]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
CUDA: mul_mat_vec_q max. batch size 8 -> 4 (llama/5370)
authorJohannes Gäßler <redacted>
Tue, 6 Feb 2024 17:43:06 +0000 (18:43 +0100)
committerGeorgi Gerganov <redacted>
Sat, 10 Feb 2024 07:55:47 +0000 (09:55 +0200)
commit77bf6b5f56d2432b231aba50051c15de9ad40405
tree066dfdb7b10180982c43ad5095bfb0f6c46e4fc3
parentb562fff9d05cce50548780ccd9113542d0bee2dd
CUDA: mul_mat_vec_q max. batch size 8 -> 4 (llama/5370)
ggml-cuda.cu