philipturner / metal-flash-attentionLinks
FlashAttention (Metal Port)
☆520Updated 11 months ago
Alternatives and similar repositories for metal-flash-attention
Users that are interested in metal-flash-attention are comparing it to the libraries listed below
Sorting:
- Efficient framework-agnostic data loading☆432Updated 2 months ago
- Benchmark of Apple MLX operations on all Apple Silicon chips (GPU, CPU) + MPS and CUDA.☆194Updated 2 months ago
- 1.58 Bit LLM on Apple Silicon using MLX☆221Updated last year
- Python bindings for ggml☆146Updated 11 months ago
- Large Language Models (LLMs) applications and tools running on Apple Silicon in real-time with Apple MLX.☆453Updated 6 months ago
- ☆552Updated 9 months ago
- ☆217Updated 7 months ago
- Fast parallel LLM inference for MLX☆206Updated last year
- C API for MLX☆122Updated last month
- Official implementation of Half-Quadratic Quantization (HQQ)☆864Updated this week
- CLI to demonstrate running a large language model (LLM) on Apple Neural Engine.☆115Updated 7 months ago
- Run transformers (incl. LLMs) on the Apple Neural Engine.☆62Updated last year
- LLM-based code completion engine☆194Updated 7 months ago
- On-device Image Generation for Apple Silicon☆646Updated 4 months ago
- SiLLM simplifies the process of training and running Large Language Models (LLMs) on Apple Silicon by leveraging the MLX framework.☆278Updated 2 months ago
- LLM training in simple, raw C/Metal Shading Language☆55Updated last year
- Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".☆277Updated last year
- Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"☆377Updated last year
- GGUF implementation in C as a library and a tools CLI program☆283Updated 7 months ago
- Export Hugging Face models to Core ML and TensorFlow Lite☆669Updated last year
- Apple GPU microarchitecture☆547Updated 11 months ago
- FastMLX is a high performance production ready API to host MLX models.☆324Updated 5 months ago
- An implementation of bucketMul LLM inference☆222Updated last year
- scalable and robust tree-based speculative decoding algorithm☆355Updated 6 months ago
- ☆55Updated 2 years ago
- llama3.cuda is a pure C/CUDA implementation for Llama 3 model.☆341Updated 3 months ago
- Convert StableHLO models into Apple Core ML format☆19Updated 3 weeks ago
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆652Updated 3 months ago
- Find out why your CoreML model isn't running on the Neural Engine!☆25Updated last year
- Inference of Mamba models in pure C☆190Updated last year