madewithlaya

Catalog / Tools & apps

0007X posts

Laya on CoreML: 99.5% of ops on the Apple Neural Engine

FluidInference ported Laya to CoreML with 99.5% of ops running on the ANE and benchmarked it at 3.7 ms per decision on an M5 Pro.

Open source ↗ x.comcostfree, localtime3.7 ms / decision on M5 Pro

Also filed under Tools & apps

  1. 0005

    laya-mlx plays Snake at 60 decisions per second★

    介绍比Jev快50倍，在你设备上跑的laya-mlx! 只在你的设备上占用最高1G内存 Laya是一个开源的类似于Jev的,基于文本输出概率的分类系统 我将其移植到MLX,并且做了一些性能优化! 视频中就是这个模型在我的本地M3Max上玩贪吃蛇 这个模型能够以每秒决策60次的速度玩贪吃蛇！ https://t.co/31KGUiNunb

    @mizorewww · Tools & apps · free, local · 60 decisions/s

  2. 0013

    Laya exported to ONNX

    ONNX export of the Laya checkpoint so it runs anywhere onnxruntime does, including browsers and edge boxes. An fp16 variant followed a day later.

    Mattepiu · Tools & apps

  3. 0010

    Laya-mlx tied with a custom JAX build on a local game benchmark

    The problem isn't the models, it's how you define the problem space, design the movements / decisions and optimize for it (batching e.g.) Jev wins for a network-based model any day. Local models tied - Laya-mlx and my custom build Jax. Look at them go.

    @tomhacks · Tools & apps

  4. 0009

    A home-made Snake benchmark: Jev vs Laya-MLX vs Kev-4B

    Jev vs locally running Laya-MLX and Kev-4B I built my own snake benchmark. Jev @typesafeai is running via API. The other models are small alternatives running on very little RAM on my Macbook! Jev seems to deliver the best quality no doubt! After running it for a while 0

    @tobiaswup · Tools & apps