Hacker News Reader

One thing to consider is that this version is a new architecture, so it’ll take time for Llama CPP to get updated. Similar to how it was with Qwen Next.

View on HN

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

has been merged

Reply on news.ycombinator.com