Y
Hacker News
new
|
ask
|
show
|
jobs
by
cristoperb
146 days ago
Apparently it is the same as the DeepseekV3 architecture and already supported by llama.cpp once the new name is added. Here's the PR:
https://github.com/ggml-org/llama.cpp/pull/18936
1 comments
khimaros
146 days ago
has been merged
link