#
Starred repositories
Real-time webcam demo with SmolVLM and llama.cpp server
Samples for CUDA Developers which demonstrates features in CUDA Toolkit
Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, sparsely activated memory layers complement compute-heavy dense f…
Examples for using ONNX Runtime for machine learning inferencing.
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
fullPage plugin by Alvaro Trigo. Create full screen pages fast and simple
AutoRAG: An Open-Source Framework for Retrieval-Augmented Generation (RAG) Evaluation & Optimization with AutoML-Style Automation
Supercharge Your LLM Application Evaluations 🚀
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
Real-time object detector for security cameras, webcams or video files using Golang + Tensorflow + OpenCV
Node.js Redis-based simple and safe work queue
The world's simplest facial recognition api for Python and the command line
Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…
Scale complete ML development with Amazon SageMaker Studio
Finetune Qwen3, Llama 4, TTS, DeepSeek-R1 & Gemma 3 LLMs 2x faster with 70% less memory! 🦥
Tools for merging pretrained large language models.
Simple Contrastive Learning of Korean Sentence Embeddings
Official repository of Evolutionary Optimization of Model Merging Recipes
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
nostaljic / mlx-examples
Forked from ml-explore/mlx-examplesExamples in the MLX framework
FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.