vlm

SoMarkAI/OXR

+1.9k

An open-source document parsing model with SOTA accuracy and speed, using an RSI loop during post-training.

sglang

+740

SGLang is a high-performance serving framework for large language models and multimodal models.

PixelRAG

+427

https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/

cosmo-edge

+197

Production-grade C++ edge AI engine for video analytics and on-device VLM across Sophon, Rockchip RKNN, and x86, with visual orchestration, real-time OSD, events, and reproducible benchmarks.

transformers

+326

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

GameScaling

+82

Scaling in Games: Continued Pre-Training for Embodied Agents in Diverse Virtual Worlds. Weights on Hugging Face.

tokenspeed

+67

TokenSpeed is a speed-of-light LLM inference engine.

OmniJev/OneJev

+25

🚀🚀 A multimodal System One decision model that gives calibrated answers to typed questions about screens, photos, video and text in one forward pass.

UI-TARS-desktop

+69

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra