Shenggan Cheng

3 papers National University of Singapore

• ElasticMM: Efficient Multimodal LLMs Serving with Elastic Multimodal Parallelism
• ElasticMM: Efficient Multimodal LLMs Serving with Elastic Multimodal Parallelism
• StarTrail: Concentric Ring Sequence Parallelism for Efficient Near-Infinite-Context Transformer Model Training