Conventional model compression techniques for LLMs address high memory consumption and slow inference challenges but typically require computationally expensive retraining to preserve accuracy. In contrast, one-shot compression methods eliminate retraining costs, but struggle to achieve accuracy comparable to dense models. This paper presents SLIM, a new one-shot compression framework that holistically integrates hardware-friendly quantization, sparsity, and low-rank approximation into a unified process.

As inference scales to multi-node deployments, disaggregation—splitting inference into distinct phases—offers a promising path to improving the throughput-interactivity Pareto frontier. Despite growing enthusiasm and a surge of open-source efforts, practical deployment of disaggregated serving remains limited due to the complexity of the optimization search space and system-level coordination. In this paper, we present the first systematic study of disaggregated inference at scale, evaluating hundreds of thousands of design points across diverse workloads and hardware configurations.

Long-context capability is critical for multi-modal foundation models, especially for long video understanding. We introduce LongVILA, a full-stack solution for long-context visual-language models by co-designing the algorithm and system. For model training, we upgrade existing VLMs to support long video understanding by incorporating two additional stages, i.e., long context extension and long video supervised fine-tuning. However, training on long video is computationally and memory intensive.