SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding Paper • 2604.09557 • Published Feb 10 • 9
Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning Paper • 2604.12374 • Published 1 day ago • 12
SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding Paper • 2604.09557 • Published Feb 10 • 9
Puzzle: Distillation-Based NAS for Inference-Optimized LLMs Paper • 2411.19146 • Published Nov 28, 2024 • 20