MOOR NEWS
FlexEE: Self-Speculative and KV-Compatible Early Exiting for Offloading-Aware LLM Inference
Research preprint listed by arXiv CS.AI: “FlexEE: Self-Speculative and KV-Compatible Early Exiting for Offloading-Aware LLM Inference”. Review the original paper for the authors’ methods and findings. Sources: 1.