Changelog / release

0.10.18 — Bounded prefill memory on long prompts

Upgrade: pip install -U rapid-mlx · brew upgrade rapid-mlx · or grab the desktop app.

Long text-only prompts no longer spike memory. The multimodal batch generator was pushing the entire prompt through the language model in a single forward and projecting logits over every position, peaking around 35 GB on a ~20k-token prompt — enough to max out a 48 GB Mac. Text-only prefill is now chunked to bound peak memory (PR #1193, fixes #1187).