SpecBundle Collection A collection of production-grade draft models for speculative decoding • 14 items • Updated 18 days ago • 13
Running 1.49k Big Code Models Leaderboard 📈 1.49k Explore and compare code generation models on a leaderboard
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads Paper • 2401.10774 • Published Jan 19, 2024 • 59
Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models Paper • 2312.06585 • Published Dec 11, 2023 • 29