FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language Paper • 2506.20920 • Published Jun 26 • 70
OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning Paper • 2506.00338 • Published May 31 • 10
view changelog Changelog Xet is now the default storage option for new users and organizations May 23 • 73
view article Article Speeding Up LLM Decoding with Advanced Universal Assisted Generation Techniques By jmamou and 8 others • Mar 24 • 20
view article Article FastRTC: The Real-Time Communication Library for Python By freddyaboulton and 1 other • Feb 25 • 172
Running 3.16k 3.16k The Ultra-Scale Playbook 🌌 The ultimate guide to training LLM on large GPU Clusters
view article Article KV Caching Explained: Optimizing Transformer Inference Efficiency By not-lain • Jan 30 • 128
view article Article How biased is Whisper ? Evaluating Whisper Models for Robustness to Diverse English Accents By Steveeeeeeen • Jan 29 • 17