RT by @awnihannun: Batching for vision models is now available in Beta with our latest MLX engine update 👾 (opens in new tab)

Batching for vision models is now available in Beta with our latest MLX engine update 👾 The updated engine also brings major improvements to caching for faster inference overall. Turn on Developer Mode, choose the beta runtime channel, and select LM Studio MLX v1.8.1. Video