⚡ nano-vLLM: Lightweight, Low-Latency LLM Inference from Scratch
By
•
•
16Agent-to-Agent Communication: Time for Agentic Patterns
By
•
OmniGen2: The Open-Source Contender to FLUX Kontext Has Arrived
By
•
•
1Automated Discovery of High-Performance GPU Kernels with OpenEvolve
By
•
•
22Welcome the NVIDIA Llama Nemotron Nano VLM to Hugging Face Hub
By
and 11 others
•
•
28Understanding Gemma 3n: How MatFormer Gives You Many Models in One
By
•
•
43Accidentally Building an AI Reasoning Research Ecosystem (Or: Can AI Stop Thinking?)
By
•
•
3What Coding Agent Wins?
By
and 1 other
•
•
7Combining Remote Reasoning with Local Models
By
•
•
12Les-Audits-Affaires: The First Comprehensive French Buisness Legal AI Benchmark
By
•
•
2📄 PDF Support in the Hugging Face Dataset Viewer
By
•
•
2Nano-vLLM meets Inference Endpoints
By
•
•
9Introduction to MedVideoCap-55K: A New, Large-Scale, High-Quality Medical Video-Caption Pair Dataset
By
•
•
9The Anthropic Ruling: Why AI Training Just Got Legal (But Piracy Didn't)
By
•
•
10Accelerating AI for Drug Discovery: Ginkgo’s GDPx Functional Genomics and GDPa Antibody Developability Dataset Series
By
and 1 other
•
•
18AI is Just Math: Building Neural Networks on Your Calculator
By
•
•
3DO THEY SEE WHAT WE SEE?
By
•
•
5Why Maybe We're Measuring LLM Compression Wrong
By
•
•
11🤔👀🎬🖥️📖 Kimi-VL-A3B-Thinking-2506: A Quick Navigation
By
and 1 other
•
•
68Adaptive Classifier: Dynamic Text Classification with Continuous Learning
By
•
•
16