama/7860)
authorJohannes Gäßler <redacted>
Tue, 11 Jun 2024 06:26:07 +0000 (08:26 +0200)
committerGeorgi Gerganov <redacted>
Sat, 15 Jun 2024 19:05:47 +0000 (22:05 +0300)
commita7eefa527475b1a4f3f50fae8ed5728e88f738d0
treeb3e985fa7e964c5cd87622fd14eda4650e26515c
parentc570abcd7fc738220b4d033749fd1b02c5da167d
CUDA: int8 tensor cores for MMQ (q4_K, q5_K, q6_K) (llama/7860)
src/ggml-cuda/mma.cuh
src/ggml-cuda/mmq.cuh