llama.cpp
8c60a8a4 - increase cuda_cpy block size (ggml/996)
Commit
View On GitHub
Commit
2 years ago
increase cuda_cpy block size (ggml/996) Co-authored-by: bssrdf <bssrdf@gmail.com>
Author
bssrdf bssrdf
Committer
ggerganov ggerganov
Parents
9e4a2563
FAQ Terms Privacy Refunds Impressum
Loading