]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
CUDA: MMQ support for iq4_nl, iq4_xs (llama/8278)
authorJohannes Gäßler <redacted>
Fri, 5 Jul 2024 07:06:31 +0000 (09:06 +0200)
committerGeorgi Gerganov <redacted>
Mon, 8 Jul 2024 11:53:55 +0000 (14:53 +0300)
commit5dc636a65a6f8f024feff16e4772196acdfba205
treeb71c6f7b0e86f165f150818a5d5c3291fd1d5b07
parent73703a144fd9d14c104932813898352549acd817
CUDA: MMQ support for iq4_nl, iq4_xs (llama/8278)
ggml/src/ggml-cuda/fattn-common.cuh
ggml/src/ggml-cuda/mmq.cu
ggml/src/ggml-cuda/mmq.cuh
ggml/src/ggml-cuda/template-instances/generate_cu_files.py
ggml/src/ggml-cuda/template-instances/mmq-instance-iq4_nl.cu [new file with mode: 0644]
ggml/src/ggml-cuda/template-instances/mmq-instance-iq4_xs.cu [new file with mode: 0644]
ggml/src/ggml-cuda/vecdotq.cuh