]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/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>
Sun, 16 Jun 2024 15:19:48 +0000 (18:19 +0300)
commita99e213a82a1af87b18536915d149b99f2144ec7
tree30161b7ffa369edfb94e2f5b1d90ec4bef1b5afd
parent7483d2b61cd534e01c433ae059519fd0b909b50a
CUDA: int8 tensor cores for MMQ (q4_K, q5_K, q6_K) (llama/7860)
ggml-cuda/mma.cuh
ggml-cuda/mmq.cuh