v0.31.2-rc2: llm: allow iGPU mmproj offload with fit padding (#16996)
🔒
https://github.com
«llm: allow iGPU mmproj offload with fit padding
llama.cpp's fit pass sizes text-model placement before the multimodal projector is loaded. Ollama had been avoiding that risk on non-Metal iGPUs by disabling projector off...»
Automatische Weiterleitung...
1.5s