3 accepted papers
Emerging LLM workloads demand extreme mem- ory agility. However, state-of-the-art inference systems (e.g., vLLM) rely on software-defined paging, which sacrifices the contiguous tensor abstraction. This rigid interface exposes fragmen- tation complexity to developers, imposing a se- vere engineering…
Leveraging intrinsic data priors is critical for effective data recovery. However, existing approaches often struggle to achieve theoretical guarantees, strong performance, and computational efficiency simultaneously. In this paper, we introduce a novel Representative Coefficient Correlated Total Va
Recent multimodal large language models (MLLMs) marry modality-specific vision or audio encoders with a shared text decoder. While the encoder is compute- intensive but memory-light, the decoder is the opposite, yet state-of-the-art serving stacks still time-multiplex these complementary kernels, id…