mlx
5 stories and discussions about mlx, aggregated from every source we track.
1.
Open-weight GLiNER2.5-Decide in MLX Swift versus TypeSafe’s hosted Jev: what each offers, what the published benchmark compared, and local measurements: 7.6 ms per request at 0.85 GB with INT8.
2.
Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API. - mizorewww/laya-mlx
3.
4.
Single logit inference runtime for all LLM models. Contribute to rreinold/jev-serve development by creating an account on GitHub.
5.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.