philipturner / metal-flash-attentionLinks
FlashAttention (Metal Port)
☆512Updated 10 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☆430Updated last month
- ☆549Updated 9 months ago
- Python bindings for ggml☆142Updated 11 months ago
- Benchmark of Apple MLX operations on all Apple Silicon chips (GPU, CPU) + MPS and CUDA.☆190Updated last month
- ☆214Updated 6 months ago
- 1.58 Bit LLM on Apple Silicon using MLX☆217Updated last year
- Large Language Models (LLMs) applications and tools running on Apple Silicon in real-time with Apple MLX.☆451Updated 6 months ago
- Run transformers (incl. LLMs) on the Apple Neural Engine.☆61Updated last year
- Official implementation of Half-Quadratic Quantization (HQQ)☆855Updated this week
- Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".☆277Updated last year
- Fast parallel LLM inference for MLX☆203Updated last year
- On-device Image Generation for Apple Silicon☆636Updated 3 months ago
- LLM-based code completion engine☆193Updated 6 months ago
- Inference of Mamba models in pure C☆189Updated last year
- ☆55Updated 2 years ago
- SiLLM simplifies the process of training and running Large Language Models (LLMs) on Apple Silicon by leveraging the MLX framework.☆275Updated last month
- Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"☆376Updated last year
- C API for MLX☆121Updated 3 weeks ago
- An efficent implementation of the method proposed in "The Era of 1-bit LLMs"☆154Updated 9 months ago
- An implementation of bucketMul LLM inference☆221Updated last year
- FastMLX is a high performance production ready API to host MLX models.☆319Updated 4 months ago
- Start a server from the MLX library.☆188Updated last year
- scalable and robust tree-based speculative decoding algorithm☆351Updated 6 months ago
- ☆183Updated 4 months ago
- CLIP inference in plain C/C++ with no extra dependencies☆514Updated last month
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆649Updated 3 months ago
- Explore a simple example of utilizing MLX for RAG application running locally on your Apple Silicon device.☆172Updated last year
- ☆556Updated 11 months ago
- MLX support for the Open Neural Network Exchange (ONNX)☆55Updated last year
- LLM training in simple, raw C/Metal Shading Language☆57Updated last year