philipturner / metal-flash-attentionLinks
FlashAttention (Metal Port)
☆497Updated 9 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:
- ☆212Updated 4 months ago
- Fast parallel LLM inference for MLX☆192Updated 11 months ago
- Efficient framework-agnostic data loading☆427Updated 2 weeks ago
- ☆541Updated 7 months ago
- Large Language Models (LLMs) applications and tools running on Apple Silicon in real-time with Apple MLX.☆446Updated 4 months ago
- On-device Image Generation for Apple Silicon☆625Updated 2 months ago
- FastMLX is a high performance production ready API to host MLX models.☆308Updated 3 months ago
- 1.58 Bit LLM on Apple Silicon using MLX☆213Updated last year
- Run transformers (incl. LLMs) on the Apple Neural Engine.☆61Updated last year
- Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".☆277Updated last year
- Official implementation of Half-Quadratic Quantization (HQQ)☆832Updated this week
- Benchmark of Apple MLX operations on all Apple Silicon chips (GPU, CPU) + MPS and CUDA.☆183Updated 2 weeks ago
- An implementation of bucketMul LLM inference☆217Updated 11 months ago
- Inference of Mamba models in pure C☆187Updated last year
- C API for MLX☆115Updated last month
- SiLLM simplifies the process of training and running Large Language Models (LLMs) on Apple Silicon by leveraging the MLX framework.☆273Updated last week
- Python bindings for ggml☆141Updated 9 months ago
- ☆176Updated 3 months ago
- Phi-3.5 for Mac: Locally-run Vision and Language Models for Apple Silicon☆268Updated 9 months ago
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆643Updated last month
- Apple GPU microarchitecture☆526Updated 9 months ago
- MLX-Embeddings is the best package for running Vision and Language Embedding models locally on your Mac using MLX.☆173Updated 3 weeks ago
- Apple MLX engine for LM Studio☆618Updated last month
- LLM-based code completion engine☆194Updated 5 months ago
- An efficent implementation of the method proposed in "The Era of 1-bit LLMs"☆154Updated 8 months ago
- Start a server from the MLX library.☆188Updated 10 months ago
- scalable and robust tree-based speculative decoding algorithm☆348Updated 4 months ago
- ☆317Updated this week
- llama3.cuda is a pure C/CUDA implementation for Llama 3 model.☆332Updated last month
- Comparison of the output quality of quantization methods, using Llama 3, transformers, GGUF, EXL2.☆154Updated last year