]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
CUDA: fix MMQ stream-k rounding if ne00 % 128 != 0 (#8311)
authorJohannes Gäßler <redacted>
Fri, 5 Jul 2024 07:05:34 +0000 (09:05 +0200)
committerGitHub <redacted>
Fri, 5 Jul 2024 07:05:34 +0000 (09:05 +0200)
commitbcefa03bc01a41aace2e200ee8e77827d6d39b4f
treeff6fba3b3a9c8a57e9deecb664919eb5d025bbf6
parent5a7447c5692c9e3dde1161e8e69edb76d3d34714
CUDA: fix MMQ stream-k rounding if ne00 % 128 != 0 (#8311)
ggml/src/ggml-cuda/mmq.cuh