llama.cpp
c811cb8f
- llama: support MoE cache over multiple GPUs (#30112)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
41 days ago
llama: support MoE cache over multiple GPUs (#30112)
References
#30112 - llama: support MoE cache over multiple GPUs
Author
am17an
Parents
033df86b
Loading