apple / ml-ane-transformersLinks
Reference implementation of the Transformer architecture optimized for Apple Neural Engine (ANE)
☆2,656Updated 2 years ago
Alternatives and similar repositories for ml-ane-transformers
Users that are interested in ml-ane-transformers are comparing it to the libraries listed below
Sorting:
- Everything we actually know about the Apple Neural Engine (ANE)☆2,260Updated 6 months ago
- Run LLaMA (and Stanford-Alpaca) inference on Apple Silicon GPUs.☆586Updated 2 years ago
- Swift app demonstrating Core ML Stable Diffusion☆2,711Updated last year
- Llama 2 Everywhere (L2E)☆1,523Updated 3 weeks ago
- Chat with your favourite LLaMA models in a native macOS app☆1,516Updated 2 years ago
- An Extensible Deep Learning Library☆2,247Updated last week
- Simple UI for LLM Model Finetuning☆2,066Updated last year
- Inference Llama 2 in one file of pure 🔥☆2,118Updated last year
- C++ implementation for BLOOM☆809Updated 2 years ago
- ☆1,029Updated last year
- Quantized inference code for LLaMA models☆1,050Updated 2 years ago
- Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.☆3,682Updated last year
- llama and other large language models on iOS and MacOS offline using GGML library.☆1,872Updated this week
- Fork of Facebooks LLaMa model to run on CPU☆772Updated 2 years ago
- ☆1,278Updated last year
- Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Ad…☆6,078Updated 2 months ago
- Numbers every LLM developer should know☆4,260Updated last year
- AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (N…☆4,679Updated this week
- An unnecessarily tiny implementation of GPT-2 in NumPy.☆3,410Updated 2 years ago
- OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset☆7,529Updated 2 years ago
- Running large language models on a single GPU for throughput-oriented scenarios.☆9,368Updated 10 months ago
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆2,499Updated last year
- FlashAttention (Metal Port)☆534Updated last year
- Efficient framework-agnostic data loading☆437Updated this week
- Cramming the training of a (BERT-type) language model into limited compute.☆1,349Updated last year
- LLM papers I'm reading, mostly on inference and model compression☆743Updated last year
- Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)☆1,284Updated 9 months ago
- Examples in the MLX framework☆7,868Updated 2 weeks ago
- Stable Diffusion with Core ML on Apple Silicon☆17,600Updated 2 months ago
- The RedPajama-Data repository contains code for preparing large datasets for training large language models.☆4,813Updated 9 months ago