model: align Laguna with upstream llama.cpp (#17335)

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 attention-gate and SWA metadata names so existing models continue to load.
This commit is contained in:
Daniel Hiltgen
2026-07-22 17:09:18 -07:00
committed by GitHub
parent efb7e3c55e
commit 1fd1ccf7ad
11 changed files with 134 additions and 387 deletions

View File

@@ -1 +1 @@
b10069
b10091