Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
Tianle Cai, Yuhong Li, Zhengyang Geng, Hongwu Peng, Jason D. Lee, Deming Chen, Tri Dao
Who it is from
- Carnegie Mellon Universityaffiliation declared by the authors, according to OpenAlex
- University of Illinois Urbana-Champaignaffiliation declared by the authors, according to OpenAlex
Other papers from the same organizations
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement LearningGoogle · 1,789 citations
- Medical SAM adapter: Adapting segment anything model for medical image segmentationAgency for Science, Technology and Research · 1,361 citations
- Dynamic 3D Gaussians: Tracking by Persistent Dynamic View SynthesisCarnegie Mellon University · 1,121 citations
- Power Hungry Processing: Watts Driving the Cost of AI Deployment?Carnegie Mellon University · 929 citations
- SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAMCarnegie Mellon University · 921 citations
- VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web TasksCarnegie Mellon University · 912 citations