view article Article Introducing SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding 28 days ago • 45
view article Article Introducing SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding 28 days ago • 45
Puzzle: Distillation-Based NAS for Inference-Optimized LLMs Paper • 2411.19146 • Published Nov 28, 2024 • 20
Minitron Collection A family of compressed models obtained via pruning and knowledge distillation • 12 items • Updated about 24 hours ago • 64