SpecBundle Collection A collection of production-grade draft models for speculative decoding • 18 items • Updated 2 days ago • 17
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads Paper • 2401.10774 • Published Jan 19, 2024 • 60
Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models Paper • 2312.06585 • Published Dec 11, 2023 • 29
Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Code Paper • 2311.07989 • Published Nov 14, 2023 • 26
