Pinned Loading

1. CLI to demonstrate running a large language model (LLM) on Apple Neural Engine.

   Swift 126 12

2. See the device (CPU/GPU/ANE) and estimated cost for every layer in your CoreML model.

   Swift 25 3

3. ModernBERT model optimized for Apple Neural Engine.

   Python 31 2

4. Run transformers (incl. LLMs) on the Apple Neural Engine.

   Python 62 2

5. Unofficial implementation of Token Recycling self-speculative decoding method.

   Python 9 1

6. GPU Adaptive Non-Uniform Quantization (GANQ) Unofficial Implementation

   Python 5