Community
qwen: merge tensors on convert pull request merged into llama.cpp
A llama.cpp pull request changes the Qwen converter to merge tensors, which may mean existing GGUF files need reconverting.
Every outlet that ran it 1 article
r/LocalLLaMACommunityLead
qwen: merge tensors on convert by am17an · Pull Request #31028 · ggml-org/llama.cpp