v0.32.3-rc0: model: align Laguna with upstream llama.cpp (#17335)
🔒
https://github.com
«Update llama.cpp to pick up upstream Laguna implementation and remove Ollama's local Laguna implementation. Retain a narrow Metal-only scaling workaround for routed-MoE prompt overflow.
Translate older Ollama GGUF attent...»
Automatische Weiterleitung...
1.5s