In this blog, we discuss continuous batching, a critical systems-level optimization that improves both throughput and latency under load for LLMs.

LLaVA team presents LLaVA-NeXT, with improved reasoning, OCR, and world knowledge. LLaVA-NeXT even exceeds Gemini Pro on several benchmarks.

Tools for merging pretrained large language models. - arcee-ai/mergekit

Algorithms for outlier, adversarial and drift detection - SeldonIO/alibi-detect

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs - infiniflow/ragflow

Inference Vision Transformer (ViT) in plain C/C++ with ggml - staghado/vit.cpp

In this work, we question the necessity of adaptive gradient methods for training deep neural networks. SGD-SaI is a simple yet effective enhancement to stochastic gradient descent with momentum...

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚ - exo-explore/exo

An OpenAI API compatible API for chat with image input and questions about the images. aka Multimodal. - matatonic/openedai-vision

The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval - parthsarthi03/raptor

The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol. - illuin-tech/colpali

Vision Transformers (ViTs) have shown remarkable performance and scalability across various computer vision tasks. To apply single-scale ViTs to image segmentation, existing methods adopt a...

Self-supervised visual foundation models produce powerful embeddings that achieve remarkable performance on a wide range of downstream tasks. However, unlike vision-language models such as CLIP,...

The ability to predict future outcomes given control actions is fundamental for physical reasoning. However, such predictive models, often called world models, remains challenging to learn and are...