view article Article Introducing SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding 18 days ago • 44
view article Article Introducing SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding 18 days ago • 44
Puzzle: Distillation-Based NAS for Inference-Optimized LLMs Paper • 2411.19146 • Published Nov 28, 2024 • 20