]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
CUDA: mul_mat_vec_q for batch sizes > 1 (llama/5351)
authorJohannes Gäßler <redacted>
Tue, 6 Feb 2024 13:44:06 +0000 (14:44 +0100)
committerGeorgi Gerganov <redacted>
Sat, 10 Feb 2024 07:30:58 +0000 (09:30 +0200)
commit8f5bb5dce581976fc2e4c9d456ecdaebf5e2554d
treece427b07984c4a01876829cdec15b6ede9cbd6a2
parent63d8fce8b57c5e97dd1d42b0d7b8c734df1f263c
CUDA: mul_mat_vec_q for batch sizes > 1 (llama/5351)
src/ggml-cuda.cu