Back to AI intel
重点
Ollama v0.31.2-rc2 Enables iGPU MMProj Offload
AI intel briefing
Core summary
One sentence to understand this update
Ollama v0.31.2-rc2 update now allows iGPU multimodal projector offload with fit padding, addressing previous limitations on non-Metal iGPUs.
Impact & opportunity
What this could mean
Ollama users with integrated GPUs will see improved efficiency for multimodal models due to better hardware resource utilization from this update.
Source
View original