]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
CUDA: fix MMQ writeback for int8 tensor cores (#8100)
authorJohannes Gäßler <redacted>
Mon, 24 Jun 2024 20:15:33 +0000 (22:15 +0200)
committerGitHub <redacted>
Mon, 24 Jun 2024 20:15:33 +0000 (22:15 +0200)
commit3b099bcd9cbf2434f90cbe40eba6fa2189ed1d02
treee99258056f08bcbf83766c954b31e2cab624d49f
parenta818f3028d1497a51cb2b8eb7d993ad58784940e
CUDA: fix MMQ writeback for int8 tensor cores (#8100)
ggml-cuda/mmq.cuh