llama.cpp
611aa914
- metal : optimize MoE for large batches (#13388)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
222 days ago
metal : optimize MoE for large batches (#13388) ggml-ci
References
#13388 - metal : optimize MoE for large batches
Author
ggerganov
Parents
0cf6725e
Loading