Decoder Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads Paper • 2401.10774 • Published Jan 19, 2024 • 55
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads Paper • 2401.10774 • Published Jan 19, 2024 • 55
video MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding Paper • 2404.05726 • Published Apr 8, 2024 • 22
MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding Paper • 2404.05726 • Published Apr 8, 2024 • 22
